Research map / Video / Video-language understanding
UFVideo: Towards Unified Fine-Grained Video Cooperative Understanding with Large Language Models
Hewen Pan, Cong Wei, Dashuang Liang, Zepeng Huang, Pengfei Gao, Ziqi Zhou, Lulu Xue, Pengfei Yan, Xiaoming Wei, Minghui Li, Shengshan Hu
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 |
|---|---|---|---|
| use relative temporal tokens instead of absolute time numbers (ablation) | UFVideo · Charades-STA | tIoU: 30.24 -> 39.19 (100 tokens) | Improved |
| increase relative time tokens from 50 to 100 (ablation) | UFVideo · Charades-STA | R@0.3: 48.31 -> 60.27 | Improved |
| increase relative time tokens from 100 to 150 (ablation) | UFVideo · Charades-STA | R@0.3: 60.27 -> 63.82 | Improved |
| jointly train segmentation, temporal grounding and QA tasks (ablation) | UFVideo · MeViS valu | J&F: 52.26 -> 62.80 | Improved |
| jointly train all tasks (ablation) | UFVideo · UFVideo-Bench PixTRQA | SAvg.: 2.57 -> 4.13 | Improved |
| unified multi-task training from VideoRefer-7B | UFVideo · VideoRefer-Bench-Q (multi-frame) | Avg. accuracy: 72.1 -> 77.9 | Improved |
| UFVideo vs LLaVA-ST on temporal grounding | UFVideo · Charades-STA | tIoU: 42.4 -> 44.7 | Improved |
| UFVideo vs UniPixel on Ref-DAVIS17 | UFVideo · Ref-DAVIS17 val | J&F: 75.7 -> 74.6 | Hurt |
| UFVideo vs DAM on VideoRefer-Bench-D multi-frame | UFVideo · VideoRefer-Bench-D (multi-frame) | Avg. score: 3.68 -> 3.61 | Hurt |
Closest papers by meaning
- VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM (CVPR 2025 · similarity 0.89)
- Momentor: Advancing Video Large Language Model with Fine-Grained Temporal Reasoning (ICML 2024 · similarity 0.89)
- Leveraging Textual Memory and Key Frame Reasoning for Full Video Understanding Using Off-the-Shelf LLMs and VLMs (Student Abstract) (AAAI 2025 · similarity 0.89)
- SlowFocus: Enhancing Fine-grained Temporal Understanding in Video LLM (NeurIPS 2024 · similarity 0.89)
- Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding (CVPR 2024 · similarity 0.89)
- SF2T: Self-supervised Fragment Finetuning of Video-LLMs for Fine-Grained Understanding (CVPR 2025 · similarity 0.89)
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.
