{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:58:35Z","timestamp":1783529915518,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"CAAI-Huawei MindSpore Open Fund"},{"name":"National Nature Science Foundation of China","award":["61972378, U19B2040, 62125207, U1936203"],"award-info":[{"award-number":["61972378, U19B2040, 62125207, U1936203"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612661","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:40Z","timestamp":1698391660000},"page":"8157-8166","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["SeeDS: Semantic Separable Diffusion Synthesizer for Zero-shot Food Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6395-8708","authenticated-orcid":false,"given":"Pengfei","family":"Zhou","sequence":"first","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6668-9208","authenticated-orcid":false,"given":"Weiqing","family":"Min","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7454-1769","authenticated-orcid":false,"given":"Yang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5439-0176","authenticated-orcid":false,"given":"Jiajun","family":"Song","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5738-8572","authenticated-orcid":false,"given":"Ying","family":"Jin","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1596-4326","authenticated-orcid":false,"given":"Shuqiang","family":"Jiang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2831627"},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the International Conference on Machine Learning (ICML). 214--223","author":"Arjovsky Martin","year":"2017","unstructured":"Martin Arjovsky, Soumith Chintala, and L\u00e9on Bottou. 2017. Wasserstein generative adversarial networks. In Proceedings of the International Conference on Machine Learning (ICML). 214--223."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-020-01153-z"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_24"},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the British Machine Vision Conference (BMVC). 56--68","author":"Berkan Demirel","year":"2018","unstructured":"Demirel Berkan, Ramazan G\u00f6kberk Cinbics, and Nazli. Ikizler Cinbics. 2018. Zero-Shot Object Detection by Hybrid Region Embedding. In Proceedings of the British Machine Vision Conference (BMVC). 56--68."},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL).","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.23919\/MVA.2017.7986835"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413657"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00240"},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of the Asian Conference on Computer Vision (ACCV).","author":"Hayat Nasir","year":"2020","unstructured":"Nasir Hayat, Munawar Hayat, Shafin Rahman, Salman Khan, Syed Waqas Zamir, and Fahad Shahbaz Khan. 2020. Synthesizing the unseen for zero-shot object detection. In Proceedings of the Asian Conference on Computer Vision (ACCV)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_14_1","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), Vol. 33, 6840--6851.","journal-title":"Proceedings of the Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00747"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-16199-0_1"},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR). 1--15","author":"Kingma D.","unstructured":"D. Kingma and J. Ba. 2015. Adam: A Method for Stochastic Optimization. In Proceedings of the International Conference on Learning Representations (ICLR). 1--15."},{"key":"e_1_3_2_1_19_1","volume-title":"Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114","author":"Kingma Diederik P","year":"2013","unstructured":"Diederik P Kingma and Max Welling. 2013. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.483"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018690"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2993948"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2927476"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.146"},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of the International Conference on Language Resources and Evaluation (LREC). 52--55","author":"Mikolov Tom\u00e1\u0161","year":"2018","unstructured":"Tom\u00e1\u0161 Mikolov, \u00c9douard Grave, Piotr Bojanowski, Christian Puhrsch, and Armand Joulin. 2018. Advances in Pre-Training Distributed Word Representations. In Proceedings of the International Conference on Language Resources and Evaluation (LREC). 52--55."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2958761"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3329168"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3233884"},{"key":"e_1_3_2_1_30_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR).","author":"Norouzi Mohammad","year":"2014","unstructured":"Mohammad Norouzi, Tomas Mikolov, Samy Bengio, Yoram Singer, Jonathon Shlens, Andrea Frome, Greg S Corrado, and Jeffrey Dean. 2014. Zero-shot learning by convex combination of semantic embeddings. In Proceedings of the International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2020.2976006"},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of the International Conference on Machine Learning (ICML). 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 Proceedings of the International Conference on Machine Learning (ICML). 8748--8763."},{"key":"e_1_3_2_1_33_1","volume-title":"Polarity Loss: Improving Visual-Semantic Alignment for Zero-Shot Detection","author":"Rahman Shafin","year":"2022","unstructured":"Shafin Rahman, Salman Khan, and Nick Barnes. 2022. Polarity Loss: Improving Visual-Semantic Alignment for Zero-Shot Detection. IEEE Transactions on Neural Networks and Learning Systems (TNNLS) (2022), 1--13."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20887-5_34"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/IAICT50021.2020.9172024"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"e_1_3_2_1_37_1","volume-title":"Proceedings of the Advances in Neural Information Processing Systems (NeurIPS)","volume":"28","author":"Ren Shaoqing","year":"2015","unstructured":"Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2015. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. In Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), Vol. 28."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00844"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2018CEP0001"},{"key":"e_1_3_2_1_41_1","volume-title":"Proceedings of the Advances in Neural Information Processing Systems (NeurIPS)","volume":"26","author":"Socher Richard","year":"2013","unstructured":"Richard Socher, Milind Ganjoo, Christopher D Manning, and Andrew Ng. 2013. Zero-shot learning through cross-modal transfer. In Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), Vol. 26."},{"key":"e_1_3_2_1_42_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR).","author":"Song Jiaming","year":"2021","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2021. Denoising Diffusion Implicit Models. In Proceedings of the International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_43_1","volume-title":"Foodtracker: A real-time food detection mobile application by deep convolutional neural networks. arXiv preprint arXiv:1909.05994","author":"Sun Jianing","year":"2019","unstructured":"Jianing Sun, Katarzyna Radecka, and Zeljko Zilic. 2019. Foodtracker: A real-time food detection mobile application by deep convolutional neural networks. arXiv preprint arXiv:1909.05994 (2019)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cogr.2021.08.001"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812448"},{"key":"e_1_3_2_1_46_1","first-page":"2579","article-title":"Visualizing Data using t-SNE","volume":"9","author":"van der Maaten Laurens","year":"2008","unstructured":"Laurens van der Maaten and Geoffrey Hinton. 2008. Visualizing Data using t-SNE. Journal of Machine Learning Research (JMLR), Vol. 9, 86 (2008), 2579--2605.","journal-title":"Journal of Machine Learning Research (JMLR)"},{"key":"e_1_3_2_1_47_1","volume-title":"Steven CH Hoi, and Chunyan Miao","author":"Wang Hao","year":"2022","unstructured":"Hao Wang, Guosheng Lin, Steven CH Hoi, and Chunyan Miao. 2022a. Learning structural representations for recipe generation and food retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) (2022), 1--15."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tifs.2022.02.017"},{"key":"e_1_3_2_1_49_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR).","author":"Xiao Zhisheng","year":"2022","unstructured":"Zhisheng Xiao, Karsten Kreis, and Arash Vahdat. 2022. Tackling the Generative Learning Trilemma with Denoising Diffusion GANs. In Proceedings of the International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3140070"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6996"},{"key":"e_1_3_2_1_52_1","volume-title":"Proceedings of the Asian Conference on Computer Vision (ACCV).","author":"Zheng Ye","year":"2020","unstructured":"Ye Zheng, Ruoran Huang, Chuanqi Han, Xi Huang, and Li Cui. 2020. Background learnable cascade for zero-shot object detection. In Proceedings of the Asian Conference on Computer Vision (ACCV)."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01171"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612661","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612661","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:08:09Z","timestamp":1755821289000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612661"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":53,"alternative-id":["10.1145\/3581783.3612661","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612661","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}