{"ID":2867543,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.17446","arxiv_id":"2509.17446","title":"MVCL-DAF++: Enhancing Multimodal Intent Recognition via Prototype-Aware Contrastive Alignment and Coarse-to-Fine Dynamic Attention Fusion","abstract":"Multimodal intent recognition (MMIR) suffers from weak semantic grounding and poor robustness under noisy or rare-class conditions. We propose MVCL-DAF++, which extends MVCL-DAF with two key modules: (1) Prototype-aware contrastive alignment, aligning instances to class-level prototypes to enhance semantic consistency; and (2) Coarse-to-fine attention fusion, integrating global modality summaries with token-level features for hierarchical cross-modal interaction. On MIntRec and MIntRec2.0, MVCL-DAF++ achieves new state-of-the-art results, improving rare-class recognition by +1.05\\% and +4.18\\% WF1, respectively. These results demonstrate the effectiveness of prototype-guided learning and coarse-to-fine fusion for robust multimodal understanding. The source code is available at https://github.com/chr1s623/MVCL-DAF-PlusPlus.","short_abstract":"Multimodal intent recognition (MMIR) suffers from weak semantic grounding and poor robustness under noisy or rare-class conditions. We propose MVCL-DAF++, which extends MVCL-DAF with two key modules: (1) Prototype-aware contrastive alignment, aligning instances to class-level prototypes to enhance semantic consistency;...","url_abs":"https://arxiv.org/abs/2509.17446","url_pdf":"https://arxiv.org/pdf/2509.17446v2","authors":"[\"Haofeng Huang\",\"Yifei Han\",\"Long Zhang\",\"Bin Li\",\"Yangfan He\"]","published":"2025-09-22T07:38:53Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[]","has_code":false,"code_links":[{"ID":609477,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2867543,"paper_url":"https://arxiv.org/abs/2509.17446","paper_title":"MVCL-DAF++: Enhancing Multimodal Intent Recognition via Prototype-Aware Contrastive Alignment and Coarse-to-Fine Dynamic Attention Fusion","repo_url":"https://github.com/chr1s623/MVCL-DAF-PlusPlus","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}