Researchers have introduced DualAlign, a novel two-stage framework designed to improve Action Quality Assessment (AQA) by effectively fusing multi-modal data. This approach addresses challenges like cross-modal misalignment and the high cost of annotation by first stabilizing visual representations from RGB, optical flow, and skeleton data before incorporating textual semantics. To support this research, a new dataset called MM--JDM was created, which includes diverse multi-modal inputs and realistic noise, class imbalance, and label scarcity. Experiments demonstrate that DualAlign significantly outperforms existing methods on MM--JDM and other benchmarks, while also showing robustness in scenarios with missing modalities or limited labels. AI
IMPACT Introduces a novel framework and dataset for multi-modal fusion in action quality assessment, potentially improving sports analysis and skill evaluation.
RANK_REASON The cluster contains a research paper detailing a new framework and dataset for action quality assessment.
- Action Quality Assessment
- alphaXiv
- arXiv
- CatalyzeX
- DagsHub
- Gotit.pub
- Hugging Face
- MM--JDM
- ScienceCast
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
