Similar Items: Count Anything at Any Granularity
- MoCapAnything V2: End-to-End Motion Capture for Arbitrary Skeletons
- Does it Really Count? Assessing Semantic Grounding in Text-Guided Class-Agnostic Counting
- ResiHMR: Residual-Limb Aware Single-Image 3D Human Mesh Recovery for Individuals with Limb Loss
- Are DeepFakes Realistic Enough? Exploring Semantic Mismatch as a Novel Challenge
- Echo-α: Large Agentic Multimodal Reasoning Model for Ultrasound Interpretation
- AesRM: Improving Video Aesthetics with Expert-Level Feedback