Research map / Video / Video-language understanding
VideoFusion: A Spatio-Temporal Collaborative Network for Multi-modal Video Fusion
Linfeng Tang, Yeda Wang, Meiqi Gong, Zizhuo Li, Yuxin Deng, Xunpeng Yi, Chunyu Li, Han Xu, Hao Zhang, Jiayi 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 bi-temporal co-attention (BiCAM) (ablation) | VideoFusion · M3SVD degraded | flowD: 4.747 -> 3.294 | Improved |
| add variational consistency loss (ablation) | VideoFusion · M3SVD degraded | flowD: 6.056 -> 3.294 | Improved |
| add cross-modal differential reinforcement module (CmDRM) (ablation) | VideoFusion · M3SVD degraded | MI: 3.557 -> 4.008 | Improved |
| use complete modality-guided fusion instead of simple summation (ablation) | VideoFusion · M3SVD degraded | SSIM: 0.366 -> 0.632 | Improved |
| use complete modality-guided fusion instead of simple summation (ablation) | VideoFusion · M3SVD degraded | SD: 61.403 -> 52.465 | Hurt |
| add color loss (ablation) | VideoFusion · M3SVD degraded | SSIM: 0.457 -> 0.632 | Improved |
| add intensity loss (ablation) | VideoFusion · M3SVD degraded | MI: 2.985 -> 4.008 | Improved |
| add gradient loss (ablation) | VideoFusion · M3SVD degraded | MI: 3.702 -> 4.008 | Improved |
| use video fusion VideoFusion instead of frame-by-frame RCVS | infrared-visible video fusion · M3SVD degraded | flowD: 6.443 -> 3.294 | 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.
- TemCoCo — TemCoCo: Temporally Consistent Multi-modal Video Fusion with Visual-Semantic Collaboration (ICCV 2025) · better on 5 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
- A Unified Solution to Video Fusion: From Multi-Frame Learning to Benchmarking (NeurIPS 2025 · similarity 0.90)
- Bridge Frame and Event: Common Spatiotemporal Fusion for High-Dynamic Scene Optical Flow (CVPR 2025 · similarity 0.88)
- Local-Global Multi-Modal Distillation for Weakly-Supervised Temporal Video Grounding (AAAI 2024 · similarity 0.87)
- MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models (CVPR 2025 · similarity 0.87)
- Motion Deblurring via Spatial-Temporal Collaboration of Frames and Events (AAAI 2024 · similarity 0.86)
- MVBench: A Comprehensive Multi-modal Video Understanding Benchmark (CVPR 2024 · similarity 0.85)
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.
