Research map / Video / Video-language understanding
TemCoCo: Temporally Consistent Multi-modal Video Fusion with Visual-Semantic Collaboration
Meiqi Gong, Hao Zhang, Xunpeng Yi, Linfeng Tang, 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 temporal consistency loss (ablation) | TemCoCo · M3SVD | flowD: 5.7999 -> 3.2847 | Improved |
| add temporal attention (ablation) | TemCoCo · M3SVD | flowD: 4.4849 -> 3.2847 | Improved |
| add visual-semantic attention (ablation) | TemCoCo · M3SVD | flowD: 4.1371 -> 3.2847 | Improved |
| use 3D convolutions instead of 2D (ablation) | TemCoCo · M3SVD | flowD: 3.9472 -> 3.2847 | Improved |
| add DCN inter-frame alignment (ablation) | TemCoCo · M3SVD | flowD and MI: flowD 3.2879 -> 3.2847; MI 2.2125 -> 2.4219 | Mixed |
| add Dinov2 distillation guidance (ablation) | TemCoCo · M3SVD | MI: 2.2591 -> 2.4219 | Improved |
| add Dinov2 distillation guidance (ablation) | TemCoCo · Video segmentation | mIoU: 0.765 -> 0.870 | Improved |
| add Dinov2 distillation guidance (ablation) | TemCoCo · M3SVD | flowD: 3.2856 -> 3.2847 | No clear effect |
| use 3D convolutions instead of 2D (ablation) | TemCoCo · Efficiency | inference time (s): 0.086 -> 0.109 | Mixed |
Later papers that compared with this method
3 later accepted papers report TemCoCo as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- VideoFusion: A Spatio-Temporal Collaborative Network for Multi-modal Video Fusion (CVPR 2026 · better on 5 of 6 shared results)
- MemoryFusion: Cross-Temporal Memory Learning for Multimodal Video Fusion (NeurIPS 2026 · better on 4 of 4 shared results)
- DRFusion: Drift-Resilient Temporally Consistent Infrared–Visible Video Fusion (ICML 2026 · better on 1 of 2 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
- VideoFusion: A Spatio-Temporal Collaborative Network for Multi-modal Video Fusion (CVPR 2026 · similarity 0.91)
- Degradation-Robust and Temporally Consistent Infrared–Visible Video Fusion via One-step Diffusion Framework (ECCV 2026 · similarity 0.90)
- A Unified Solution to Video Fusion: From Multi-Frame Learning to Benchmarking (NeurIPS 2025 · similarity 0.89)
- MemoryFusion: Cross-Temporal Memory Learning for Multimodal Video Fusion (NeurIPS 2026 · similarity 0.89)
- V2VFusion: Text-Controlled Video-to-Video Diffusion for Degradation-Aware Video Fusion (NeurIPS 2026 · similarity 0.89)
- Every SAM Drop Counts: Embracing Semantic Priors for Multi-Modality Image Fusion and Beyond (CVPR 2025 · 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.
