Research map / Video / Video-language understanding
VTimeCoT: Thinking by Drawing for Video Temporal Grounding and Reasoning
Jinglei Zhang, Yuanfan Guo, Rolandos Alexandros Potamias, Jiankang Deng, Hang Xu, Chao Ma
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add text-only chain-of-thought (ablation) | GPT4o · QVHighlights | mIoU: 37.66 -> 41.85 | Improved |
| add progress bar to CoT (ablation) | GPT4o · QVHighlights | mIoU: 41.85 -> 49.40 | Improved |
| add highlight tool to CoT + progress bar (ablation) | GPT4o · QVHighlights | mIoU: 49.40 -> 54.49 | Improved |
| add text-only chain-of-thought (ablation) | GPT4o · Vript-RR (multiple choice) | accuracy: 70.39 -> 73.68 | Improved |
| add progress bar to CoT (ablation) | GPT4o · Vript-RR (multiple choice) | accuracy: 73.68 -> 76.32 | Improved |
| add highlight tool to CoT + progress bar (ablation) | GPT4o · Vript-RR (multiple choice) | accuracy: 76.32 -> 83.55 | Improved |
| wrap Qwen2VL-7B in VTimeCoT | Qwen2VL-7B · Charades-STA | mIoU: 24.34 -> 43.41 | Improved |
| wrap GPT4o in VTimeCoT | GPT4o · Charades-STA | R1@0.5: 37.12 -> 51.02 | Improved |
| wrap GPT4o in VTimeCoT | GPT4o · QVHighlights | mIoU: 37.66 -> 54.49 | Improved |
| wrap Qwen2VL-7B in VTimeCoT | Qwen2VL-7B · Vript-RR (open-ended) | accuracy: 35.95 -> 41.45 | Improved |
| wrap GPT4o in VTimeCoT | GPT4o · VideoMME (w. subtitles) | accuracy: 65.1 -> 73.6 | Improved |
| wrap GPT4o in VTimeCoT | GPT4o · VideoMME (w/o subtitles) | accuracy: 61.6 -> 64.2 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- VTimeLLM-13B — VTimeLLM: Empower LLM to Grasp Video Moments (CVPR 2024) · better on 6 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- VGR: Visual Grounded Reasoning (ICLR 2026 · similarity 0.90)
- Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition (ICML 2024 · similarity 0.89)
- Divide and Conquer: Exploring Language-centric Tree Reasoning for Video Question-Answering (ICML 2025 · similarity 0.89)
- Modularized Self-Reflected Video Reasoner for Multimodal LLM with Application to Video Question Answering (ICML 2025 · similarity 0.89)
- VTimeLLM: Empower LLM to Grasp Video Moments (CVPR 2024 · similarity 0.88)
- Temporal Reasoning Transfer from Text to Video (ICLR 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
