Research map / Video / Video-language understanding
PiTe: Pixel-Temporal Alignment for Large Video-Language Model
Yang Liu, Pengxiang Ding, Siteng Huang, Min Zhang, Han Zhao, Donglin Wang
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 trajectory-guided alignment training (ablation) | PiTe 7B · ActivityNet Captions temporal grounding | mIoU: 17.4 -> 22.0 | Improved |
| add trajectory-guided alignment training (ablation) | PiTe 7B · MSVD-QA | accuracy: 68.1 -> 68.4 | No clear effect |
| initialize trajectory projector from the localization projector (ablation) | PiTe 7B · ActivityNet Captions temporal grounding | mIoU: 17.1 -> 22.0 | Improved |
| initialize trajectory projector from the localization projector (ablation) | PiTe 7B · ActivityNet Captions dense captioning | CIDEr: 21.7 -> 21.7 | No clear effect |
| trajectory training without initialization versus no trajectory training (ablation) | PiTe 7B · ActivityNet Captions temporal grounding | mIoU: 17.4 -> 17.1 | Hurt |
| scale LLM from 7B to 13B | PiTe · MSVD-QA | accuracy: 68.4 -> 71.6 | Improved |
| increase number of tracking points P from 1 to 5 (ablation) | PiTe · ActivityNet dense captioning and temporal grounding | task performance | Mixed |
| PiTe vs Video-ChatGPT with trajectory alignment | Video LLM · ActivityNet Captions dense captioning | CIDEr: 5.8 -> 21.7 | Improved |
Closest papers by meaning
- MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models (CVPR 2025 · similarity 0.89)
- VidLA: Video-Language Alignment at Scale (CVPR 2024 · similarity 0.89)
- Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis (CVPR 2025 · similarity 0.88)
- TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment (NeurIPS 2024 · similarity 0.88)
- Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension (NeurIPS 2025 · similarity 0.87)
- VideoGLaMM : A Large Multimodal Model for Pixel-Level Visual Grounding in Videos (CVPR 2025 · similarity 0.87)
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.
