l Imaging and low-level related n Computational photography n Low-level and physics-based vision l 3D related n 3D from a single image and shape-from-x n Stereo, 3D from multiview and other sensors n SLAM n Computer Vision with 3D l Fundamental and Generic CV tasks n Representation learning n Detection and localization in 2D n Recognition and classification n Segmentation, grouping and shape n Motion and tracking n Scene text and document understanding n Scene analysis and understanding n Video analysis and understanding n Image and video retrieval n Image and video synthesis n Image and video manipulation detection and integrity method n Anomaly detection l Methods(esp. Learning) for Vision n Adversarial learning n Self-supervised Learning n Knowledge leveraging for CV n Transfer/Low-shot/Semi-supervised learning n Brain-inspired CV n Transformer/Attention for CV n Graph models for CV l New machine learning theory and methods n Meta-learning n Incremental learning/continual learning/curriculum learning n Machine learning architectures and formulations n Causality learning n Efficient training and inference methods n Optimization and learning methods l Reliable CV models n Explainable CV models n Fairness, accountability, transparency, and ethics in vision n Visual reasoning and logical representation l Human-centered CV n Face recognition related n Biometrics (except face) n Vision-based affective computing (e.g., expression recognition) n Medical image analysis n Human re-ID n Action and behavior recognition n Gestures and body pose l Vision + X n Vision + language n Vision + audio n Vision + other modalities l Vision for X n X=机器人 n X=自动驾驶汽车 n X=无人机 n X=产品瑕疵检测 n X=医疗(精神性疾病) n X=健康养老 n X=Biology (animals…) n X=energy and power l Other topics n Heterogeneous pattern recognition n Occlusion-robust CV models |
小黑屋|手机版|Archiver|Vision And Learning SEminar
GMT+8, 2024-10-13 14:42 , Processed in 0.012913 second(s), 14 queries .
Powered by Discuz! X3.4
Copyright © 2001-2020, Tencent Cloud.