multi-modal learning

5 papers

• CAML: Collaborative Auxiliary Modality Learning for Multi-Agent Systems
• COCONut-PanCap: Joint Panoptic Segmentation and Grounded Captions for Fine-Grained Understanding and Generation
• DAVE: Diagnostic benchmark for Audio Visual Evaluation
• Hierarchical Semantic-Augmented Navigation: Optimal Transport and Graph-Driven Reasoning for Vision-Language Navigation
• OctoNet: A Large-Scale Multi-Modal Dataset for Human Activity Understanding Grounded in Motion-Captured 3D Pose Labels