AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Two-Stage Multi-Modal Fusion with Adaptive Alignment for Action Quality Assessment

Kanglei Zhou, Ruizhi Cai, Xinning Wang, Yijian Zheng, Liyuan Wang, Jianguo Li, Xiaohui Liang

IJCV 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 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
use DualAlign two-stage multi-modal alignment instead of best unimodal baselineDualAlign · MM-JDMSRCC x100: 64.28 -> 85.44Improved
use DualAlign instead of strongest multi-modal baselineDualAlign · MM-JDMSRCC x100: 60.30 -> 85.44Improved
use DualAlign instead of DAEDualAlign · MM-JDMrMSE: 3.036 -> 2.363Improved
use DualAlign instead of best unimodal baselineDualAlign · MM-JDMaccuracy (%): 81.64 -> 87.41Improved
use DualAlign instead of MLAVL on RGDualAlign · RGSRCC: 0.849 -> 0.878Improved
use DualAlign instead of MLAVL on Fis-VDualAlign · Fis-VSRCC: 0.823 -> 0.872Improved
use DualAlign instead of MLAVL on Fis-VDualAlign · Fis-VMSE: 13.31 -> 11.66Improved
use DualAlign instead of unimodal CoRe on Action 10DualAlign · MM-JDM Action 10SRCC x100: 82.26 -> 70.56Hurt
remove the RGB video stream (ablation)DualAlign · MM-JDMSRCC: dropping by 45%Improved
remove the RGB video stream (ablation)DualAlign · MM-JDMrMSE: increasing by 187%Improved
remove the RGB video stream (ablation)DualAlign · MM-JDMaccuracy: decreasing by 23%Improved
use zero-shot GPT-4o or Gemini-3 Pro instead of trained DualAlignmLLMs · MM-JDMaccuracy (%): 20.29% and 36.87% vs 87.41%Hurt

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