设为首页收藏本站

VALSE

查看: 6564|回复: 0

ICCV 2015 Main Conference Program 论文列表

[复制链接]
发表于 2015-9-25 12:30:46 | 显示全部楼层 |阅读模式
http://pamitc.org/iccv15/program.php

ICCV 2015 Main Conference Program



  
Orals
  
  
  
  
Multi-task Recurrent Neural Network for Immediacy Prediction
  Xiao Chu*, Wei Yang, Wanli Ouyang, Xiaogang Wang
  
  
  
  
SPM-BP: Sped-up PatchMatch Belief Propagation for Continuous MRFs
  YU LI*, Dongbo Min, Jiangbo Lu, Michael Brown, Minh Do
  
  
  
  
3D Time-Lapse Reconstruction from Internet Photos
  Ricardo Martin*, Steve Seitz, David Gallup
  
  
  
  
Shape Interaction Matrix Revisited and Robustified: Efficient Subspace  Clustering with Corrupted and Incomplete Data
  Pan Ji*, Mathieu Salzmann, Hongdong Li
  
  
  
  
Panoptic Studio: A Massively Multiview System for Social Motion Capture
  Hanbyul Joo*, Hao Liu, Lei Tan, Lin Gui, Shohei Nobuhara, Yaser Sheikh
  
  
  
  
Holistically-Nested Edge Detection
  Saining Xie, Zhuowen Tu*
  
  
  
  
Learning image representations equivariant to ego-motion
  Dinesh Jayaraman*, Kristen Grauman
  
  
  
  
Robust Nonrigid Registration by Convex Optimization
  Qifeng Chen, Vladlen Koltun*
  
  
  
  
Dense Semantic Correspondence where Every Pixel is a Classifier
  Hilton Bristow*, Jack Valmadre, Simon Lucey
  
  
  
  
Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with  Rendered 3D Model Views
  Hao Su*, Charles R. Qi, Leonidas Guibas, Yangyan Li
  
  
  
  
Human Parsing with Contextualized Convolutional Neural Network
  Xiaodan Liang, Chunyan Xu, Xiaohui Shen, Jianchao Yang, Liu Si, jinhui Tang,  Liang Lin*, Shuicheng Yan
  
  
  
  
Weakly supervised graph based semantic segmentation by learning  communities of image-parts
  Niloufar Pourian*, Karthikeyan Shanmuga Vadivel, B.S. Manjunath
  
  
  
  
Learning to Track: Online Multi-Object Tracking by Decision Making
  Yu Xiang*, Alexandre Alahi, Silvio Savarese
  
  
  
  
Learning Complexity-Aware Cascades for Deep Pedestrian Detection
  Zhaowei Cai*, Mohammad Saberian, Nuno Vasconcelos
  
  
  
  
Polarized 3D: High-Quality Depth Sensing with Polarization Cues
  Achuta Kadambi*, Vage Taamazyan, Boxin Shi, Ramesh Raskar
  
  
  
  
Webly Supervised Learning of Convolutional Networks
  Xinlei Chen*, Abhinav Gupta
  
  
  
  
Camera Pose Voting for Large-Scale Image-Based Localization
  Bernhard Zeisl*, Torsten Sattler, Marc Pollefeys
  
  
  
  
Mutual-Structure for Joint Filtering
  Xiaoyong Shen*, Chao Zhou, Li Xu, Jiaya Jia
  
  
  
  
Flow Fields: Dense Unregularized Correspondence Fields for Highly  Accurate Large Displacement Optical Flow Estimation
  Christian Bailer*, Bertram Taetz, Didier Stricker
  
  
  
  
Structured Indoor Modeling
  Yasutaka Furukawa, Hang Yang, Satoshi Ikehata*
  
  
  
  
Web-scale image clustering revisited
  Yannis Avrithis*, Yannis Kalantidis, Evangelos Anagnostopoulos, Ioannis  Emiris
  
  
  
  
Piecewise Flat Embedding for Image Segmentation
  Chaowei Fang, Zicheng Liao, Yizhou Yu*
  
  
  
  
Where to Buy It: Matching Street Clothing Photos in Online Shops
  Mohammadhadi Kiapour*, Xufeng Han, Svetlana Lazebnik, Alex Berg, Tamara Berg
  
  
  
  
Issuing Notifications for Missing Actions: Don't Forget to Turn the  Lights Off!
  Bilge Soran*, Ali Farhadi, Linda Shapiro
  
  
  
  
Semantic Image Labeling via Deep Parsing Network
  Ziwei Liu*, Xiaoxiao Li, Ping Luo, Chen-Change Loy, Xiaoou Tang
  
  
  
  
On the Visibility of Point Clouds
  Sagi Katz, Ayellet Tal*
  
  
  
  
Global, Dense Multiscale Reconstruction for a Billion Points
  Benjamin Ummenhofer*, Thomas Brox
  
  
  
  
Registering Images to Untextured Geometry using Average Shading  Gradients
  Tobias Plötz*, Stefan Roth
  
  
  
  
Training a Feedback Loop for Hand Pose Estimation
  Markus Oberweger*, Paul Wohlhart, Vincent Lepetit
  
  
  
  
Learning Discriminative Reconstructions for Unsupervised Outlier Removal
  Yan Xia*, Xudong Cao, Fang Wen, Gang Hua, Jian Sun
  
  
  
  
Removing rain from a single image via discriminative sparse coding
  Yu Luo, Yong Xu, Hui Ji*
  
  
  
  
Opening the Black Box: Hierarchical Sampling Optimization for Estimating  Human Hand Pose
  Danhang Tang*, Jonathan Taylor, Pushmeet Kohli, Cem Keskin, Tae-Kyun Kim,  Jamie Shotton
  
  
  
  
CV-HAZOP: Introducing Test Data Validation for Computer Vision
  Oliver Zendel*, Markus Murschitz, Martin Humenberger, Wolfgang Herzner
  
  
  
  
Minimum Barrier Salient Object Detection at 80 FPS
  Jianming Zhang*, Stan Sclaroff, Zhe Lin, Xiaohui Shen, Brian Price, Radomir  Mech
  
  
  
  
Multi-Image Matching via Fast Alternating Minimization
  Xiaowei Zhou*, Menglong Zhu, Kostas Danilidiis
  
  
  
  
Low-rank Matrix Factorization under General Mixture Noise Distributions
  Xiangyong Cao*, Yang Chen, Qian Zhao, Deyu Meng, Yao Wang, Dong Wang, Zongben  Xu
  
  
  
  
Partial Person Re-identification
  Wei-Shi Zheng*, Xiang Li, Tao Xiang, Shengcai Liao, Jianhuang Lai, Shaogang  Gong
  
  
  
  
Discovering the Spatial Extent of Relative Attributes
  Fanyi Xiao*, Yong Jae Lee
  
  
  
  
Bilinear CNN Models for Fine-grained Visual Recognition
  Tsung-Yu Lin*, Aruni RoyChowdhury, Subhransu Maji
  
  
  
  
Multiple Hypothesis Tracking Revisited: Blending in Modern Appearance  Model
  Chanho Kim*, Fuxin Li, Arridhana Ciptadi, James Rehg
  
  
  
  
Ask Your Neurons: A Neural-based Approach to Answering Questions about  Images
  Mateusz Malinowski*, Marcus Rohrbach, Mario Fritz
  
  
  
  
Semantic Component Analysis
  Calvin Murdock*, Fernando De la Torre
  
  
  
  
Fast R-CNN
  Ross Girshick*
  
  
  
  
Deep Fried Convnets
  Zichao Yang*, Marcin Moczulski, Misha Denil, Nando Freitas, Alex Smola, Le  Song, Ziyu Wang
  
  
  
  
Aligning Books and Movies: Towards Story-like Visual Explanations by  Watching Movies and Reading Books
  Yukun Zhu*, Ryan Kiros, Rich Zemel, Ruslan salakhutdinov, Raquel Urtasun,  Antonio Torralba, Sanja Fidler
  
  
  
  
Unsupervised Visual Representation Learning by Context Prediction
  Carl Doersch*, Abhinav Gupta, Alexei Efros
  
  
  
  
Lost Shopping! Monocular Localization in Large Indoor Spaces
  Shenlong Wang*, Sanja Fidler, Raquel Urtasun
  
  
  
  
Leave-One-Out Kernel Optimization for Shadow Detection
  Tomas F Yago Vicente*, Minh Hoai, Dimitris Samaras
  
  
  
  
Deep Convolutional Neural Decision Forests
  Madalina Fiterau*, Peter Kontschieder, Antonio Criminisi, Samuel Rota Bulò
  
  
  
  
Uncovering Interactions and Interactors: Joint Estimation of Head, Body  Orientation and F-formations from Surveillance Videos
  Elisa Ricci*, Jagannadan Varadarajan, Ramanathan Subramanian, Samuel Rota  Bulò, Narendra Ahuja, Oswald Lanz
  
  
  
  
Learning Query and Image Similarities with Ranking Canonical Correlation  Analysis
  Ting Yao*, Tao Mei, Chong-Wah Ngo
  
  
  
  
Robust and Optimal SoS-based Point-to-Plane Registration of Image Sets  and Structured Scenes
  Danda Pani Paudel*, Adlane Habed, Cédric Demonceaux, Pascal Vasseur
  
  
  
  
Airborne Three-Dimensional Cloud Tomography
  Aviad Levis*, Amit Aides, Yoav Schechner, Anthony Davis
  
  
  
  
Segment-Phrase Table for Semantic Segmentation, Visual Entailment and  Paraphrasing
  Hamid Izadinia*, Fereshteh Sadeghi, Santosh Kumar Divvala, Hannaneh  Hajishirzi, Yejin Choi, Ali Farhadi
  
  
  
  
3D-Assisted Image Feature Synthesis for Novel Views of an Object
  Hao Su*, Fan Wang, Li Yi, Leonidas Guibas
  
  
  
  
MeshStereo: A Global Stereo Model with Mesh Alignment Regularization for  View Interpolation
  Chi Zhang*, Zhiwei Li, Hongyang CHAO, Rui Cai
  
  
  
  
Posters
  
  
  
  
Attributed Grammars for Joint Estimation of Human Attributes, Part and  Pose
  Seyoung Park*, Song-Chun Zhu
  
  
  
  
Weakly Supervised Learning of Part Detectors for Visual Recognition
  Thibaut Durand*, Nicolas Thome, Matthieu Cord
  
  
  
  
Face Flow
  Patrick Snape*, Anastasios Roussos, Yannis Panagakis, Stefanos Zafeiriou
  
  
  
  
Love Thy Neighbors: Image Annotation by Exploiting Social Metadata
  Lamberto Ballan*, Justin Johnson, Fei-Fei Li
  
  
  
  
Fill and Transfer: A Simple Physics-based Approach for Containability  Reasoning
  Lap-Fai Yu*, Noah Duncan, Sai-Kit Yeung
  
  
  
  
Discriminative Low-Rank Tracking
  Yao Sui*, Yafei Tang, Li Zhang
  
  
  
  
A Groupwise Multilinear Correspondence Optimization for 3D Faces
  Timo Bolkart*, Stefanie Wuhrer
  
  
  
  
Real-Time Pose Estimation Piggybacked on Object Detection
  Roman Juranek, Marketa Dubska*, Adam Herout, Pavel Zemcik
  
  
  
  
On Linear Structure from Motion for Light Field Cameras
  Ole Johannsen, Antonin Sulc, Bastian Goldluecke*
  
  
  
  
Category-blind Human Action Recognition: A Practical Recognition System
  Wenbo Li*, Longyin Wen, Mooi Choo Chuah, Siwei Lyu
  
  
  
  
Learning Affordance for Direct Perception in Autonomous Driving
  Chenyi Chen, Ari Seff, Alain Kornhauser, Jianxiong Xiao*
  
  
  
  
A Comprehensive Multi-illuminant Dataset for Benchmarking of the  Intrinsic Image Algorithms
  Shida Beigpour*, Andreas Kolb, Sven Kunz
  
  
  
  
Photometric Stereo in a Scattering Medium
  Zak Murez*, Ravi Ramamoorthi, Tali Treibitz, David Kriegman
  
  
  
  
Selective Encoding for Recognizing Unreliably Localized Faces
  Ang Li*, Vlad Morariu, Larry Davis
  
  
  
  
Temporal Subspace Clustering for Human Motion Segmentation
  Sheng Li*, Kang Li, Yun Fu
  
  
  
  
Pedestrian Travel Time Estimation in Crowded Scenes
  Shuai Yi*, Hongsheng Li, Xiaogang Wang
  
  
  
  
SOWP: Spatially Ordered and Weighted Patch Descriptor for Visual  Tracking
  Han-Ul Kim*, Dae-Youn Lee, Jae-Young Sim, Chang-Su Kim
  
  
  
  
PatchMatch-based Automatic Lattice Detection for Near-Regular Textures
  Siying Liu*, Tian-Tsong Ng, Minh Do, Kalyan Sunkavalli, Eli Shechtman, Nathan  Carr
  
  
  
  
Live Repetition Counting
  Ofir Levy, Lior Wolf*
  
  
  
  
A Data-driven Metric for Comprehensive Evaluation of Saliency Models
  Jia Li*, Changqun Xia, Yafei Song, Shu Fang, Xiaowu Chen
  
  
  
  
Understanding and Predicting Memorability at a Large-scale
  Aditya Khosla*, Akhil Raju, Antonio Torralba, Aude Oliva
  
  
  
  
Active Learning Revisited: Reusing Past Datasets for Future Tasks
  Stratis Gavves*, Thomas Mensink, Tatiana Tommasi, Cees Snoek, Tinne  Tuytelaars
  
  
  
  
3D Object Reconstruction from Hand-Object Interactions
  Dimitrios Tzionas*, Juergen Gall
  
  
  
  
Learning Concept Embeddings with Combined Human-Machine Expertise
  Michael Wilber*, Iljung Kwak, Serge Belongie
  
  
  
  
Object Detection Using Generalization and Efficiency Balanced  Co-occurrence Features
  Haoyu Ren*, Ze-Nian Li
  
  
  
  
Weakly-Supervised Alignment of Video With Text
  Piotr Bojanowski*, Rémi Lajugie, Edouard Grave, Francis Bach, Ivan Laptev,  Jean Ponce, Cordelia Schmid
  
  
  
  
HD-CNN: Hierarchical Deep Convolutional Neural Network for Large Scale  Visual Recognition
  Zhicheng Yan*, Hao Zhang, Robinson Piramuthu, Vignesh Jagadeesh, Dennis  DeCoste, Wei Di, Yizhou Yu
  
  
  
  
Deep Multiple Instance Network
  Xin Lu*, Zhe Lin, Xiaohui Shen, Radomir Mech, James Wang
  
  
  
  
A Matrix Decomposition Perspective to Multiple Graph Matching
  Junchi Yan*, Hongteng Xu, Hongyuan Zha, Xiaokang Yang
  
  
  
  
Multiple Granularity Descriptors for Fine-grained Categorization
  Dequan Wang*, Zhiqiang Shen, Jie Shao, Wei Zhang, Xiangyang Xue, Zheng Zhang
  
  
  
  
Structure from Motion Using Structure-less Resection
  Enliang Zheng*, Changchang Wu
  
  
  
  
Minimal Solvers for 3D Geometry from Satellite Imagery
  Enliang Zheng*, Ke Wang, Enrique Dunn, Jan-Michael Frahm
  
  
  
  
Sparse Dynamic 3D Reconstruction from Unsynchronized Videos
  Enliang Zheng*, Dinghuang Ji, Enrique Dunn, Jan-Michael Frahm
  
  
  
  
Resolving Scale Ambiguity Via XSlit Aspect Ratio Analysis
  Wei Yang*, Haiting Lin, Sing Bing Kang, Jingyi Yu
  
  
  
  
Learning Temporal Embeddings for Complex Video Analysis
  Vignesh Ramanathan*, Kevin Tang, Greg Mori, Fei-Fei Li
  
  
  
  
Deep Dynamic Convolutional Networks
  Jiashi Feng*, Trevor Darrell
  
  
  
  
Fast and Effective L_0 Gradient Minimization by Region Fusion
  Rang Man Ho Nguyen*, Michael Brown
  
  
  
  
Guided Long-Short Term Memory for Image Caption Generation
  Xu Jia*, Stratis Gavves, Basura Fernando, Tinne Tuytelaars
  
  
  
  
Towards Computational Baby Learning: A Weakly-supervised Approach for  Object Detection
  Xiaodan Liang, Si Liu, Yunchao Wei, Luoqi Liu, Liang Lin*, Shuicheng Yan
  
  
  
  
Generic Promotion of Diffusion-Based Salient Object Detection
  Peng Jiang*, Nuno Vasconcelos, Jingliang Peng
  
  
  
  
Nighttime Haze Removal with Glow and Multiple Light Colors
  YU LI*, Robby Tan, Michael Brown
  
  
  
  
Learning Optical Flow with Convolutional Neural Networks
  Philipp Fischer*, Alexey Dosovitskiy, Eddy Ilg, Philip Häusser, Caner  Hazırbaş, Vladimir Golkov, Patrick van der Smagt, Daniel Cremers, Thomas Brox
  
  
  
  
An Efficient Minimal Solution for Multi-Camera Motion
  Jonathan Ventura*, Clemens Arth, Vincent Lepetit
  
  
  
  
Just Noticeable Differences in Visual Attributes
  Aron Yu*, Kristen Grauman
  
  
  
  
Confidence Preserving Machine for Facial Action Unit Detection
  Jiabei Zeng*, Wen-Sheng Chu, Fernando De la Torre, Jeffrefy Cohn, Zhang Xiong
  
  
  
  
Learning Semi-Supervised Representation Towards a Unified Optimization  Framework for Semi-Supervised Learning
  Chun-Guang Li*, Zhouchen Lin, Honggang Zhang, Jun Guo
  
  
  
  
Conformal and Low-Rank Sparse Representation for Image Restoration
  Jianwei Li*, Xiaowu Chen, Dongqing Zou, Bo Gao, Bin Zhou
  
  
  
  
Unsupervised Synchrony Discovery in Human Interaction
  Wen-Sheng Chu*, Jiabei Zeng, Fernando De la Torre, Jeffrefy Cohn, Daniel  Messinger
  
  
  
  
Patch Group Based Nonlocal Self-Similarity Prior Learning for Image  Denoising
  Jun Xu, Lei Zhang*, Wangmeng Zuo, David Zhang, Xiangchu Feng
  
  
  
  
Automatic Thumbnail Generation Based on Visual Representativeness and  Foreground Recognizability
  Jingwei Huang, Huarong Chen*, Bin Wang, Stephen Lin
  
  
  
  
Extraction of Illusory Baselines from Distorted Document Images Using Curvilinear  Projection
  Gaofeng MENG*, Zuming HUANG, Yonghong SONG, Shiming XIANG, Chunhong PAN
  
  
  
  
Near-Online Multi-target Tracking with Aggregated Local Flow Descriptor
  Wongun Choi*
  
  
  
  
Joint Camera Clustering and Surface Segmentation for Large-scale Multi-view  Stereo
  Runze Zhang, Shiwei Li, Tian Fang*, Siyu Zhu, Long Quan
  
  
  
  
SALICON: Bridging the Semantic Gap in Saliency Prediction
  Xun Huang*, Chengyao Shen, Xavier Boix, Qi Zhao
  
  
  
  
A Novel Sparsity Measure for Tensor Recovery
  Qian Zhao*, Deyu Meng, Xu Kong, Qi Xie, Wenfei Cao, Yao Wang, Zongben Xu
  
  
  
  
Single-shot Specular Surface Reconstruction with Gonio-plenoptic Imaging
  Lingfei Meng*, Liyang Lu, Noah Berdard, Kathrin Berkner
  
  
  
  
Oriented Object Proposals
  Shengfeng He*, Rynson Lau
  
  
  
  
VQA: Visual Question Answering
  Stanislaw Antol*, Aishwarya Agrawal, Jiasen Lu, Margaret Mitchell, Dhruv  Batra, Larry Zitnick, Devi Parikh
  
  
  
  
Learning Shape, Motion and Elastic Models in Force Space
  Antonio Agudo*, Francesc Moreno-Noguer
  
  
  
  
Improving Image Classification with Location Context
  Kevin Tang*, Manohar Paluri, Fei-Fei Li, Rob Fergus, Lubomir Bourdev
  
  
  
  
Context-aware diffusion for label propagation on graphs
  Kwang In Kim*, James Tompkin, Hanspeter Pfister, Christian Theobalt
  
  
  
  
Depth-based hand pose estimation: data, methods, and challenges
  James Supancic III*, Deva Ramanan, Gregory Rogez, Yi Yang, Jamie Shotton
  
  
  
  
Adaptive Dither Voting for Robust Spatial Verification
  Xiaomeng Wu*, Kunio Kashino
  
  
  
  
Learning Deconvolution Network for Semantic Segmentation
  Hyeonwoo Noh, Seunghoon Hong, Bohyung Han*
  
  
  
  
Robust RGB-D Odometry Using Point and Line Features
  Yan Lu, Dezhen Song*
  
  
  
  
TransCut: Transparent Object Segmentation from a Light-Field Image
  Yichao Xu*, Hajime Nagahara, Atsushi Shimada, Rin-ichiro Taniguchi
  
  
  
  
HICO: A Benchmark for Recognizing Human-Object Interactions in Images
  Yu-Wei Chao*, Zhan Wang, Yugeng He, Jiaxuan Wang, Jia Deng
  
  
  
  
Delving Deep into Rectifiers: Surpassing Human-Level Performance on  ImageNet Classification
  Kaiming He*, Xiangyu Zhang, Shaoqing Ren, Jian Sun
  
  
  
  
Learning-to-Rank based on Subsequences
  Basura Fernando*, Stratis Gavves, Damien Muselet, Tinne Tuytelaars
  
  
  
  
Learning Nonlinear Spectral Filters for Color Image Reconstruction
  Julia Diebold*, Michael Moeller, Daniel Cremers, Guy Gilboa
  
  
  
  
Alternating Co-Quantization for Cross-modal Hashing
  Go Irie*, Hiroyuki Arai, Yukinobu Taniguchi
  
  
  
  
Beyond White: Ground Truth Colors for Color Constancy Correction
  Dongliang Cheng*, Brian Price, Scott Cohen, Michael Brown
  
  
  
  
Conditional Random Fields as Recurrent Neural Networks
  Shuai Zheng*, Sadeep Jayasumana, Bernardino Romera-Paredes, Vibhav Vineet,  Zhizhong Su, Dalong Du, Chang Huang, philip Torr
  
  
  
  
A Versatile Scene Model with Differentiable Visibility Applied to  Generative Pose Estimation
  Helge Rhodin*, Nadia Robertini, Christian Richardt, Hans-Peter Seidel,  Christian Theobalt
  
  
  
  
Depth Recovery from Light Field Using Focal Stack Symmetry
  Haiting Lin*, Can Chen, Sing Bing Kang, Jingyi Yu
  
  
  
  
Parsimonious Labeling
  Puneet Dokania*, M. Pawan Kumar
  
  
  
  
Unsupervised Learning of Visual Representations using Videos
  Xiaolong Wang*, Abhinav Gupta
  
  
  
  
Semantic Pose using Deep Networks Trained on Synthetic RGB-D
  Jeremie Papon*, Markus Schoeler
  
  
  
  
Localize me Anywhere, Anytime: A Multi-task Point-Retrieval Approach
  Guoyu Lu*, Yan Yan, Li Ren, Jingkuan Song, Nicu Sebe, Chandra Kambhamettu
  
  
  
  
Depth Map Estimation and Colorization of Anaglyph Images Using Local  Color Prior and Reverse Intensity Distribution
  Williem Williem, In Kyu Park*
  
  
  
  
Volumetric Bias in Energy-based Segmentation: Secrets and Solutions
  Yuri Boykov*, Hossam Isack, Carl Olsson, Ismail Ben Ayed
  
  
  
  
Learning a Discriminative Model for the Perception of Realism using  Composite Images
  Jun-yan Zhu*, Philipp Krahenbuhl, Eli Shechtman, Alexei Efros
  
  
  
  
Learning Data-driven Reflectance Priors for Intrinsic Image  Decomposition
  Tinghui Zhou*, Philipp Krahenbuhl, Alexei Efros
  
  
  
  
Multi-kernel Correlation Filter for Visual Tracking
  Ming Tang*, JIayi Feng
  
  
  
  
Joint Probabilistic Data Association Revisited
  Seyed Hamid Rezatofighi*, Anton Milan, Zhen Zhang, Qinfeng Shi, Anthony Dick,  Ian Reid
  
  
  
  
RGB-Guided Hyperspectral Image Upsampling
  Hyeokhyen Kwon, Yu-Wing Tai*
  
  
  
  
Mining And-Or Graphs for Graph Matching
  Quanshi Zhang*, Yingnian Wu, Song-Chun Zhu
  
  
  
  
Learning Deep Representation with Large-scale Attributes
  Wanli Ouyang*, Hongyang Li, Xingyu Zeng, Xiaogang Wang
  
  
  
  
Efficient Video Segmentation using Parametric Graph Partitioning
  Chen-Ping Yu*, Hieu Le, Greg Zelinsky, Dimitris Samaras
  
  
  
  
Tracking-by-Segmentation with Online Gradient Boosting Decision Tree
  Jeany Son, Ilchae Jung, Kayoung Park, Bohyung Han*
  
  
  
  
Projection onto the Manifold of Elongated Structures for Accurate  Extraction
  Amos Sironi*, Vincent Lepetit, Pascal Fua
  
  
  
  
Naive Bayes Super-Resolution Forest
  Jordi Salvador*, Eduardo Pérez-Pellitero
  
  
  
  
The One Triangle Three Parallelograms Sampling Strategy and Its  Application in Shape Regression
  Mikael Nilsson*
  
  
  
  
Exploring Causal Relationships in Visual Object Tracking
  Karel Lebeda*, Simon Hadfield, Richard Bowden
  
  
  
  
Exploiting high level scene cues in stereo reconstruction
  Simon Hadfield*, Richard Bowden
  
  
  
  
Entropy Minimization for Convex Relaxation Approaches
  Mohamed Souiai*, Martin Oswald, Youngwook Kee, Junmo Kim, Marc Pollefeys,  Daniel Cremers
  
  
  
  
Boosting Object Proposals: From Pascal to COCO
  Jordi Pont-Tuset*, Luc Van Gool
  
  
  
  
A Nonparametric Bayesian Approach Toward Stacked Convolutional  Independent Component Analysis
  Sotirios Chatzis*, Dimitrios Kosmopoulos
  
  
  
  
Point triangulation through polyhedron collapse using the L-infinity  norm
  Simon Donné*, Bart Goossens, Wilfried Philips
  
  
  
  
Continuous Pose Estimation with a Spatial Ensemble of Fisher Regressors
  Michele Fenzi*, Laura Leal-Taixe, Joern Ostermann, Tinne Tuytelaars
  
  
  
  
Secrets of GrabCut and Kernel K-means
  Meng Tang, Ismail Ben Ayed, Yuri Boykov*
  
  
  
  
Deep Learning Strong Parts for Pedestrian Detection
  Yonglong Tian*
  
  
  
  
POP image fusion - derivative domain image fusion without reintegration
  Graham Finlayson, Alex Hayes*
  
  
  
  
Learning Social Relation Traits from Face Images
  Zhanpeng Zhang*, Ping Luo, Chen-Change Loy, Xiaoou Tang
  
  
  
  
Robust Heart Rate Measurement from Video Using Select Random Patches
  Antony Lam*, Yoshinori Kuno
  
  
  
  
Dense Optical Flow Prediction from a Static Image
  Jacob Walker*, Abhinav Gupta, Martial Hebert
  
  
  
  
Adaptive Spatial-Spectral Dictionary Learning for Hyperspectral Image  Denoising
  Ying Fu*, Antony Lam, Imari Sato, Yoichi Sato
  
  
  
  
Fully Connected Guided Image Filtering
  Longquan Dai*, Mengke Yuan, Feihu Zhang, Xiaopeng Zhang
  
  
  
  
Adaptively Unified Semi-Supervised Dictionary Learning with Active  Points
  Xiaobo Wang*, Xiaojie Guo, Yangjun Lu, Shiming XIANG
  
  
  
  
Segment Graph Based Image Filtering: Fast Structure-Preserving Smoothing
  Feihu Zhang*, Longquan Dai, Shiming XIANG, Xiaopeng Zhang
  
  
  
  
Video Matting via Sparse and Low-rank Representation
  Dongqing Zou*, Xiaowu Chen, Guangying Cao, Xiaogang Wang
  
  
  
  
A Versatile Learning-based 3D Temporal Tracker: Scalable, Robust, Online
  David Joseph Tan*, Federico Tombari, Slobodan Ilic, Nassir Navab
  
  
  
  
Dual-Feature Warping-based Motion Model Estimation
  Shiwei Li*, Lu Yuan, Jian Sun, Long Quan
  
  
  
  
Flowing ConvNets for Human Pose Estimation in Videos
  Tomas Pfister*, James Charles, Andrew Zisserman
  
  
  
  
Robust Principal Component Analysis on Graphs
  Nauman Shahid*, Vassilis Kalofolias, Xavier Bresson, Michael Bronstein,  Pierre Vandergheynst
  
  
  
  
Projection Bank: From High-dimensional Data to Medium-length Binary  Codes
  Li Liu, Mengyang Yu, Ling Shao*
  
  
  
  
Robust Optimization for Deep Regression
  Vasileios Belagiannis*, Christian Rupprecht, Gustavo Carneiro, Nassir Navab
  
  
  
  
Deeply Improved Sparse Coding for Image Super-Resolution
  Zhaowen Wang*, Ding Liu, Jianchao Yang, Wei Han, Thomas Huang
  
  
  
  
Robust Model-based 3D Head Pose Estimation
  Gregory Meyer, Shalini Gupta*, Iuri Frosio, Dikpal Reddy, Jan Kautz
  
  
  
  
Learning to track for spatio-temporal action localization
  Philippe Weinzaepfel*, Zaid Harchaoui, Cordelia Schmid
  
  
  
  
Pose Induction for Novel Object Categories
  Shubham Tulsiani*, Joao Carreira, Jitendra Malik
  
  
  
  
Multi-class Multi-annotator Active Learning with Robust Gaussian Process  for Visual Recognition
  Chengjiang Long*, Gang Hua
  
  
  
  
Robust Facial Landmark Detection under Significant Head Poses and  Occlusion
  Yue Wu*, Qiang Ji
  
  
  
  
What Makes Kevin Spacey Look Like Kevin Spacey
  Supasorn Suwajanakorn*, Ira Kemelmacher, Steve Seitz
  
  
  
  
Convolutional Color Constancy
  Jonathan Barron*
  
  
  
  
Unsupervised Object Discovery and Tracking in Video Collections
  Suha Kwak*, Minsu Cho, Jean Ponce, Cordelia Schmid, Ivan Laptev
  
  
  
  
Differential Recurrent Neural Networks for Action Recognition
  Vivek Veeriah, Naifan Zhuang, Guo-Jun Qi*
  
  
  
  
Learning Ordinal Relationships for Mid-Level Vision
  Daniel Zoran*, Phillip Isola, Dilip Krishnan, William Freeman
  
  
  
  
Hierarchical Convolutional Features for Visual Tracking
  Chao Ma*, Jia-Bin Huang, Xiaokang Yang, Ming-Hsuan Yang
  
  
  
  
Top Rank Supervised Binary Coding for Visual Search
  Dongjin Song, Rongrong Ji, David Meyer, John Smith, Wei Liu*
  
  
  
  
Optimizing the Viewing Graph for Structure-from-Motion
  Chris Sweeney*, Torsten Sattler, Matthew Turk, Tobias Hollerer, Marc  Pollefeys
  
  
  
  
Distilling the Visual World: Foveated imaging for visual discovery
  Kevin Matzen*, Noah Snavely
  
  
  
  
Adaptive Hashing for Fast Similarity Search
  Fatih Cakir*, Stan Sclaroff
  
  
  
  
Unsupervised Domain Adaptation for Zero-Shot Learning
  Elyor Kodirov*, Tao Xiang, Zhenyong Fu, Shaogang Gong
  
  
  
  
Joint Object and Part Segmentation using Deep Learned Potentials
  Peng Wang*, Xiaohui Shen, Zhe Lin, Scott Cohen, Brian Price, Alan Yuille
  
  
  
  
Know Before You Do: Anticipating Maneuvers via Learning Temporal Driving  Models
  Ashesh Jain*, Hema Koppula, Bharad Raghavan, Shane Soh, Ashutosh Saxena
  
  
  
  
Intrinsic Scene Decomposition from RGB-D images
  Mohammed Hachama*, Bernard Ghanem, Peter Wonka
  
  
  
  
Photometric Stereo with Small Angular Variations
  Jian Wang*, Yasuyuki Matsushita, Boxin Shi, Aswin Sankaranarayanan
  
  
  
  
Occlusion-aware depth estimation using light-field cameras
  Ting-Chun Wang*, Alexei Efros, Ravi Ramamoorthi
  
  
  
  
3D Hand Pose Estimation Using Randomized Decision Forest with  Segmentation Index Points
  PEIYI LI*, Haibin Ling
  
  
  
  
Oriented Light-Field Windows for Scene Flow
  Pratul Srinivasan*, Michael Tao, Ren Ng, Ravi Ramamoorthi
  
  
  
  
Extended Depth of Field Catadioptric Imaging Using Focal Sweep
  Ryunosuke Yokoya*, Shree Nayar
  
  
  
  
Single Image 3D Without a Single 3D Image
  David Fouhey*, Muhammad Wajahat Hussain, Abhinav Gupta, Martial Hebert
  
  
  
  
Wide-Area Image Geolocalization with Aerial Reference Imagery
  Scott Workman*, Richard Souvenir, Nathan Jacobs
  
  
  
  
Thin Structure Estimation with Curvature Regularization
  Dmitrii Marin, Yuri Boykov*, Yuchen Zhong
  
  
  
  
Maximum-Margin Structured Learning with Deep Networks for 3D Human Pose  Estimation
  Sijin Li*, Weichen Zhang, Antoni Chan
  
  
  
  
Unsupervised Semantic Parsing of Video Collections
  Ozan Sener*, Amir Zamir, Silvio Savarese, Ashutosh Saxena
  
  
  
  
Learning Spatiotemporal Features with 3D Convolutional Networks
  Du Tran*, Lubomir Bourdev, Rob Fergus, Lorenzo Torresani, Manohar Paluri
  
  
  
  
Cross-domain Image Retrieval with a Dual Attribute-aware Ranking Network
  Junshi Huang*, Rogerio Feris, Qiang Chen, Shuicheng Yan
  
  
  
  
Conditional Convolutional Neural Network for Modality-aware Face  Recognition
  Chao Xiong*, Xiaowei Zhao, Danhang Tang, Shuicheng Yan, Tae-Kyun Kim
  
  
  
  
Dynamic Texture Recognition via Structured Tensor Dictionary Learning
  YUHUI QUAN*, Yan Huang, Hui Ji
  
  
  
  
Activity Auto-Completion: Predicting Human Activities from Partial  Videos
  Zhen Xu*, Laiyun Qing, Jun Miao
  
  
  
  
Intrinsic Depth: Improving Depth Transfer with Intrinsic Images
  Naejin Kong*, Michael Black
  
  
  
  
HARF: Hierarchy-associated Rich Features for Salient Object Detection
  Wenbin Zou*, Nikos Komodakis
  
  
  
  
An Exploration of Parameter Redundancy in Deep Networks with Circulant  Projections
  Yu Cheng, Felix Yu*, Rogerio Feris, Sanjiv Kumar, Shi-Fu Chang
  
  
  
  
Low-Rank Tensor Constrained Multiview Subspace Clustering
  Changqing Zhang*, Si Liu, Huazhu Fu, Guangcan Liu, Xiaochun Cao
  
  
  
  
Additive Nearest Neighbor Feature Maps
  WANG Zhenzhen*, YUAN Xiao-Tong, LIU Qingshan, Shuicheng Yan
  
  
  
  
Learning to See by Moving
  Pulkit Agrawal*, Joao Carreira, Jitendra Malik
  
  
  
  
Unsupervised Cross-modal Synthesis of Subject-specific Scans
  Raviteja Vemulapalli*, Hien Nguyen, Kevin Zhou
  
  
  
  
Robust Non-rigid Motion Tracking and Surface Reconstruction Using L0  Regularization
  Kaiwen Guo, Feng Xu, Yangang Wang, Yebin Liu*, Qionghai Dai
  
  
  
  
Person Re-identification with Correspondence Structure Learning
  Yang Shen, Weiyao Lin*, Junchi Yan, Mingliang Xu, Jianxin Wu, Jingdong Wang
  
  
  
  
Understanding deep features with computer-generated imagery
  Mathieu Aubry*, Bryan Russell
  
  
  
  
Deep Colorization
  Zezhou Cheng*, Qingxiong Yang, Bin Sheng
  
  
  
  
Attribute-Graph: A Graph based approach to Image Ranking
  Nikita Prabhu*, Venkatesh Babu Radhakrishnan
  
  
  
  
Constrained Convolutional Neural Networks for Weakly Supervised Semantic  Segmentation
  Deepak Pathak*, Philipp Krahenbuhl, Evan Shelhamer, Trevor Darrell
  
  
  
  
Personalized Age Progression with Aging Dictionary
  Xiangbo Shu*, jinhui Tang, Hanjiang Lai, Luoqi Liu, Shuicheng Yan
  
  
  
  
From Facial Part Responses to Face Detection: A Deep Learning Approach
  Shuo Yang*, Ping Luo, Chen-Change Loy, Xiaoou Tang
  
  
  
  
Accurate Camera Calibration Robust to Defocus using a Smartphone
  Hyowon Ha*, Yunsu Bok, Kyungdon Joo, Jiyoung Jung, In So Kweon
  
  
  
  
High Quality Structure from Small Motion for Rolling Shutter Cameras
  Sunghoon Im*, Hyowon Ha, Gyeongmin Choe, Hae-Gon Jeon, Kyungdon Joo, In So  Kweon
  
  
  
  
Higher-order CRF Structural Segmentation of 3D Reconstructed Surfaces
  Jingbo Liu*, Jinglu Wang, Tian Fang, Chiew-Lan Tai, Long Quan
  
  
  
  
Semi- and Weakly-supervised Human Pose Estimation
  Norimichi Ukita*
  
  
  
  
Image Matting with KL-Divergence Based Sparse Sampling
  Levent Karacan, Aykut Erdem*, Erkut Erdem
  
  
  
  
BodyPrint: Pose Invariant 3D Shape Matching of Human Bodies
  Jiangping Wang*, Kai Ma, Terrence Chen, Vivek Singh, Thomas Huang
  
  
  
  
Convolutional Channel Features For Pedestrian, Face and Edge Detection
  Bin Yang*, Junjie Yan, Zhen Lei, Stan Li
  
  
  
  
Efficient PSD Constrained Asymmetric Metric Learning for Person  Re-identification
  Shengcai Liao*, Stan Li
  
  
  
  
Local Convolutional Features with Unsupervised Training for Image  Retrieval
  Mattis Paulin*, Matthijs Douze, Zaid Harchaoui, Julien Mairal, Florent  Perronin, Cordelia Schmid
  
  
  
  
Visual Madlibs: Fill in the blank Description Generation and Question  Answering
  Licheng Yu*, Eunbyung Park, Alex Berg, Tamara Berg
  
  
  
  
Separating Fluorescent and Reflective Components by Using a Single  Hyperspectral Image
  Yinqiang Zheng*, Ying Fu, Antony Lam, Imari Sato, Yoichi Sato
  
  
  
  
Interpolation on the manifold of $k$ component GMMs
  Hyunwoo Kim*, Nagesh Adluru, Vikas Singh, Baba Vemuri, Monami Banerjee, Sarah  Turner, David Fuller, John Forder
  
  
  
  
Contextual Action Recognition with R*CNN
  Georgia Gkioxari*, Ross Girshick, Jitendra Malik
  
  
  
  
Actions and Attributes from Wholes and Parts
  Georgia Gkioxari*, Ross Girshick, Jitendra Malik
  
  
  
  
Context-aware CNNs for person detection
  Tuan-Hung Vu, Anton Osokin*, Ivan Laptev
  
  
  
  
The Middle Child Problem: Revisiting Parametric Min-cut for Fast Object  Proposals
  Ahmad Humayun*, Fuxin Li, James Rehg
  
  
  
  
Temporal Perception and Prediction in Ego-Centric Video
  Yipin Zhou*, Tamara Berg
  
  
  
  
DeepBox: Learning Objectness with Convolutional Networks
  WEICHENG KUO*, Bharath Hariharan, Jitendra Malik
  
  
  
  
Frequency-based Environment Matting by Compressive Sensing
  Yiming Qian*, Minglun Gong, Yee Hong Yang
  
  
  
  
Mode-Seeking on Hypergraphs for Robust Geometric Model Fitting
  Hanzi Wang*, Guobao Xiao, Yan Yan, David Suter
  
  
  
  
Highly-Expressive Spaces of Well-Behaved Transformations: Keeping It  Simple
  Oren Freifeld*, Soren Hauberg, Nematollah Batmanghelich, John Fisher III
  
  
  
  
The Layered Deformation Model for Shape Matching
  Yuanqi Su*, Yuehu Liu, Bonan CUAN
  
  
  
  
Pose-Invariant 3D Face Alignment
  Amin Jourabloo, Xiaoming Liu*
  
  
  
  
Robust Image Segmentation Using Contour-guided Color Palettes
  Xiang Fu*, Chien-Yi Wang, Chen Chen, Changhu Wang, C.-C. Jay Kuo
  
  
  
  
PQTable: Fast Exact Asymmetric Distance Neighbor Search for Product  Quantization using Hash Tables
  Yusuke Matsui*, Toshihiko Yamasaki, Kiyoharu Aizawa
  
  
  
  
Complementary Sets of Shutter Sequences for Motion Deblurring
  Hae-Gon Jeon*, Joon-Young Lee, Yudeog Han, Seon Joo Kim, In So Kweon
  
  
  
  
From Emotions to Action Units with Hidden and Semi-Hidden-Task Learning
  Adria Ruiz*, Joost van de Weijer, Xavier Binefa
  
  
  
  
Entropy-based Latent Structured Output Prediction
  Diane Bouchacourt*, Sebastian Nowozin, M. Pawan Kumar
  
  
  
  
Photogeometric Scene Flow for High-Detail Dynamic 3D Reconstruction
  Paulo Gotardo*, Tomas Simon, Yaser Sheikh, Iain Matthews
  
  
  
  
Facial Trait Judgment and Election Outcome Prediction: Social Dimensions  of Face
  Jungseock Joo*, Francis Steen, Song-Chun Zhu
  
  
  
  
Semantic Guidance of Visual Attention for Localizing Objects in Scenes
  Juan Caicedo*, Svetlana Lazebnik
  
  
  
  
Lending A Hand: Detecting Hands and Recognizing Activities in Complex Egocentric  Interactions
  Sven Bambach*, Stefan Lee, David Crandall, Chen Yu
  
  
  
  
What makes an object memorable?
  Rachit Dubey*, Joshua Peterson, Aditya Khosla, Ming-Hsuan Yang, Bernard  Ghanem
  
  
  
  
Fast Orthogonal Projection Based on Kronecker Product
  Xu Zhang*, Felix Yu, Sanjiv Kumar, Shengjin Wang, Shi-Fu Chang, Ruiqi Guo
  
  
  
  
Blur-aware Disparity Estimation from Defocus Stereo Images
  Ching-Hui Chen*, Hui Zhou, Timo Ahonen
  
  
  
  
Online Object Tracking with Proposal Selection
  Yang Hua*, Karteek Alahari, Cordelia Schmid
  
  
  
  
Global Structure-from-Motion by Similarity Averaging
  Zhaopeng Cui*, Ping Tan
  
  
  
  
Scene-Domain Active Part Models for Object Representation
  Zhou Ren*, Chaohui Wang, Alan Yuille
  
  
  
  
Fast and Accurate Head Pose Estimation via Random Projection Forests
  Donghoon Lee*, Ming-Hsuan Yang, Songhwai Oh
  
  
  
  
Joint Optimization of Segmentation and Color Clustering
  Ekaterina Lobacheva, Yuri Boykov*, Olga Veksler
  
  
  
  
An Adaptive Data Representation for Robust Point-Set Registration and  Merging
  Dylan Campbell*, Lars Petersson
  
  
  
  
Adaptive Exponential Smoothing for Online Filtering of Pixel Prediction  Maps
  Kang Dang*, JIONG YANG, Junsong Yuan
  
  
  
  
Similarity Gaussian Process Latent Variable Model for Multi-Modal Data  Analysis
  Guoli Song*, Shuhui Wang, Qingming Huang, Qi Tian
  
  
  
  
Simultaneous Binary Feature Learning and Encoding for Face Recognition
  Jiwen Lu*, Venice Erin Liong, Jie Zhou
  
  
  
  
A Unified Multiplicative Framework for Attribute Learning
  Kongming Liang*, Hong Chang, Shiguang Shan, Xilin Chen
  
  
  
  
Learning Ensemble Latent Structured Models in Functional Space by  Gradient Boosting
  Hossein Hajimirsadeghi*, Greg Mori
  
  
  
  
Contractive Rectifier Networks for Nonlinear Maximum Margin  Classification
  Senjian An*, Munawar Hayat, Salman Khan, Mohammed Bennamoun, Farid Boussaid,  Ferdous Sohel
  
  
  
  
kNN Hashing with Factorized Neighborhood Representation
  Kun Ding*, Chunlei Huo, Bin Fan, Chunhong PAN
  
  
  
  
Deep Learning Face Attributes in the Wild
  Ziwei Liu*, Ping Luo, Xiaogang Wang, Xiaoou Tang
  
  
  
  
Augmenting Strong Supervision Using Web Data for Fine-grained  Categorization
  Zhe Xu*, SJTU, Shaoli Huang, Ya Zhang, Dacheng Tao
  
  
  
  
Multi-View Complementary Hash Tables for Nearest Neighbor Search
  Xianglong Liu*, Lei Huang, Cheng Deng, Jiwen Lu, Bo Lang
  
  
  
  
Understanding and Diagnosing Visual Tracking Systems
  Naiyan Wang*, Jianping Shi, Dit-Yan Yeung, Jiaya Jia
  
  
  
  
Describing Videos by Exploiting Temporal Structure
  Li Yao*, Atousa Torabi, Kyunghyun Cho, Nicolas Ballas, Christopher Pal, Hugo  Larochelle, Aaron Courville
  
  
  
  
BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks  for Semantic Segmentation
  Jifeng Dai*, Kaiming He, Jian Sun
  
  
  
  
Fast Novel Visual Concept Learning from Sentence Descriptions of Images
  Junhua Mao*, Xu Wei, Yi Yang, Jiang Wang, Zhiheng Huang, Alan Yuille
  
  
  
  
Scalable Person Re-identification: A Benchmark
  Liang Zheng*, Shengjin Wang, Jingdong Wang, Liyue Shen, Jiahao Bu, Qi Tian
  
  
  
  
Simultaneous Deep Transfer Across Domains and Tasks
  Eric Tzeng*, Judy Hoffman, Trevor Darrell, Kate Saenko
  
  
  
  
Multi-modal Sharable and Specific Feature Learning for RGB-D Object  Recognition
  Anran Wang, Jianfei Cai*, Jiwen Lu, Tat-Jen Cham
  
  
  
  
Low Dimensional Explicit Feature Maps
  Ondrej Chum*
  
  
  
  
Highly articulated human detection using a Markov Random Field model of  poselets and variational method
  Thanh Nguyen*, Khoi Tran, Sai-Kit Yeung
  
  
  
  
Gipuma: Massively parallel multiview stereopsis
  Silvano Galliani*, Katrin Lasinger, Konrad Schindler
  
  
  
  
Convolutional networks for real-time 6-DOF camera relocalization
  Alex Kendall*, Matthew Grimes, Roberto Cipolla
  
  
  
  
Intrinsic decomposition of image sequences from local temporal  variations
  Pierre-Yves Laffont*, Jean-Charles Bazin
  
  
  
  
Multi-Task Learning with Low Rank Attribute Embedding for Person  Re-identification
  Chi Su*, Fan Yang, Shiliang Zhang, Qi Tian, Larry Davis, Wen Gao
  
  
  
  
Low-Rank Tensor Approximation with Laplacian Scale Mixture Modeling for  Multiframe Image Denoising
  Weisheng Dong*, Guangyu Li, Guangming Shi, Xin LI, Yi Ma
  
  
  
  
RIDE: Reversal Invariant Descriptor Enhancement
  Lingxi Xie*, Jingdong Wang, Weiyao Lin, Bo Zhang, Qi Tian
  
  
  
  
P-CNN: Pose-based CNN Features for Action Recognition
  Guilhem Chéron*, Ivan Laptev, Cordelia Schmid
  
  
  
  
Fully Connected Object Proposals for Video Segmentation
  Federico Perazzi*, Oliver Wang, Alexander Sorkine-Hornung, Markus Gross
  
  
  
  
Learning Parametric Distributions for Image Super-Resolution: Where  Patch Matching Meets Sparse Coding
  Yongbo Li, Weisheng Dong*, Guangming Shi
  
  
  
  
Variational PatchMatch MultiView Reconstruction and Refinement
  Philipp Heise*, Brian Jensen, Sebastian Klose, Alois Knoll
  
  
  
  
As-Rigid-As-Possible Volumetric Shape-from-Template
  Shaifali PARASHAR*, Daniel Pizarro, Adrien Bartoli, Toby Collins
  
  
  
  
Object detection via a multi-region and semantic segmentation-aware CNN  model
  Spyros Gidaris*, Nikos Komodakis
  
  
  
  
General Dynamic Scene Reconstruction from Multiple View Video
  Armin Mustafa*, Jean-Yves Guillemaut, Hansung Kim, Adrian Hilton
  
  
  
  
The joint image handbook
  Matthew Trager*, Jean Ponce, Martial Hebert
  
  
  
  
Dense, Direct and Deformable: Non-Rigid 3D Reconstruction from RGB Video
  Rui Yu, Chris Russell, Neill Campbell, Lourdes Agapito*
  
  
  
  
Unsupervised Generation of a Viewpoint Annotated Car Dataset from Videos
  Nima Sedaghat Alvar*, Thomas Brox
  
  
  
  
Regressing a 3D Face Shape from a Single Image
  Sergey Tulyakov*, Nicu Sebe
  
  
  
  
Integrating Dashcam Views through Inter-Video Mapping
  Hsin-Yi Chen*, Bing-Yu Chen, Yi-Ling Chen, Wei-Tse Lee, Fan Wang
  
  
  
  
Visual Tracking with Fully Convolutional Networks
  Lijun Wang*, Wanli Ouyang, Xiaogang Wang, Huchuan Lu
  
  
  
  
Multiple Feature Fusion via Weighted Entropy for Visual Tracking
  Lin Ma*, Jiwen Lu, Jianjiang Feng, Jie Zhou
  
  
  
  
Local Subspace Collaborative Tracking
  Lin Ma*, Xiaoqin Zhang, Weiming Hu, Junliang Xing, Jiwen Lu, Jie Zhou
  
  
  
  
Neural Activation Constellations: Unsupervised Part Model Discovery with  Convolutional Networks
  Marcel Simon*, Erik Rodner
  
  
  
  
FaceDirector: Continuous Control of Facial Performance in Video
  Charles Malleson, Jean-Charles Bazin*, Oliver Wang, Thabo Beeler, Derek  Bradley, Adrian Hilton, Alexander Sorkine-Hornung
  
  
  
  
Hyperpoints and Fine Vocabularies for Large-Scale Location Recognition
  Torsten Sattler*, Michal Havlena, Filip Radenovic, Konrad Schindler, Marc  Pollefeys
  
  
  
  
Video Segmentation with Just a Few Strokes
  Naveen Shankar Nagaraja*, Frank Schmidt, Thomas Brox
  
  
  
  
Learning Spatially Regularized Correlation Filters for Visual Tracking
  Martin Danelljan*, Gustav Häger, Fahad Khan, Michael Felsberg
  
  
  
  
Globally Optimal 2D / 3D Registration from Points or Lines Without  Correspondences
  Mark Brown*, David Windridge, Jean-Yves Guillemaut
  
  
  
  
Improving Image Restoration with Soft-Rounding
  Xing Mei*, Honggang Qi, Baogang Hu, Siwei Lyu
  
  
  
  
SpeDo: 6 DOF Ego-Motion Sensor Using Speckle Defocus Imaging
  Kensei Jo*, Mohit Gupta, Shree Nayar
  
  
  
  
Detection and Segmentation of 2D Curved Symmetric Structures
  Ching Teo*, Cornelia Fermuller, Yiannis Aloimonos
  
  
  
  
Rendering of Eyes for Eye-Shape Registration and Gaze Estimation
  Erroll Wood*, Tadas Baltrušaitis, Peter Robinson, Andreas Bulling, Yusuke  Sugano, Xucong Zhang
  
  
  
  
Beyond RMS: Geometry-Aware Performance Evaluation of Stereo Algorithms
  Katrin Honauer*, Lena Maier-Hein, Daniel Kondermann
  
  
  
  
Multi-scale Learning for Low-resolution Person Re-identification
  Xiang Li, Wei-Shi Zheng*, Xiaojuan Wang, Tao Xiang, Shaogang Gong
  
  
  
  
Unsupervised Learning of Spatiotemporally Coherent Metrics
  Ross Goroshin*, Joan Bruna, Jonathan Tompson, David Eigen, Yann LeCun
  
  
  
  
Unsupervised Trajectory Clustering via Adaptive Multi-Kernel-based  Shrinkage
  Hongteng Xu*, Yang Zhou, Weiyao Lin, Hongyuan Zha
  
  
  
  
Unsupervised Extraction of Video Highlights Via Robust Recurrent  Auto-encoders
  Huan Yang, Baoyuan Wang*, Stephen Lin, David Wipf, Minyi Guo, Baining Guo
  
  
  
  
Learning to transfer: transferring latent task structures and its  application to person-specific facial action unit detection
  Timur Almaev, Brais Martinez, Michel Valstar*
  
  
  
  
TRIC-track: Tracking by Regression with Incrementally Learned Cascades
  Xiaomeng Wang, Michel Valstar*, Brais Martinez, Muhammad Khan, Tony Pridmore
  
  
  
  
See the Difference: Direct Pre-Image Reconstruction and Pose Estimation  by Differentiating HOG
  Wei-Chen Chiu*, Mario Fritz
  
  
  
  
An Efficient Statistical Method for Image Noise Level Estimation
  Guangyong Chen*, Fengyuan Zhu, Pheng ann Heng
  
  
  
  
A Multiscale Variable-grouping Framework for MRF Energy Minimization
  Omer Meir*, Meirav Galun, Stav Yagev, Ronen Basri, Irad Yavneh
  
  
  
  
Inferring M-Best Diverse Labelings in a Single One
  Alexander Kirillov*, Bogdan Savchynskyy, Dmitrij Schlesinger, Dmitry Vetrov,  Carsten Rother
  
  
  
  
Cascaded Sparse Spatial Bins for Efficient and Effective Generic Object  Detection
  David Novotny*, Jiri Matas
  
  
  
  
Merging the Unmatchable: Stitching Visually Disconnected SfM Models
  Andrea Cohen*, Torsten Sattler, Marc Pollefeys
  
  
  
  
Multi-Label Cross-modal Retrieval
  Viresh Ranjan*, Nikhil Rasiwasia, C.V. Jawahar
  
  
  
  
Probabilistic Label Relation Graphs with Ising Models
  Nan Ding*, Jia Deng, Kevin Murphy, Hartmut Neven
  
  
  
  
Unsupervised Tube Extraction using Transductive Learning and Dense  Trajectories
  Mihai Puscas, Enver Sangineto*, Dubravko Culibrk, Nicu Sebe
  
  
  
  
Predicting Multiple Structured Visual Interpretations
  Debadeepta Dey*, Varun Ramakrishna, Martial Hebert, J. Andrew Bagnell
  
  
  
  
Person Re-Identification with Discriminatively Trained Viewpoint  Invariant Dictionaries
  Srikrishna Karanam*, Yang Li, Richard Radke
  
  
  
  
Pairwise Conditional Random Forests for Facial Expression Recognition
  Arnaud Dapogny*, Kevin Bailly, Severine Dubuisson
  
  
  
  
3D Fragment Reassembly using Integrated Template Guidance and  Fracture-Region Matching
  Kang Zhang, Wuyi Yu, Mary Manhein, Waggenspack Warren, Xin Li*
  
  
  
  
Single Image Pop-Up from Discriminatively Learned Parts
  Menglong Zhu*, Xiaowei Zhou, Kostas Danilidiis
  
  
  
  
Compositional Hierarchical Representation of Shape Manifolds for  Classification of Non-manifold Shapes
  Mete Ozay*, Umit Aktas, Jeremy Wyatt, Ales Leonardis
  
  
  
  
Procedural Editing of Building Point Clouds
  Ilke Demir*, Daniel Aliaga, Bedrich Benes
  
  
  
  
Contour Detection and Characterization for Asynchronous Event Sensors
  Francisco Barranco*, Ching Teo, Cornelia Fermuller, Yiannis Aloimonos
  
  
  
  
Improving ferns ensembles by pruning leaves and quantising posterior  probabilities
  Antonio Rodriguez*, Vitor Sequeira
  
  
  
  
Storyline Representation of Egocentric Videos with an Applications to  Story-based Search
  Bo Xiong*, Leonid Sigal, Gunhee Kim
  
  
  
  
Joint Facial Action Unit Detection with Multi-conditional Latent  Variable Models
  Stefanos Eleftheriadis*, Ognjen Rudovic, Maja Pantic
  
  
  
  
Learning by Playing: Learning Common Sense Via Visual Abstractions
  Shanmukha Ramakrishn Vedantam*, Xiao Lin, Tanmay Batra, Larry Zitnick, Devi  Parikh
  
  
  
  
Semantically-Aware Aerial Reconstruction from Multi-Modal Data
  Randi Cabezas*, Julian Straub, John Fisher III
  
  
  
  
Predicting Good Features for Image Geo-Localization Using Per-Bundle  VLAD
  Hyo Jin Kim*, Enrique Dunn, Jan-Michael Frahm
  
  
  
  
Sequence to Sequence Video to Text
  Subhashini Venugopalan*, Marcus Rohrbach, Raymond Mooney, Trevor Darrell,  Kate Saenko
  
  
  
  
Appearance Mosaics from Internet Photo-Collections
  Dinghuang Ji*, Enrique Dunn, Jan-Michael Frahm
  
  
  
  
Learning informative edge maps for indoor scene layout prediction
  Arun Mallya*, Svetlana Lazebnik
  
  
  
  
Recurrent Network Models for Kinematic Tracking
  Katerina Fragkiadaki*, Panna Felsen, Sergey Levine, Jitendra Malik
  
  
  
  
Contour Flow: Middle-Level Motion Estimation by Combining Motion  Segmentation and Contour Alignment
  Huijun Di*, Qingxuan Shi, Feng Lv, Ming Qin, Yao Lu
  
  
  
  
Beyond Gauss: Image-Set Matching on the Riemannian Manifold of PDFs
  Mehrtash Harandi*, Mathieu Salzmann, Mahsa Baktashmotlagh
  
  
  
  
Actionness-assisted Recognition of Actions
  Ye Luo, Loong-Fah Cheong*, An Tran
  
  
  
  
Leveraging Datasets with Varying Annotations for Face Alignment via Deep  Regression Network
  Jie Zhang*, Meina Kan, Shiguang Shan, Xilin Chen
  
  
  
  
A SPATIO-TEMPORAL APPEARANCE REPRESENTATION FOR VIDEO-BASED PEDESTRIAN  RE-IDENTIFICATION
  Kan Liu, Bingpeng Ma, Wei Zhang, Rui Huang*
  
  
  
  
Task-Driven Feature Pooling for Image Classification
  Guo-Sen Xie*, Xu-Yao Zhang, Xiangbo Shu, Shuicheng Yan, Cheng-Lin Liu
  
  
  
  
Class-Specific Image Deblurring
  Saeed Anwar, Cong Phuoc Huynh, Fatih Porikli*
  
  
  
  
Two Birds, One Stone: Jointly Learning Binary Code for Large-scale Face  Image Retrieval and Attributes Prediction
  Yan Li*, Ruiping Wang, Haomiao Liu, Huajie Jiang, Shiguang Shan, Xilin Chen
  
  
  
  
Cutting Edge: Soft Correspondences in Multimodal Scene Parsing
  Sarah Taghavi Namin*, Mohammad Najafi, Mathieu Salzmann, Lars Petersson
  
  
  
  
Domain Generalization for Object Recognition with Multi-task  Autoencoders
  Muhammad Ghifary*, W. Bastiaan Kleijn, Mengjie Zhang, David Balduzzi
  
  
  
  
COUNT Forest: CO-voting Uncertain Number of Targets using Random Forest  for Crowd Density Estimation
  Viet Pham*, Osamu Yamaguchi, Tatsuo Kozakaya, Ryuzo Okada
  
  
  
  
Guaranteed Outlier Removal for Rotation Search
  Alvaro Parra*, Tat-Jun Chin
  
  
  
  
One Shot Learning via Compositions of Meaningful Patches
  Alex Wong*, Alan Yuille
  
  
  
  
High-for-Low and Low-for-High: Efficient Boundary Detection from Deep  Object Features and its Applications to High-Level Vision
  Gedas Bertasius*, Jianbo Shi, Lorenzo Torresani
  
  
  
  
Discrete Tabu Search for Graph Matching
  Kamil Adamczewski, Yumin Suh, Kyoung Mu Lee*
  
  
  
  
Hyperspectral Compressive Sensing Using Manifold-Structured Sparsity  Prior
  Lei Zhang*, Wei Wei, Yanning Zhang, Qinfeng Shi, Chunhua Shen, Fei Li
  
  
  
  
Efficient Square Localization for Object Detection
  Cewu Lu*, Yongyi Lu, Hao Chen, ChiKeung Tang
  
  
  
  
An Accurate Iris Segmentation Framework under Relaxed Imaging  Constraints using Total Variation Model
  Zijing Zhao*, Kumar Ajay
  
  
  
  
Learning to Boost Filamentary Structure Segmentation
  Lin Gu*, LI Cheng
  
  
  
  
Box Aggregation for Proposal Decimation: Last Mile of Object Detection
  Shu Liu*, Cewu Lu, Jiaya Jia
  
  
  
  
Deep Convolutional Feature Point Descriptors
  Edgar Simo-Serra*, Eduard Trulls, Luis Ferraz, Iasonas Kokkinos, Pascal Fua,  Francesc Moreno-Noguer
  
  
  
  
Look and Think Twice: Capturing Top-Down Visual Attention with Feedback  Convolutional Neural Networks
  Chunshui Cao, Xianming Liu, Jiang Wang, Yinan Yu, Wei Xu, Yi Yang*
  
  
  
  
Unsupervised Domain Adaptation with Imbalanced Cross-Domain Data
  Tzu Ming Harry Hsu, Cheng-An Hou, Wei Yu Chen, Yi-Ren Yeh, Yu-Chiang Frank  Wang*
  
  
  
  
Variational Depth Superresolution using Example-Based Edge  Representations
  David Ferstl*, Gernot Riegler, Matthias Rüther, Horst Bischof
  
  
  
  
FASTex: Efficient Unconstrained Scene Text Detector
  Michal Busta, Lukas Neumann*, Jiri Matas
  
  
  
  
Conditioned Regression Models for Non-Blind Single Image  Super-Resolution
  Gernot Riegler, Samuel Schulter*, Matthias Rüther, Horst Bischof
  
  
  
  
A Gaussian Process Latent Variable Model for BRDF Inference
  Stamatios Georgoulis*, Vincent Vanweddingen, Marc Proesmans, Luc Van Gool
  
  
  
  
Convolutional Sparse Coding for Image Super-resolution
  Shuhang Gu*, Lei Zhang, Wangmeng Zuo, Xiangchu Feng, Deyu Meng, Qi Xie
  
  
  
  
Peeking Template Matching for Depth Extension
  Simon Korman*, Eyal Ofek, Shai Avidan
  
  
  
  
Deformable 3D Fusion: From Partial Dynamic 3D Observations to Complete  4D Models
  Weipeng Xu*, Mathieu Salzmann, Yongtian Wang, Yue Liu
  
  
  
  
Multi-scale recognition with DAG-CNNs
  Songfan Yang*, Deva Ramanan
  
  
  
  
Non-Parametric Structure-Based Calibration of Radially Symmetric Cameras
  Federico Camposeco Paulsen*, Torsten Sattler, Marc Pollefeys
  
  
  
  
Discriminative Pose-Free Descriptors for Face and Object Matching
  Soubhik Sanyal, Sivaram Mudunuri, Soma Biswas*
  
  
  
  
Bi-shifting Auto-Encoder for Unsupervised Domain Adaptation
  Meina Kan*, Shiguang Shan, Xilin Chen
  
  
  
  
Relaxed Multiple-Instance SVM with Application to Object Discovery
  Xinggang Wang*, Zhuotun Zhu, Cong Yao, Xiang Bai
  
  
  
  
Active oneshot scan for wide depth range using a light-field projector  based on coded aperture
  Hiroshi Kawasaki*, Yuki Horita, Yuki Shiba, Satoshi Ono, Ryo Furukawa,  Shinsaku Hiura
  
  
  
  
Multi-Cue Structure Preserving MRF for Unconstrained Video Segmentation
  Saehoon Yi*, Vladimir Pavlovic
  
  
  
  
Regressive Tree Structured Model for Facial Landmark Localization
  Gee-Sern Hsu*, Kai-Hsiang Chang, Shih-Chieh Huang
  
  
  
  
Person Recognition in Personal Photo Collections
  Seong Joon Oh*, Rodrigo Benenson, Mario Fritz, Bernt Schiele
  
  
  
  
Weakly-supervised Structured Output Learning with Flexible and Latent  Graphs using High-order Loss Functions
  Gustavo Carneiro*, tingying Peng, Christine Bayer, Nassir Navab
  
  
  
  
DeepBoxes: Hunting Objects by Cascading Deep Convolutional Layers
  Amir Ghodrati*, Marco Pedersoli, Tinne Tuytelaars, Ali Diba, Luc Van Gool
  
  
  
  
Beyond Tree Structure Models: A New Occlusion Aware Graphical Model for  Human Pose Estimation
  Lianrui Fu*, Junge Zhang, Kaiqi Huang
  
  
  
  
Realtime edge-based visual odometry for a monocular camera
  Juan Tarrio*, Sol Pedre
  
  
  
  
Shell PCA: statistical shape modelling in shell space
  Chao Zhang*, William Smith, Behrend Heeren, Martin Rumpf
  
  
  
  
Secrets of Matrix Factorization: Approximations, Numerics and Manifold  Optimization
  Je Hyeong Hong*, Andrew Fitzgibbon
  
  
  
  
Semantic Segmentation With Object Clique Potential
  QI Xiaojuan*, Shu Liu, Jianping Shi, Renjie Liao, Jiaya Jia
  
  
  
  
Multi-Frame Super-Resolution via Draft-Ensemble Learning
  Renjie Liao*, Xin Tao, Ziyang Ma, Ruiyu Li, Jiaya Jia
  
  
  
  
Pan-sharpening with a Hyper-Laplacian Penalty
  Yiyong Jiang, Xinghao Ding*, Delu Zeng, Yue Huang, John Paisley
  
  
  
  
Structured Learning for Generating Region Proposals with Mid-level Cues
  Tom Lee*, Sanja Fidler, Sven Dickinson
  
  
  
  
FollowMe: Efficient Online Min-Cost Flow Tracking with Bounded Memory  and Computation
  Philip Lenz, Andreas Geiger*, Raquel Urtasun
  
  
  
  
Relaxing from Vocabulary: Robust Weakly-Supervised Deep Learning for  Vocabulary-Free Image Tagging
  Jianlong Fu*, Yue Wu, Tao Mei, Jinqiao Wang, Hanqing Lu, Yong Rui
  
  
  
  
Learning to Divide and Conquer for Online Multi-Target Tracking
  Francesco Solera*, Simone Calderara, Rita Cucchiara
  
  
  
  
Visual Phrases for Exemplar Face Detection
  Vijay Kumar Reddy*, Anoop Namboodiri, C.V. Jawahar
  
  
  
  
Enhancing World Maps by Parsing Aerial Images
  Gellert Mattyus*, Shenlong Wang, Sanja Fidler, Raquel Urtasun
  
  
  
  
Exploiting Object Similarity in Large-Scale 3D Reconstruction
  Chen Zhou, Fatma Güney, Yizhou Wang, Andreas Geiger*
  
  
  
  
Probabilistic Appearance Models for Segmentation and Classification
  Julia Krüger*, Jan Ehrhardt, Heinz Handels
  
  
  
  
HotOrNot: What Images Tell Us About Temperature
  Daniel Glasner*, Pascal Fua, Todd Zickler, Lihi Zelnik-Manor
  
  
  
  
Geometry-aware Deep Transform
  Jiaji Huang*, Qiang Qiu, Robert Calderbank, Guillermo Sapiro
  
  
  
  
Video Restoration against Yin-Yang Phasing
  Xiaolin Wu*, Zhenhao Li, Xiaowei Deng
  
  
  
  
Rolling Shutter Super-Resolution
  Abhijith Punnappurath*, Vijay Rengarajan, A N Rajagopalan
  
  
  
  
Im2Calories: towards an automated mobile vision food diary
  Alex Gorban, Nick Johnston, Anoop Korattikara, George Papandreou, Vivek  Rathod, Kevin Murphy*, Sergio Guadarrama
  
  
  
  
You Are Here: Mimicking the Human Thinking Process in Reading  Floor-Plans
  Hang Chu*, Dong Ki Kim, Tsuhan Chen
  
  
  
  
Automatic Concept Discovery from Parallel Text and Visual Corpora
  Chen Sun*, Chuang Gan, Ram Nevatia
  
  
  
  
Simpler non-parametric methods provide as good or better results to  multiple-instance learning.
  Ragav Venkatesan*, Parag Chandakkar, Baoxin Li
  
  
  
  
Minimizing Human Effort in Interactive Tracking by Incremental Learning  of Model Parameters
  Arridhana Ciptadi*, James Rehg
  
  
  
  
Robust Statistical Face Frontalization
  Christos Sagonas*, Yannis Panagakis, Stefanos Zafeiriou, Maja Pantic
  
  
  
  
MAP Disparity Estimation using Hidden Markov Trees
  Eric Psota*, Jedrzej Kowalczuk, Mateusz Mittek, Lance Pérez
  
  
  
  
Model-Based Tracking at 300Hz using Raw Time-of-Flight Observations
  Jan Stühmer*, Sebastian Nowozin, Andrew Fitzgibbon, Richard Szeliski, Travis  Perry, Sunil Acharya, Daniel Cremers, Jamie Shotton
  
  
  
  
LEWIS: Latent Embeddings for Word Images and their Semantics
  Albert Gordo*, Jon Almazan, Naila Murray, Florent Perronin
  
  
  
  
Learning Binary Codes for Maximum Inner Product Search
  Fumin Shen*, Shaoting Zhang, Heng Tao Shen, Wei Liu
  
  
  
  
Learning Large-Scale Automatic Image Colorization
  Aditya Deshpande*, Jason Rock, David Forsyth
  
  
  
  
Robust 3D Object Detection and Tracking from Minimal Image Information
  Alberto Crivellaro*, Mahdi Rad, Yannick Verdie, Kwang Yi, Pascal Fua, Vincent  Lepetit
  
  
  
  
Motion Trajectory Segmentation via Minimum Cost Multicuts
  Margret Keuper*, Bjoern Andres, Thomas Brox
  
  
  
  
Building Dynamic Cloud Maps from the Ground Up
  Calvin Murdock*, Nathan Jacobs, Robert Pless
  
  
  
  
Multi-view convolutional neural networks for 3D shape recognition
  Hang Su*, Subhransu Maji, Erik Miller, Evangelos Kalogerakis
  
  
  
  
Wide Baseline Stereo Matching with Convex Bounded-Distortion Constraints
  Meirav Galun*, Tal Amir, Tal Hassner, Ronen Basri, Yaron Lipman
  
  
  
  
ML-MG: Multi-label Learning with Missing Labels Using a Mixed Graph
  Baoyuan Wu*, Siwei Lyu, Bernard Ghanem
  
  
  
  
Spatial Semantic Regularisation for Large Scale Object Detection
  Damian Mrowca*, Marcus Rohrbach, Judy Hoffman, Ronghang Hu, Kate Saenko,  Trevor Darrell
  
  
  
  
A Randomized Ensemble Approach to Industrial CT Segmentation
  Hyojin Kim*, Jayaraman Jayaraman Thiagarajan, Peer-Timo Bremer
  
  
  
  
Action Localization in Videos through Context Walk
  Khurram Soomro*, Haroon Idrees, Mubarak Shah
  
  
  
  
Zero-Shot Learning via Semantic Similarity Embedding
  Ziming Zhang*, Venkatesh Saligrama
  
  
  
  
Bayesian Model Adaptation for Crowd Counts
  Bo Liu*, Nuno Vasconcelos
  
  
  
  
Monocular Object Instance Segmentation and Depth Ordering with CNNs
  Ziyu Zhang*, Alexander Schwing, Raquel Urtasun, Sanja Fidler
  
  
  
  
Compression Artifacts Reduction by Deep Convolutional Network
  Chao Dong, Yubin Deng, Chen-Change Loy*, Xiaoou Tang
  
  
  
  
Amodal Completion and Size Constancy in Natural Scenes
  Abhishek Kar*, Shubham Tulsiani, Joao Carreira, Jitendra Malik
  
  
  
  
RGB-W: When Vision Meets Wireless
  Alexandre Alahi*, Albert Haque, Fei-Fei Li
  
  
  
  
Semi-Supervised Normalized Cuts for Image Segmentation
  Selene Chew, Nathan Cahill*
  
  
  
  
PIEFA: Personalized Incremental and Ensemble Face Alignment in the Wild
  Xi Peng*, Yu Yang, Shaoting Zhang, Dimitris Metaxas
  
  
  
  
Understanding Everyday Hands in Action from RGB-D Images
  Gregory Rogez*, James Supancic III, Deva Ramanan
  
  
  
  
Multimodal Convolutional Neural Networks for Matching Image and Sentence
  Lin Ma*, Zhengdong Lu, Lifeng Shang, Hang Li
  
  
  
  
Per-Sample Kernel Adaptation for Visual Recognition and Grouping
  Borislav Antic*, Bjorn Ommer
  
  
  
  
Structural Kernel Learning for Large Scale Multiclass Object  Co-Detection
  Zeeshan Hayder*, Xuming He, Mathieu Salzmann
  
  
  
  
An NMF perspective on Binary Hashing
  Lopamudra Mukherjee*, Sathya Ravi, Vamsi Ithapu
  
  
  
  
Interactive Visual Hull Refinement for Specular and Transparent Object  Surface Reconstruction
  Xinxin Zuo*, University of Kentucky, Chao Du, Sen Wang, Jiangbin Zheng,  Ruigang Yang
  
  
  
  
Learning Visual Clothing Style with Heterogeneous Dyads from  Co-occurrence
  Andreas Veit*, Balazs Kovacs, Sean Bell, Julian McAuley, Kavita Bala, Serge  Belongie
  
  
  
  
Multiple-hypotheses affine region estimation by anisotropic LoG filter
  Takahiro Hasegawa*, Mitsuru Ambai, Gou Koutaki, Kohta Ishikawa, Yuji  Yamauchi, Takayoshi Yamashita, Hironobu Fujiyoshi
  
  
  
  
Learning where to position parts in 3D
  Marco Pedersoli*, Tinne Tuytelaars
  
  
  
  
Globally Linear Approximation to Nonlinear Learning for Visual Tracking
  Bo Ma*, Hongwei Hu, Yuping Zhang, Jianbing Shen, Fatih Porikli
  
  
  
  
Flickr30k Entities: Collecting Region-to-Phrase Correspondences for  Richer Image-to-Sentence Models
  Bryan Plummer*, Liwei Wang, Chris Cervantes, Juan Caicedo, Julia Hockenmaier,  Svetlana Lazebnik
  
  
  
  
Context Aware Online Adaptation of Activity Recognition Models
  MAHMUDUL HASAN*, Amit Roy-Chowdhury
  
  
  
  
Predicting Depth, Surface Normals and Semantic Labels with a Common  Multi-Scale Convolutional Architecture
  David Eigen*, Rob Fergus
  
  
  
  
Self-Occlusions and Disocclusions in Causal Video Object Segmentation
  Yanchao Yang*, Ganesh Sundaramoorthi, Stefano Soatto
  
  
  
  
Action Recognition by Hierarchical Mid-level Action Elements
  Yuke Zhu, Amir Zamir, Silvio Savarese, Tian Lan*
  
  
  
  
Selecting Relevant Web Trained Concepts for Automated Event Retrieval
  Bharat Singh*, Xintong Han, Zhe Wu, Vlad Morariu, Larry Davis
  
  
  
  
Action Detection by Implicit Intentional Motion Clustering
  Wei Chen*, Jason Corso
  
  
  
  
Beyond Covariance: Feature Representation with Nonlinear Kernel matrices
  Lei Wang*, Jianjia Zhang, Luping Zhou, Chang Tang, Wanqing Li
  
  
  
  
3D Indoor Scene Labelling with Hierarchical Higher-order Regression  Forest Fields
  Trung Pham*, Ian Reid, Stephen Gould, Yasir Latif
  
  
  
  
Multiresolution hierarchy co-clustering for semantic segmentation in  sequences with small variations
  David Varas*, Ferran Marques
  
  
  
  
AttentionNet: Aggregating Weak Directions for Accurate Object Detection
  Donggeun Yoo*, Sunggyun Park, Joon-Young Lee, Anthony Paek, In So Kweon
  
  
  
  
Objects2action: Classifying and localizing actions without any video  example
  Mihir Jain*, Jan van Gemert, Thomas Mensink, Cees Snoek
  
  
  
  
Query Adaptive Similarity Measure for RGB-D Object Recognition
  Yanhua Cheng*, CASIA, Rui Cai, Zhiwei Li, Xin Zhao, Kaiqi Huang, Yong Rui
  
  
  
  
Human Action Recognition using Factorized Spatio-Temporal Convolutional  Networks
  LIN SUN*, Kui Jia, Dit-Yan Yeung, Bertram Shi
  
  
  
  
Fine-Grained Change Detection of Misaligned Scenes with Varied  Illuminations
  Wei Feng*, Fei-Peng Tian, Qian Zhang, Nan Zhang, Liang Wan, Jizhou Sun
  
  
  
  
A Wavefront Marching Method for Solving the Eikonal Equation on  Cartesian Grids
  Brais Cancela*, Marcos Ortega, Manuel Penedo
  
  
  
  
StereoSnakes: Contour Based Consistent Object Extraction For Stereo  Images
  Ran Ju, Tongwei Ren, Gangshan Wu*
  
  
  
  
Example-Based Modeling of Facial Texture from Deficient Data
  Arnaud Dessein*, William Smith, Richard Wilson, Edwin Hancock
  
  
  
  
Common Subspace for Model and Similarity: Phrase Learning for Sentence  Generation from Images
  Yoshitaka Ushiku*, Yusuke Mukuta, Masataka Yamaguchi, Tatsuya Harada
  
  
  
  
Simultaneous foreground detection and classification with hybrid  features
  Jaemyun Kim*, Adin Ramirez Rivera, Byungyong Ryu, Oksam Chae
  
  
  
  
Classical Scaling Revisited
  Gil Shamai*, Yonathan Aflalo, Ron Kimmel, Michael Zibulevsky
  
  
  
  
Aggregating local deep features for image retrieval
  Artem Babenko*, Victor Lempitsky
  
  
  
  
A Self-paced Multiple-instance Learning Framework for Co-saliency  Detection
  Dingwen Zhang, Deyu Meng, Chao Li, Lu Jiang, Qian Zhao, Junwei Han*
  
  
  
  
Matrix Backpropagation for Deep networks with Structured Layers
  Catalin Ionescu*, Orestis Vantzos, Cristian Sminchisescu
  
  
  
  
Bayesian non-parametric inference for manifold based MoCap  representation
  Fabrizio Natola*, Valsamis Ntouskos, Fiora Pirri, Marta Sanzari
  
  
  
  
Learning to Predict Saliency on Face Images
  Mai Xu*, Yun Ren
  
  
  
  
Person Re-Identification Ranking Optimisation by Discriminant Context  Information Analysis
  Jorge García*, Niki Martinel, christian Micheloni, Alfredo Gardel
  
  
  
  
Introducing Geometry into Active Learning for Image Segmentation
  Ksenia Konyushkova*, Raphael Sznitman, Pascal Fua
  
  
  
  
Hyperspectral Super-Resolution by Coupled Spectral Unmixing
  Charis Alexandros Lanaras*, Emmanuel Baltsavias, Konrad Schindler
  
  
  
  
Efficient Classifier Training for Electron Microscopy Segmentation
  Toufiq Parag*
  
  
  
  
Learning Analysis-by-Synthesis for 6D Pose Estimation in RGB-D Images
  Alexander Krull*, Eric Brachmann, Frank Michel, Michael Ying Yang, Stefan  Gumhold, Carsten Rother
  
  
  
  
Dense Continuous-Time Tracking and Mapping with Rolling Shutter RGB-D  Cameras
  Christian Kerl*, Jörg Stückler, Daniel Cremers
  
  
  
  
Large Displacement 3D Scene Flow with Occlusion Reasoning
  Andrei Zanfir*, Cristian Sminchisescu
  
  
  
  
Dense image registration and deformable surface reconstruction in  presence of occlusions and minimal texture
  Dat Tien Ngo*, Sanghyuk Park, Anne Jorstad, Alberto Crivellaro, Chang Yoo,  Pascal Fua
  
  
  
  
3D Surface Profilometry using Phase Shifting of De Bruijn Pattern
  Matea Donlic*, Tomislav Petkovic, Tomislav Pribanic
  
  
  
  
Listening by Eyes: Towards a Practical Visual Speech Recognition System  Using Deep Boltzmann Machines
  Chao Sui*, Mohammed Bennamoun, Roberto Togneri
  
  
  
  
Multi-view Domain Generalization for Visual Recognition
  Li Niu*, Wen Li, Dong Xu
  
  
  
  
Human Pose Estimation in Videos
  Dong Zhang*, Mubarak Shah
  
  
  
  
Semantic Segmentation of RGBD Images with Mutex Constraints
  Zhuo Deng*, Sinisa Todorovic, Longin Jan Latecki
  
  
  
  
Learning Deep Object Detectors from 3D Models
  Xingchao Peng*, Kate Saenko, Baochen Sun, Karim Ali
  
  
  
  
External patch prior guided internal clustering for image denoising
  Fei Chen*, Lei Zhang, Huimin Yu
  
  
  
  
The Likelihood-Ratio Test and Efficient Robust Estimation
  Andrea Cohen, Christopher Zach*
  
  
  
  
Reflection Modeling for Passive Stereo
  Rahul Nair*, Andrew Fitzgibbon, Daniel Kondermann, Carsten Rother
  
  
  
  
Harvesting Discriminative Meta Objects with Deep CNN Features for Scene  Classification
  Ruobing Wu, Baoyuan Wang, Yizhou Yu*
  
  
  
  
Cluster-based point set saliency
  Flora Ponjou Tasse*, Jiri Kosinka, Neil Dodgson
  
  
  
  
Co-interest of Multiple Wearable Cameras
  Yuewei Lin*, Kareem Abdelfatah, Youjie Zhou, xiaochuan Fan, Hongkai Yu, Hui  Qian, Song Wang
  
  
  
  
Infinite Feature Selection
  Giorgio Roffo*, Simone Melzi, Marco Cristani
  
  
  
  
Scalable Nonlinear Embeddings for Semantic Category-based Image  Retrieval
  Gaurav Sharma*, Bernt Schiele
  
  
  
  
Deep Temporal Appearance-Geometry Network for Facial Expression  Recognition
  Heechul Jung*, Sihaeng Lee, JUNHO YIM, Sunjeong Park, Junmo Kim
  
  
  
  
Direct Intrinsics: Albedo and Shading Decomposition by CNN Regression
  Takuya Narihira*, Michael Maire, Stella Yu
  
  
  
  
On Statistical Analysis of Neuroimages with Imperfect Registration
  Won Hwa Kim*, Sathya Ravi, Ozioma Okonkwo, Sterling Johnson, Vikas Singh
  
  
  
  
Detailed Full-Body Reconstructions of Moving People from Monocular RGB-D  Sequences
  Federica Bogo*, Javier Romero, Matthew Loper, Michael Black
  
  
  
  
Efficient Solution to the Relative Pose Problem for Radially Distorted  Cameras
  Zuzana Kukelova*, Jan Heller, Martin Bujnak, Andrew Fitzgibbon, Tomas Pajdla
  
  
  
  
Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image  Segmentation
  George Papandreou, Liang-Chieh Chen*, Kevin Murphy, Alan Yuille
  
  
  
  
Learning a Descriptor-specific 3D Keypoint Detector
  Samuele Salti*, Federico Tombari, Riccardo Spezialetti, Luigi Di Stefano
  
  
  
  
Component-wise modeling of articulated objects
  Valsamis Ntouskos*, Marta Sanzari, Bruno Cafaro, Federico Nardi, Fabrizio  Natola, Fiora Pirri, Manuel Ruiz Garcia
  
  
  
  
Semi-supervised Zero-Shot Classification with Label Representation  Learning
  Xin Li, Yuhong Guo*, Dale Schuurmans
  
  
  
  
Depth Selective Camera: A Direct, On-chip, Programmable Technique for  Depth Selectivity in Photography
  Ryuichi Tadano*, Adithya Pediredla, Ashok Veeraraghavan
  
  
  
  
A Supervised Low-rank Method for Learning Invariant Subspaces
  Gianfranco Doretto*
  
  
  
  
Efficient Decomposition of Image and Mesh Graphs by Lifted Multicuts
  Margret Keuper, Evgeny Levinkov, Nicolas Bonneel, Guillaume Lavoue, Thomas  Brox, Bjoern Andres*
  
  
  
  
Recursive Frechet Mean Computation on the Grassmann and its Applications  to Computer Vision
  Rudrasis Chakraborty*, Baba Vemuri
  
  
  
  
A collaborative filtering approach to real-time hand pose estimation
  Chiho Choi*, Ayan Sinha, Joon Hee Choi, Sujin Jang, Karthik Ramani
  
  
  
  
Self-calibration of optical lenses
  Michael Hirsch*, Bernhard Schölkopf
  
  
  
  
Multi-Modal Subspace Clustering
  Hongchang Gao, Feiping Nie, Heng Huang*
  
  
  
  
Predicting Deep Zero-Shot Convolutional Neural Networks using Textual  Descriptions
  Jimmy Ba*, Kevin Swersky, Ruslan salakhutdinov, Sanja Fidler
  
  
  
  
A Projection free method for Generalized Eigenvalue Problem with a  nonsmooth Regularizer
  Seong Jae Hwang*, Maxwell Collins, Sathya Ravi, Vamsi Ithapu, Nagesh Adluru,  Sterling Johnson, Vikas Singh
  
  
  
  
Optimizing expected Intersection-over-Union with candidate-constrained  CRFs
  Faruk Ahmed*, Vittal Premachandran, Dany Tarlow, Dhruv Batra
  
  
  
  
Structured Feature Selection
  Tian Gao*, Ziheng Wang, Qiang Ji
  
  
  
  
Higher-Order Inference for Multi-class Log-supermodular Models
  Jian Zhang*, Josip Djolonga, Andreas Krause
  
  
  
  
Semantic Video Entity Linking based on Visual Content and Metadata
  Yuncheng Li*, Xitong Yang, Jiebo Luo
  
  
  
  
On the Equivalence of Moving Entrance Pupil and Radial Distortion for  Camera Calibration
  Avinash Kumar*, Narendra Ahuja
  
  
  
  
Group Membership Prediction
  Ziming Zhang*, Yuting Chen, Venkatesh Saligrama
  
  
  
  
A Deep Visual Correspondence Embedding Model for Stereo Matching Costs
  Zhuoyuan Chen*, Xun Sun, Yinan Yu, Wang Liang, Chang Huang, Haoyuan Gao, Kai  Yu
  
  
  
  
A Linear Generalized Camera Calibration from Three Intersecting  Reference Planes
  Mai Nishimura, Shohei Nobuhara*, Takashi Matsuyama
  
  
  
  
Conditional High-order Boltzmann Machine: A Supervised Learning Model  for Relation Learning
  Yan Huang*, Wei Wang, Liang Wang
  
  
  
  
Text Flow: A Unified Text Detection System in Natural Scene Images
  Shangxuan Tian*, Yifeng Pan, Chang Huang, Shijian Lu, Kai Yu, Chew Lim Tan
  
  
  
  
Illumination Robust Color Naming via Label Propagation
  yuanliu liu, Zejian Yuan*
  
  
  
  
Towards Pointless Structure from Motion: 3D reconstruction and camera  calibration from general 3D curves
  Irina Nurutdinova, Andrew Fitzgibbon*
  
  
  
  
Learning Image and User Features for Recommendation in Social Networks
  Xue Geng, Hanwang Zhang*, Jingwen Bian, Tag-Seng Chua
  
  
  
  
Contour Box: Rejecting Object Proposals Without Explicit Closed Contours
  Cewu Lu, ChiKeung Tang*
  
回复

使用道具 举报

您需要登录后才可以回帖 登录 | 立即注册

本版积分规则

Archiver|手机版|小黑屋|Vision And Learning SEminar    

GMT+8, 2017-2-20 18:56 , Processed in 0.122955 second(s), 27 queries .

Powered by Discuz! X3.2

© 2001-2013 Comsenz Inc.

快速回复 返回顶部 返回列表