AI Paper Atlas

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

ICCV 2025 · Video › Video-language understanding · approach: Dense video captioning · 5 citations (OpenAlex)

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 changedWhereMeasuredEffect
add temporal consistency loss (ablation)TemCoCo · M3SVDflowD: 5.7999 -> 3.2847Improved
add temporal attention (ablation)TemCoCo · M3SVDflowD: 4.4849 -> 3.2847Improved
add visual-semantic attention (ablation)TemCoCo · M3SVDflowD: 4.1371 -> 3.2847Improved
use 3D convolutions instead of 2D (ablation)TemCoCo · M3SVDflowD: 3.9472 -> 3.2847Improved
add DCN inter-frame alignment (ablation)TemCoCo · M3SVDflowD and MI: flowD 3.2879 -> 3.2847; MI 2.2125 -> 2.4219Mixed
add Dinov2 distillation guidance (ablation)TemCoCo · M3SVDMI: 2.2591 -> 2.4219Improved
add Dinov2 distillation guidance (ablation)TemCoCo · Video segmentationmIoU: 0.765 -> 0.870Improved
add Dinov2 distillation guidance (ablation)TemCoCo · M3SVDflowD: 3.2856 -> 3.2847No clear effect
use 3D convolutions instead of 2D (ablation)TemCoCo · Efficiencyinference time (s): 0.086 -> 0.109Mixed

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy