TraCE: Trajectory-Aware Concepts for Explainable Video Understanding
cs.CV
Submitted: 2026-11-04
Updated: 2026-11-06
Project page: https://leewooil.github.io/TraCE_project_page
Terminology
Sources
- Qwen3-VL Technical Report
- VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs
- Representation Learning with Contrastive Predictive Coding
- OpenAI GPT-5 System Card
- UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
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