Fine-grained Motion Retrieval via Joint-Angle Motion Images and Token-Patch Late Interaction
cs.CV, cs.IR
Submitted: 2026-03-10
Updated: 2026-11-02
Terminology
Sources
- Beyond Global Alignment: Fine-Grained Motion-Language Retrieval via Pyramidal Shapley-Taylor Learning
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- RoBERTa: A Robustly Optimized BERT Pretraining Approach
- Decoupled Weight Decay Regularization
- Absolute Coordinates Make Motion Generation Easy
- WaMo: Wavelet-Enhanced Multi-Frequency Trajectory Analysis for Fine-Grained Text-Motion Retrieval
- Using joint angles based on the international biomechanical standards for human action recognition and related tasks
- Human Motion Diffusion Model
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs