{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:05:09Z","timestamp":1750309509162,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":34,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"the Young Scientists Fund of the National Natural Science Foundation of China","award":["No.62201401"],"award-info":[{"award-number":["No.62201401"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680613","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"4524-4532","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Advancing Semantic Edge Detection through Cross-Modal Knowledge Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5912-0152","authenticated-orcid":false,"given":"Ruoxi","family":"Deng","sequence":"first","affiliation":[{"name":"Wenzhou Institute of Data Research School of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6993-318X","authenticated-orcid":false,"given":"Bin","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2058-3004","authenticated-orcid":false,"given":"Jinxuan","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8922-3966","authenticated-orcid":false,"given":"Caixia","family":"Zhou","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Traffic Data Analysis and Mining, Beijing Jiaotong University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9492-0796","authenticated-orcid":false,"given":"Zhao-Min","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3296-5459","authenticated-orcid":false,"given":"Jie","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou, China"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01133"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"crossref","unstructured":"David Acuna Amlan Kar and Sanja Fidler. 2019. Devil is in the Edges: Learning Semantic Boundaries from Noisy Annotations. In CVPR.","DOI":"10.1109\/CVPR.2019.01133"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1986.4767851"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126742"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413750"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475593"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_35"},{"key":"e_1_3_2_2_9_1","unstructured":"M. Everingham L. Van Gool C. K. I. Williams J. Winn and A. Zisserman. [n. d.]. The PASCAL Visual Object Classes Challenge 2011 (VOC2011) Results. http:\/\/www.pascalnetwork. org\/challenges\/VOC\/voc2011\/workshop\/index.html."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/T-C.1975.224274"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"e_1_3_2_2_12_1","volume-title":"Dynamic Feature Fusion for Semantic Edge Detection. arXiv preprint arXiv:1902.09104","author":"Hu Yuan","year":"2019","unstructured":"Yuan Hu, Yunpeng Chen, Xiang Li, and Jiashi Feng. 2019. Dynamic Feature Fusion for Semantic Edge Detection. arXiv preprint arXiv:1902.09104 (2019)."},{"key":"e_1_3_2_2_13_1","volume-title":"Diego de las Casas, Emma Bou Hanna, Florian Bressand, et al.","author":"Jiang Albert Q","year":"2024","unstructured":"Albert Q Jiang, Alexandre Sablayrolles, Antoine Roux, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, et al. 2024. Mixtral of experts. arXiv preprint arXiv:2401.04088 (2024)."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/0262-8856(83)90006-9"},{"key":"e_1_3_2_2_16_1","volume-title":"Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems 25","author":"Krizhevsky Alex","year":"2012","unstructured":"Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems 25 (2012)."},{"key":"e_1_3_2_2_17_1","volume-title":"Language-driven Semantic Segmentation. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=RriDjddCLN","author":"Li Boyi","year":"2022","unstructured":"Boyi Li, Kilian Q Weinberger, Serge Belongie, Vladlen Koltun, and Rene Ranftl. 2022. Language-driven Semantic Segmentation. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=RriDjddCLN"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_2_19_1","unstructured":"Haotian Liu Chunyuan Li Qingyang Wu and Yong Jae Lee. 2023. Visual Instruction Tuning."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01934"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01539-8"},{"key":"e_1_3_2_2_22_1","volume-title":"International Conference on Machine Learning. PMLR, 23033--23044","author":"Luo Huaishao","year":"2023","unstructured":"Huaishao Luo, Junwei Bao, Youzheng Wu, Xiaodong He, and Tianrui Li. 2023. Segclip: Patch aggregation with learnable centers for open-vocabulary semantic segmentation. In International Conference on Machine Learning. PMLR, 23033--23044."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.56205"},{"key":"e_1_3_2_2_24_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_2_25_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_2_26_1","volume-title":"Pixel Difference Networks for Efficient Edge Detection. arXiv preprint arXiv:2108.07009","author":"Su Zhuo","year":"2021","unstructured":"Zhuo Su, Wenzhe Liu, Zitong Yu, Dewen Hu, Qing Liao, Qi Tian, Matti Pietik\u00e4inen, and Li Liu. 2021. Pixel Difference Networks for Efficient Edge Detection. arXiv preprint arXiv:2108.07009 (2021)."},{"key":"e_1_3_2_2_27_1","volume-title":"International Conference on Machine Learning. PMLR, 6105--6114","author":"Tan Mingxing","year":"2019","unstructured":"Mingxing Tan and Quoc Le. 2019. Efficientnet: Rethinking model scaling for convolutional neural networks. In International Conference on Machine Learning. PMLR, 6105--6114."},{"key":"e_1_3_2_2_28_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_2_29_1","article-title":"Visualizing data using t-SNE","volume":"9","author":"der Maaten Laurens Van","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research 9, 11 (2008).","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.164"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.191"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_24"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01488"},{"key":"e_1_3_2_2_34_1","volume-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592","author":"Zhu Deyao","year":"2023","unstructured":"Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li, and Mohamed Elhoseiny. 2023. Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)."}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Melbourne VIC Australia","acronym":"MM '24"},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680613","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680613","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:56Z","timestamp":1750295876000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680613"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":34,"alternative-id":["10.1145\/3664647.3680613","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680613","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}