CVPR Daily - Friday

4.1.1: Multi-Level Feature Learning for Contrastive Multi-View Clustering 4.1.1: SLIC: Self-Supervised Learning With Iterative Clustering for Human Action Videos 4.1.1: Class- Incremental Learning by Knowledge Distillation With Adaptive Feature… 4.1.1: Versatile Multi-Modal Pre-Training for Human-Centric Perception 4.1.3: Towards General Purpose Vision Systems: An End-to-End Task- Agnostic Vision… 4.1.3: Robust Cross-Modal Representation Learning With Progressive Self-Distillation 4.1.55a: On Learning Contrastive Representations for Learning With Noisy Labels Cigdem’s picks of the day: Cigdem Beyan (@BeyanCigdem) is an Assistant Professor in the Department of Information Engineering and Computer Science, University of Trento, Italy where she is a part of the MHUG research group. She is also an Affiliated Researcher in the Pattern Analysis and Computer Vision (PAVIS) research line in Istituto Italiano di Tecnologia, Genoa, Italy. She has been named outstanding reviewer at CVPR 2022. Cigdem pursues a very multidisciplinary research by keeping computer vision and machine learning as the core fields. She is interested in automatic understanding of human actions, interactions and emotions and transferring all these skills to humanoid robots. Some recent research of her includes: domain adaptation for gaze target detection, unsupervised skeleton based action recognition, egocentric (inter-) action anticipation, human soft skills (e.g., leadership, personality traits) estimation, full-body movement based emotion recognition, and visual voice activity detection. For today, Friday 24 2 Cigdem’s Picks DAILY CVPR Friday Orals Poster