AI Paper Atlas

Research map / Video / Video-language understanding

DisCo: Towards Distinct and Coherent Visual Encapsulation in Video MLLMs

Jiahe Zhao, Rongkun Zheng, Yi Wang, Helin Wang, Hengshuang Zhao

ICCV 2025 · Video › Video-language understanding · approach: Video LLMs with fine-grained understanding · 0 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 DisCo encapsulationInternVideo2-HD · MVBenchaccuracy: 66.3 -> 68.2Improved
add DisCo encapsulationInternVideo2 · STARaccuracy: 64.5 -> 72.7Improved
add DisCo encapsulationST-LLM · MVBenchaccuracy: 54.7 -> 58.0Improved
add DisCo encapsulationInternVideo2-HD · VideoChatGPT-Benchavg score: 2.96 -> 3.24Improved
add DisCo encapsulationST-LLM · VideoMME medium (w/o sub)accuracy: 40.2 -> 39.6Hurt
fine-tune on same data without modules (SFT) (ablation)InternVideo2-HD · MVBenchaccuracy: 66.3 -> 66.5No clear effect
add VCD module (ablation)InternVideo2-HD · EgoSchema subsetaccuracy: 67.0 -> 71.8Improved
add TFC module (ablation)InternVideo2-HD · EgoSchema subsetaccuracy: 67.0 -> 70.4Improved
add TFC on top of VCD (full DisCo) (ablation)InternVideo2-HD · EgoSchema subsetaccuracy: 71.8 -> 72.2Improved
add global tokens to VCD (ablation)DisCo · MVBenchaccuracy: 65.8 -> 68.2Improved
use 16 groups instead of 4 (ablation)DisCo VCD · MVBenchaccuracy: 66.5 -> 68.2Improved
use 16 groups instead of 64 (ablation)DisCo VCD · MVBenchaccuracy: 67.3 -> 68.2Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most 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

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