zero-shot settings
- Boosting Skeleton-based Zero-Shot Action Recognition with Training-Free Test-Time Adaptation
- InstructHOI: Context-Aware Instruction for Multi-Modal Reasoning in Human-Object Interaction Detection
- NavBench: Probing Multimodal Large Language Models for Embodied Navigation
- RPG360: Robust 360 Depth Estimation with Perspective Foundation Models and Graph Optimization
- VLM-R³: Region Recognition, Reasoning, and Refinement for Enhanced Multimodal Chain-of-Thought
- X-Mahalanobis: Transformer Feature Mixing for Reliable OOD Detection
- mmWalk: Towards Multi-modal Multi-view Walking Assistance