{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:26:12Z","timestamp":1774419972109,"version":"3.50.1"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889139","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["DiffGAP: A Lightweight Diffusion Module in Contrastive Space for Bridging Cross-Model Gap"],"prefix":"10.1109","author":[{"given":"Shentong","family":"Mo","sequence":"first","affiliation":[{"name":"Tsinghua University,Department of CST,Beijing,China,100084"}]},{"given":"Zehua","family":"Chen","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of CST,Beijing,China,100084"}]},{"given":"Fan","family":"Bao","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of CST,Beijing,China,100084"}]},{"given":"Jun","family":"Zhu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of CST,Beijing,China,100084"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.336"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2023.3268730"},{"key":"ref4","article-title":"Multi-modal grouping network for weakly-supervised audio-visual video parsing","volume-title":"Proceedings of Advances in Neural Information Processing Systems (NeurIPS)","author":"Mo"},{"key":"ref5","article-title":"Semantic-aware multi-modal grouping for weakly-supervised audio-visual video parsing","volume-title":"European Conference on Computer Vision (ECCV) Workshop","author":"Mo"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01018"},{"key":"ref7","article-title":"Weakly-supervised audio-visual segmentation","author":"Mo","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02567"},{"key":"ref9","article-title":"AV-SAM: Segment anything model meets audio-visual localization and segmentation","author":"Mo","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00717"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00716"},{"key":"ref12","article-title":"Audiogen: Textually guided audio generation","volume-title":"International Conference on Learning Representations (ICLR)","author":"Kreuk"},{"key":"ref13","article-title":"Audioldm: Textto-audio generation with latent diffusion models","author":"Liu","year":"2023"},{"key":"ref14","article-title":"Semantic grouping network for audio source separation","author":"Mo","year":"2024"},{"key":"ref15","article-title":"Diff-foley: Synchronized video-to-audio synthesis with latent diffusion models","author":"Luo","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_13"},{"key":"ref18","article-title":"A closer look at weakly-supervised audio-visual source localization","volume-title":"Proceedings of Advances in Neural Information Processing Systems (NeurIPS)","author":"Mo"},{"key":"ref19","article-title":"Benchmarking weakly-supervised audio-visual sound localization","volume-title":"European Conference on Computer Vision (ECCV) Workshop","author":"Mo"},{"key":"ref20","article-title":"A unified audio-visual learning framework for localization, separation, and recognition","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Mo"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73209-6_22"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00798"},{"key":"ref23","article-title":"Beyond accuracy: Statistical measures and benchmark for evaluation of representation from self-supervised learning","author":"Wu","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00158"},{"key":"ref25","article-title":"Rethinking positive pairs in contrastive learning","author":"Wu","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref27","first-page":"119","article-title":"AudioCaps: Generating captions for audios in the wild","volume-title":"Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics","author":"Kim"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwae276"},{"key":"ref29","article-title":"Denoising diffusion probabilistic models","volume-title":"Proceedings of Advances In Neural Information Processing Systems (NeurIPS)","author":"Ho"},{"key":"ref30","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"International Conference on Learning Representations (ICLR)","author":"Song"},{"key":"ref31","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i18.34144"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3204461"},{"key":"ref34","article-title":"DiT-3D: Exploring plain diffusion transformers for 3d shape generation","volume-title":"Proceedings of Advances In Neural Information Processing Systems (NeurIPS)","author":"Mo"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72907-2_21"},{"key":"ref36","article-title":"Efficient 3d shape generation via diffusion mamba with bidirectional ssms","author":"Mo","year":"2024"},{"key":"ref37","article-title":"Diffwave: A versatile diffusion model for audio synthesis","volume-title":"International Conference on Learning Representations (ICLR)","author":"Kong"},{"key":"ref38","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022"},{"key":"ref39","article-title":"DiffAVA: Personalized text-to-audio generation with visual alignment","author":"Mo","year":"2023"},{"key":"ref40","article-title":"Text-to-audio generation synchronized with videos","author":"Mo","year":"2024"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72940-9_1"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00958"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02168-7"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29475"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889139.pdf?arnumber=10889139","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:42Z","timestamp":1774416342000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889139\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889139","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}