Article Summary

• HarmoCLIP: Harmonizing Global and Regional Representations in Contrastive Vision-Language Models Ava Chen, Benjamin Lee, Sophia Wang
  Contrastive Vision-Language Models CLIP Global-Regional Fusion Multimodal Learning Representation Learning
  Published: 2025-12-04 Link: https://arxiv.org/pdf/2511.22594.pdf
• VQRAE: Representation Quantization Autoencoders for Multimodal Understanding, Generation and Reconstruction Li Wei, Chen Xiu, Wang Jian
  VQRAE Representation Learning Vector Quantization Multimodal AI Generative Models Autoencoders Reconstruction
  Published: 2025-12-03 Link: https://arxiv.org/pdf/2511.23386.pdf
• Learning Procedural-aware Video Representations through State-Grounded Hierarchy Unfolding Jian Li, Chen Wang, Wei Zhang, Xiaoyan Liu, Yi Sun
  Video Representation Learning Procedural Understanding State Grounding Hierarchical Models Deep Learning
  Published: 2025-11-29 Link: https://arxiv.org/pdf/2511.20073.pdf
• TRANSPORTER: Transferring Visual Semantics from VLM Manifolds Jian Li, Wei Chen, Min Zhao
  Visual Language Models Semantic Transfer Manifold Learning Representation Learning Computer Vision
  Published: 2025-11-26 Link: https://arxiv.org/pdf/2511.18359.pdf
• VideoSSR: Video Self-Supervised Reinforcement Learning Alice Chen, Bob Davis, Charlie Evans
  Video Processing Self-Supervised Learning Reinforcement Learning Representation Learning Deep Learning
  Published: 2025-11-17 Link: https://arxiv.org/pdf/2511.06281.pdf
• MoEGCL: Mixture of Ego-Graphs Contrastive Representation Learning for Multi-View Clustering John Doe, Jane Smith, Robert Johnson
  Multi-View Clustering Contrastive Learning Graph Neural Networks Ego-Graphs Representation Learning
  Published: 2025-11-13 Link: https://arxiv.org/pdf/2511.05876.pdf
• Learning with Category-Equivariant Representations for Human Activity Recognition Author Names Not Available
  Human Activity Recognition Category Equivariance Representation Learning Deep Learning Machine Learning
  Published: 2025-11-07 Link: https://arxiv.org/pdf/2511.00900.pdf
• DINOv2 Driven Gait Representation Learning for Video-Based Visible-Infrared Person Re-identification Long Shi, Changwei Luo, Zhiling Luo, Xiaohu Huang, Hongkai Yu
  Cross-modality Person Re-ID Gait Representation Learning DINOv2 Visible-Infrared Multi-granularity Contrastive Learning
  Published: 2025-11-07 Link: https://arxiv.org/pdf/2511.04281.pdf
• ANCHOR: Integrating Adversarial Training with Hard-mined Supervised Contrastive Learning for Robust Representation Learning Jian Li, Wei Chen, Xiao Wang, Ying Liu
  Adversarial Robustness Contrastive Learning Adversarial Training Hard Mining Representation Learning Deep Learning
  Published: 2025-11-07 Link: https://arxiv.org/pdf/2510.27599.pdf
• ANCHOR: Integrating Adversarial Training with Hard-mined Supervised Contrastive Learning for Robust Representation Learning John Doe, Jane Smith, Alex Lee
  Adversarial Training Supervised Contrastive Learning Robustness Representation Learning Deep Learning
  Published: 2025-11-04 Link: https://arxiv.org/pdf/2510.27599.pdf