VALSE 2025 Poster 展示交流活动圆满结束

2025年6月7日，第十五届视觉与学习青年学者研讨会 (VALSE 2025)在珠海国际会展中心进行了两场Poster展示交流活动。本次展示包括了近两年发表的398篇优秀研究成果，涵盖四大方向：生成、恢复与合成；大型模型与多模态交互；感知、识别与重建；学习策略、基准与应用。

为了进一步促进学术交流，本次大会特别设计了“点赞”机制——每位参会者可以为自己喜爱的Poster点赞支持。经过统计，十一篇人气Poster信息如下：

人气Poster列表：

论文题目：DifIISR: Diffusion Model with Gradient Guidance for Infrared Image Super-Resolution

讲者单位：大连理工大学

期刊或会议：IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2025

全部作者：Xingyuan Li, Zirui Wang, Yang Zou, Zhixin Chen, Jun Ma, Zhiying Jiang, Long Ma, Jinyuan Liu

论文题目：HyperSIGMA: Hyperspectral Intelligence Comprehension Foundation Model

讲者单位：武汉大学

期刊或会议：IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI) 2025

全部作者：Di Wang, Meiqi Hu, Yao Jin, Yuchun Miao, Jiaqi Yang, Yichu Xu, Xiaolei Qin, Jiaqi Ma, Lingyu Sun, Chenxing Li, Chuan Fu, Hongruixuan Chen, Chengxi Han, Naoto Yokoya, Jing Zhang, Minqiang Xu, Lin Liu, Lefei Zhang, Chen Wu, Bo Du, Dacheng Tao, Liangpei Zhang

论文题目：MulFS-CAP: Multimodal Fusion-supervised Cross-modality Alignment Perception for Unregistered Infrared-visible Image Fusion

讲者单位：昆明理工大学

期刊或会议：IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI) 2025

全部作者：Huafeng Li, Zengyi Yang, Yafei Zhang, Wei Jia, Zhengtao Yu, Yu Liu

论文题目：Pedestrian Attribute Recognition: A New Benchmark Dataset and A Large Language Model Augmented Framework

讲者单位：安徽大学

期刊或会议：AAAI Conference on Artificial Intelligence (AAAI) 2025

全部作者：Jiandong Jin, Xiao Wang, Qian Zhu, Haiyang Wang, Chenglong Li

论文题目：SegEarth-OV: Towards Training-Free Open-Vocabulary Segmentation for Remote Sensing Images

讲者单位：西安交通大学

期刊或会议：IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2025

全部作者：Kaiyu Li, Ruixun Liu, Xiangyong Cao, Xueru Bai, Feng Zhou, Deyu Meng, Zhi Wang

论文题目：Real-world Image Dehazing with Coherence-based Pseudo Labeling and Cooperative Unfolding Network

讲者单位：清华大学

期刊或会议：Conference on Neural Information Processing Systems (NeurIPS) 2024

全部作者：Chengyu Fang, Chunming He, Fengyang Xiao, Yulun Zhang, Longxiang Tang, Yuelin Zhang, Kai Li, Xiu Li

论文题目：HyperFree: A Channel-adaptive and Tuning-free Foundation Model for Hyperspectral Remote Sensing Imagery

讲者单位：武汉大学

期刊或会议：IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2025

全部作者：Jingtao Li, Yingyi Liu, Xinyu Wang, Yunning Peng, Chen Sun, Shaoyu Wang, Zhendong Sun, Tian Ke, Xiao Jiang, Tangwei Lu, Anran Zhao, Yanfei Zhong

论文题目：MMRole: A Comprehensive Framework for Developing and Evaluating Multimodal Role-Playing Agents

讲者单位：中国人民大学高瓴人工智能学院

期刊或会议：International Conference on Learning Representations (ICLR) 2025

全部作者：Yanqi Dai, Huanran Hu, Lei Wang, Shengjie Jin, Xu Chen, Zhiwu Lu

论文题目：Towards Unified Deep Image Deraining: A Survey and A New Benchmark

讲者单位：南京理工大学

期刊或会议：IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2025

全部作者：Xiang Chen, Jinshan Pan, Jiangxin Dong, Jinhui Tang

论文题目：DyFo: A Training-Free Dynamic Focus Visual Search for Enhancing LMMs in Fine-Grained Visual Understanding

讲者单位：北京大学

期刊或会议：IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2025

全部作者：Geng Li, Jinglin Xu, Yunzhen Zhao, Yuxin Peng

论文题目：Multi-modal Agent Tuning: Building a VLM-Driven Agent for Efficient Tool Usage

讲者单位：北京大学

期刊或会议：International Conference on Learning Representations (ICLR) 2025

全部作者：Zhi Gao, Bofei Zhang, Pengxiang Li, Xiaojian Ma, Yue Fan, Tao Yuan, Yuwei Wu, Yunde Jia, Songchun Zhu, Qing Li