AI Paper Atlas

Research map / Video / Video-language understanding

MECD+: Unlocking Event-Level Causal Graph Discovery for Video Reasoning

Tieyuan Chen, Huabin Liu, Yi Wang, Yihang Chen, Tianyao He, Chaofan Gan, Huanyu He, Weiyao Lin

TPAMI 2025 · Video › Video-language understanding · approach: Event and anomaly reasoning in video · 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 caption loss L_C (ablation)VGCM · MECD test setaccuracy: 64.8 -> 67.0Improved
add reconstruction loss L_V (ablation)VGCM · MECD test setaccuracy: 65.1 -> 67.0Improved
add similarity loss L_S (ablation)VGCM · MECD test setaccuracy: 65.3 -> 67.0Improved
add front-door adjustment (ablation)VGCM · MECD test setaccuracy: 67.0 -> 68.7Improved
add counterfactual intervention (ablation)VGCM · MECD test setaccuracy: 67.0 -> 69.3Improved
add context chain reasoning (ablation)VGCM · MECD test setaccuracy: 71.2 -> 71.3No clear effect
add context chain reasoning (ablation)VGCM · MECD test setSHD: 4.19 -> 3.94Improved
use Videobert encoder instead of CLIP-L (ablation)VGCM · MECD test setaccuracy: 69.99 -> 71.28Improved
add non-regressive complete graph reasoning (ablation)VGCM · MECD inference speedseconds/sample: 3.39 -> 0.76Improved
add front-door adjustment (ablation)VGCM · MECD temporal illusory causalityaccuracy drop at first relation: -3.3 -> -0.7Improved
add counterfactual intervention (ablation)VGCM · MECD existence illusory testsimilarity division: 1.04 -> 0.93Improved
use LLM reasoner instead of MLP head on the same encoderVideoLLaVA vs LanguageBind · MECD test setaccuracy: 59.83 -> 67.12Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 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