{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T12:29:48Z","timestamp":1786969788501,"version":"build-2736575974"},"reference-count":54,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62406053"],"award-info":[{"award-number":["62406053"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62441231"],"award-info":[{"award-number":["62441231"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.patcog.2026.114586","type":"journal-article","created":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T15:44:17Z","timestamp":1785858257000},"page":"114586","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PF","title":["Bridging CLIP and CLAP for open-vocabulary audio\u2013visual segmentation with semantic coherence"],"prefix":"10.1016","volume":"180","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4288-4516","authenticated-orcid":false,"given":"Yunzhi","family":"Zhuge","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengyuan","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2972-8883","authenticated-orcid":false,"given":"Yizhuang","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin","family":"Zhan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pingping","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6668-9758","authenticated-orcid":false,"given":"Huchuan","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.114586_b1","series-title":"European Conference on Computer Vision","first-page":"386","article-title":"Audio-visual segmentation","author":"Zhou","year":"2022"},{"key":"10.1016\/j.patcog.2026.114586_b2","first-page":"1","article-title":"Audio-visual segmentation with semantics","author":"Zhou","year":"2024","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.patcog.2026.114586_b3","series-title":"AAAI Conference on Artificial Intelligence","first-page":"12155","article-title":"Avsegformer: Audio-visual segmentation with transformer","volume":"vol. 38","author":"Gao","year":"2024"},{"key":"10.1016\/j.patcog.2026.114586_b4","series-title":"International Joint Conference on Artificial Intelligence","first-page":"875","article-title":"Discovering sounding objects by audio queries for audio visual segmentation","author":"Huang","year":"2023"},{"key":"10.1016\/j.patcog.2026.114586_b5","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","first-page":"27134","article-title":"Cooperation does matter: Exploring multi-order bilateral relations for audio-visual segmentation","author":"Yang","year":"2024"},{"key":"10.1016\/j.patcog.2026.114586_b6","article-title":"Mettle: Meta-token learning for memory-efficient audio-visual adaptation","author":"Zhou","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.114586_b7","series-title":"European Conference on Computer Vision","first-page":"311","article-title":"Stepping stones: A progressive training strategy for audio-visual semantic segmentation","author":"Ma","year":"2024"},{"key":"10.1016\/j.patcog.2026.114586_b8","series-title":"ACM International Conference on Multimedia","first-page":"7533","article-title":"Open-vocabulary audio-visual semantic segmentation","author":"Guo","year":"2024"},{"key":"10.1016\/j.patcog.2026.114586_b9","series-title":"OpenAVS: Training-free open-vocabulary audio visual segmentation with foundational models","author":"Chen","year":"2025"},{"key":"10.1016\/j.patcog.2026.114586_b10","series-title":"European Conference on Computer Vision","first-page":"247","article-title":"Audio-visual event localization in unconstrained videos","author":"Tian","year":"2018"},{"issue":"6","key":"10.1016\/j.patcog.2026.114586_b11","doi-asserted-by":"crossref","first-page":"7239","DOI":"10.1109\/TPAMI.2022.3223688","article-title":"Contrastive positive sample propagation along the audio-visual event line","volume":"45","author":"Zhou","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.114586_b12","doi-asserted-by":"crossref","unstructured":"J. Zhou, D. Guo, R. Guo, Y. Mao, J. Hu, Y. Zhong, X. Chang, M. Wang, Towards open-vocabulary audio-visual event localization, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2025, pp. 8362\u20138371.","DOI":"10.1109\/CVPR52734.2025.00783"},{"key":"10.1016\/j.patcog.2026.114586_b13","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2026.113312","article-title":"Effective audio-visual event localization using CLIP-based global context regulation for mitigating event overconfidence","author":"Lee","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114586_b14","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2021.107906","article-title":"Multimodal fusion for indoor sound source localization","volume":"115","author":"Chen","year":"2021","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114586_b15","series-title":"International Conference on Computer Vision","first-page":"7777","article-title":"Sound source localization is all about cross-modal alignment","author":"Senocak","year":"2023"},{"issue":"11","key":"10.1016\/j.patcog.2026.114586_b16","doi-asserted-by":"crossref","first-page":"5308","DOI":"10.1007\/s11263-024-02142-3","article-title":"Advancing weakly-supervised audio-visual video parsing via segment-wise pseudo labeling","volume":"132","author":"Zhou","year":"2024","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.patcog.2026.114586_b17","series-title":"ACM International Conference on Multimedia","first-page":"5997","article-title":"Boosting audio visual question answering via key semantic-aware cues","author":"Li","year":"2024"},{"key":"10.1016\/j.patcog.2026.114586_b18","series-title":"IEEE International Workshop on Machine Learning for Signal Processing","first-page":"01","article-title":"Rethinking audio-visual synchronization for active speaker detection","author":"Wuerkaixi","year":"2022"},{"key":"10.1016\/j.patcog.2026.114586_b19","series-title":"ACM International Conference on Multimedia","first-page":"1485","article-title":"Catr: Combinatorial-dependence audio-queried transformer for audio-visual video segmentation","author":"Li","year":"2023"},{"key":"10.1016\/j.patcog.2026.114586_b20","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","first-page":"8352","article-title":"Revisiting audio-visual segmentation with vision-centric transformer","author":"Huang","year":"2025"},{"key":"10.1016\/j.patcog.2026.114586_b21","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1290","article-title":"Masked-attention mask transformer for universal image segmentation","author":"Cheng","year":"2022"},{"key":"10.1016\/j.patcog.2026.114586_b22","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","first-page":"28922","article-title":"Robust audio-visual segmentation via audio-guided visual convergent alignment","author":"Liu","year":"2025"},{"key":"10.1016\/j.patcog.2026.114586_b23","doi-asserted-by":"crossref","first-page":"4108","DOI":"10.1109\/TIP.2025.3580269","article-title":"Contrastive conditional latent diffusion for audio-visual segmentation","volume":"34","author":"Mao","year":"2025","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.114586_b24","doi-asserted-by":"crossref","first-page":"5413","DOI":"10.1109\/TMM.2025.3542995","article-title":"Avs-Mamba: Exploring temporal and multi-modal Mamba for audio-visual segmentation","volume":"27","author":"Gong","year":"2025","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.114586_b25","doi-asserted-by":"crossref","first-page":"8954","DOI":"10.1109\/TPAMI.2024.3413013","article-title":"A survey on open-vocabulary detection and segmentation: Past, present, and future","volume":"46","author":"Zhu","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.114586_b26","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","first-page":"11583","article-title":"Decoupling zero-shot semantic segmentation","author":"Ding","year":"2022"},{"key":"10.1016\/j.patcog.2026.114586_b27","series-title":"International Conference on Computer Vision","first-page":"7061","article-title":"Open-vocabulary semantic segmentation with mask-adapted clip","author":"Liang","year":"2023"},{"key":"10.1016\/j.patcog.2026.114586_b28","series-title":"European Conference on Computer Vision","first-page":"736","article-title":"A simple baseline for open-vocabulary semantic segmentation with pre-trained vision-language model","author":"Xu","year":"2022"},{"key":"10.1016\/j.patcog.2026.114586_b29","series-title":"European Conference on Computer Vision","first-page":"540","article-title":"Scaling open-vocabulary image segmentation with image-level labels","author":"Ghiasi","year":"2022"},{"key":"10.1016\/j.patcog.2026.114586_b30","first-page":"32215","article-title":"Convolutions die hard: Open-vocabulary segmentation with single frozen convolutional clip","volume":"36","author":"Yu","year":"2023","journal-title":"Annu. Conf. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.114586_b31","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2945","article-title":"Side adapter network for open-vocabulary semantic segmentation","author":"Xu","year":"2023"},{"key":"10.1016\/j.patcog.2026.114586_b32","doi-asserted-by":"crossref","first-page":"520","DOI":"10.1109\/TCSVT.2024.3454227","article-title":"Generalization boosted adapter for open-vocabulary segmentation","volume":"35","author":"Xu","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.114586_b33","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2955","article-title":"Open-vocabulary panoptic segmentation with text-to-image diffusion models","author":"Xu","year":"2023"},{"key":"10.1016\/j.patcog.2026.114586_b34","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","first-page":"4113","article-title":"Cat-seg: Cost aggregation for open-vocabulary semantic segmentation","author":"Cho","year":"2024"},{"key":"10.1016\/j.patcog.2026.114586_b35","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","first-page":"3426","article-title":"Sed: A simple encoder-decoder for open-vocabulary semantic segmentation","author":"Xie","year":"2024"},{"key":"10.1016\/j.patcog.2026.114586_b36","series-title":"LMSeg: Unleashing the power of large-scale models for open-vocabulary semantic segmentation","author":"Tang","year":"2024"},{"key":"10.1016\/j.patcog.2026.114586_b37","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","first-page":"25346","article-title":"DPSeg: Dual-prompt cost volume learning for open-vocabulary semantic segmentation","author":"Zhao","year":"2025"},{"key":"10.1016\/j.patcog.2026.114586_b38","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.129982","article-title":"GCD-Net: Global consciousness-driven open-vocabulary semantic segmentation network","volume":"636","author":"Wu","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.patcog.2026.114586_b39","doi-asserted-by":"crossref","first-page":"8442","DOI":"10.1109\/TMM.2023.3330102","article-title":"Class enhancement losses with pseudo labels for open-vocabulary semantic segmentation","volume":"26","author":"Dao","year":"2023","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.114586_b40","doi-asserted-by":"crossref","first-page":"2924","DOI":"10.1109\/TMM.2025.3557719","article-title":"Towards open-vocabulary video semantic segmentation","volume":"27","author":"Li","year":"2025","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.114586_b41","doi-asserted-by":"crossref","first-page":"1895","DOI":"10.1109\/TIP.2025.3551648","article-title":"Diffusion model is secretly a training-free open vocabulary semantic segmenter","volume":"34","author":"Wang","year":"2025","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.114586_b42","doi-asserted-by":"crossref","first-page":"6780","DOI":"10.1109\/TPAMI.2025.3562930","article-title":"Rethinking evaluation metrics of open-vocabulary segmentation","volume":"47","author":"Zhou","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.114586_b43","series-title":"International Conference on Computer Vision","first-page":"4057","article-title":"Towards open-vocabulary video instance segmentation","author":"Wang","year":"2023"},{"key":"10.1016\/j.patcog.2026.114586_b44","doi-asserted-by":"crossref","first-page":"1098","DOI":"10.1109\/TCSVT.2024.3474698","article-title":"CLIP-VIS: Adapting CLIP for open-vocabulary video instance segmentation","volume":"35","author":"Zhu","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.114586_b45","doi-asserted-by":"crossref","first-page":"5048","DOI":"10.1007\/s11263-024-02076-w","article-title":"Ov-vis: Open-vocabulary video instance segmentation","volume":"132","author":"Wang","year":"2024","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.patcog.2026.114586_b46","series-title":"The British Machine Vision Conference","first-page":"367","article-title":"How can contrastive pre-training benefit audio-visual segmentation? A study from supervised and zero-shot perspectives","author":"Yu","year":"2023"},{"key":"10.1016\/j.patcog.2026.114586_b47","series-title":"Detectron2","author":"Wu","year":"2019"},{"key":"10.1016\/j.patcog.2026.114586_b48","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.patcog.2026.114586_b49","series-title":"IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"1","article-title":"Clap learning audio concepts from natural language supervision","author":"Elizalde","year":"2023"},{"key":"10.1016\/j.patcog.2026.114586_b50","doi-asserted-by":"crossref","first-page":"10015","DOI":"10.1109\/TMM.2024.3405622","article-title":"BAVS: Bootstrapping audio-visual segmentation by integrating foundation knowledge","volume":"26","author":"Liu","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.114586_b51","doi-asserted-by":"crossref","first-page":"2398","DOI":"10.1109\/TCSVT.2024.3486344","article-title":"Bootstrapping audio-visual segmentation by strengthening audio cues","volume":"35","author":"Chen","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.114586_b52","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.patcog.2026.114586_b53","series-title":"Leveraging foundation models for unsupervised audio-visual segmentation","author":"Bhosale","year":"2023"},{"key":"10.1016\/j.patcog.2026.114586_b54","series-title":"AAAI Conference on Artificial Intelligence","first-page":"3715","article-title":"Unleashing the temporal-spatial reasoning capacity of gpt for training-free audio and language referenced video object segmentation","volume":"vol. 39","author":"Huang","year":"2025"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326015505?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326015505?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T12:20:51Z","timestamp":1786969251000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326015505"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":54,"alternative-id":["S0031320326015505"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114586","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Bridging CLIP and CLAP for open-vocabulary audio\u2013visual segmentation with semantic coherence","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114586","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"114586"}}