{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:19:47Z","timestamp":1765340387174,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFF0725103"],"award-info":[{"award-number":["2023YFF0725103"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100017052","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62192784, U23A20319, 62422202, U24A20329, 62272058"],"award-info":[{"award-number":["62192784, U23A20319, 62422202, U24A20329, 62272058"]}],"id":[{"id":"10.13039\/100017052","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Natural Science Foundation","award":["4242027"],"award-info":[{"award-number":["4242027"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755850","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:38:54Z","timestamp":1761377934000},"page":"6353-6362","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Asymmetric Pre-aligned Anchor Contrastive Enhanced Diffusion Hashing Model for Incomplete Multimodal Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-4686-1170","authenticated-orcid":false,"given":"Yang","family":"Yu","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1835-1848","authenticated-orcid":false,"given":"Meiyu","family":"Liang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1661-9501","authenticated-orcid":false,"given":"Wei","family":"Huang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2280-3351","authenticated-orcid":false,"given":"Juncheng","family":"zheng","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0983-758X","authenticated-orcid":false,"given":"Kangkang","family":"Lu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2662-3444","authenticated-orcid":false,"given":"Yawen","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9402-3806","authenticated-orcid":false,"given":"Junping","family":"Du","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6123-0043","authenticated-orcid":false,"given":"Zhe","family":"Xue","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1633-7575","authenticated-orcid":false,"given":"Wu","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372278.3390711"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2018.2798607"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01816"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646452"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19-1423"},{"key":"e_1_3_2_1_6_1","first-page":"3877","article-title":"Unsupervised contrastive cross-modal hashing","volume":"45","author":"Hu Peng","year":"2022","unstructured":"Peng Hu, Hongyuan Zhu, Jie Lin, Dezhong Peng, Yin-Ping Zhao, and Xi Peng. 2022. Unsupervised contrastive cross-modal hashing. IEEE Transactions on Pattern Analysis and Machine Intelligence 45, 3 (2022), 3877-3889.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1460096.1460104"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.348"},{"key":"e_1_3_2_1_9_1","volume-title":"Diffusionret: Generative text-video retrieval with diffusion model. arXiv preprint arXiv:2303.09867","author":"Jin Peng","year":"2023","unstructured":"Peng Jin, Hao Li, Zesen Cheng, Kehan Li, Xiangyang Ji, Chang Liu, Li Yuan, and Jie Chen. 2023. Diffusionret: Generative text-video retrieval with diffusion model. arXiv preprint arXiv:2303.09867 (2023)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02243"},{"key":"e_1_3_2_1_11_1","unstructured":"Junnan Li Dongxu Li Silvio Savarese and Steven Hoi. 2023. BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models. arXiv:2301.12597 [cs.CV] https:\/\/arxiv.org\/abs\/2301.12597"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548431"},{"key":"e_1_3_2_1_13_1","volume-title":"Momentdiff: Generative video moment retrieval from random to real. arXiv preprint arXiv:2307.02869","author":"Li Pandeng","year":"2023","unstructured":"Pandeng Li, Chen-Wei Xie, Hongtao Xie, Liming Zhao, Lei Zhang, Yun Zheng, Deli Zhao, and Yongdong Zhang. 2023. Momentdiff: Generative video moment retrieval from random to real. arXiv preprint arXiv:2307.02869 (2023)."},{"key":"e_1_3_2_1_14_1","volume-title":"DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training. arXiv preprint arXiv:2303.03032","author":"Li Wei","year":"2023","unstructured":"Wei Li, Linchao Zhu, Longyin Wen, and Yi Yang. 2023. DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training. arXiv preprint arXiv:2303.03032 (2023)."},{"key":"e_1_3_2_1_15_1","first-page":"17612","article-title":"Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning","volume":"35","author":"Liang Victor Weixin","year":"2022","unstructured":"Victor Weixin Liang, Yuhui Zhang, Yongchan Kwon, Serena Yeung, and James Y Zou. 2022. Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning. Advances in Neural Information Processing Systems 35 (2022), 17612-17625.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_16_1","first-page":"740","volume-title":"Zurich","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In Computer Vision-ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13. Springer, 740-755."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612411"},{"key":"e_1_3_2_1_18_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350999"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475598"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2969792"},{"key":"e_1_3_2_1_22_1","volume-title":"Umap: Uniform manifold approximation and projection for dimension reduction. arXiv preprint arXiv:1802.03426","author":"McInnes Leland","year":"2018","unstructured":"Leland McInnes, John Healy, and James Melville. 2018. Umap: Uniform manifold approximation and projection for dimension reduction. arXiv preprint arXiv:1802.03426 (2018)."},{"key":"e_1_3_2_1_23_1","volume-title":"Text-only training for image captioning using noise-injected clip. arXiv preprint arXiv:2211.00575","author":"Nukrai David","year":"2022","unstructured":"David Nukrai, Ron Mokady, and Amir Globerson. 2022. Text-only training for image captioning using noise-injected clip. arXiv preprint arXiv:2211.00575 (2022)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3221787"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01847"},{"key":"e_1_3_2_1_26_1","unstructured":"William Peebles and Saining Xie. 2023. Scalable Diffusion Models with Transformers. arXiv:2212.09748 [cs.CV] https:\/\/arxiv.org\/abs\/2212.09748"},{"key":"e_1_3_2_1_27_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_1_28_1","volume-title":"Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125 1, 2","author":"Ramesh Aditya","year":"2022","unstructured":"Aditya Ramesh, Prafulla Dhariwal, Alex Nichol, Casey Chu, and Mark Chen. 2022. Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125 1, 2 (2022), 3."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_30_1","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily L Denton, Kamyar Ghasemipour, Raphael Gontijo Lopes, Burcu Karagol Ayan, Tim Salimans, et al. 2022. Photorealistic text-to-image diffusion models with deep language understanding. Advances in Neural Information Processing Systems 35 (2022), 36479-36494.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_31_1","first-page":"1","article-title":"Exploiting Subspace Relation in Semantic Labels for Cross-modal Hashing","volume":"99","author":"Shen Heng Tao","year":"2020","unstructured":"Heng Tao Shen, Luchen Liu, Yang Yang, Xing Xu, and Richang Hong. 2020. Exploiting Subspace Relation in Semantic Labels for Cross-modal Hashing. IEEE Transactions on Knowledge and Data Engineering PP, 99 (2020), 1-1.","journal-title":"IEEE Transactions on Knowledge and Data Engineering PP"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612282"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612282"},{"key":"e_1_3_2_1_34_1","volume-title":"International conference on machine learning. PMLR, 2256-2265","author":"Sohl-Dickstein Jascha","year":"2015","unstructured":"Jascha Sohl-Dickstein, Eric Weiss, Niru Maheswaranathan, and Surya Ganguli. 2015. Deep unsupervised learning using nonequilibrium thermodynamics. In International conference on machine learning. PMLR, 2256-2265."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Jingkuan Song Yang Yang Yi Yang Zi Huang and Heng Tao Shen. 2013. Intermedia hashing for large-scale retrieval from heterogeneous data sources. ACM. 785 pages.","DOI":"10.1145\/2463676.2465274"},{"key":"e_1_3_2_1_36_1","volume-title":"The AAAI-23 Workshop on Creative AI Across Modalities.","author":"Tam Derek","year":"2023","unstructured":"Derek Tam, Colin Raffel, and Mohit Bansal. 2023. Simple Weakly-Supervised Image Captioning via CLIP's Multimodal Embeddings. In The AAAI-23 Workshop on Creative AI Across Modalities."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548187"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107479"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Shitao Xiao Zheng Liu Yingxia Shao and Zhao Cao. 2022. RetroMAE: Pre-Training Retrieval-oriented Language Models Via Masked Auto-Encoder. arXiv:2205.12035 [cs.CL] https:\/\/arxiv.org\/abs\/2205.12035","DOI":"10.18653\/v1\/2022.emnlp-main.35"},{"key":"e_1_3_2_1_40_1","article-title":"Deep Multi-View Enhancement Hashing for Image Retrieval","author":"Yan Chenggang","year":"2020","unstructured":"Chenggang Yan, Biao Gong, Yuxuan Wei, and Yue Gao. 2020. Deep Multi-View Enhancement Hashing for Image Retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligence,IEEE Transactions on Pattern Analysis and Machine Intelligence (Feb 2020).","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence,IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463625"},{"key":"e_1_3_2_1_42_1","volume-title":"Diagnosing and rectifying vision models using language. arXiv preprint arXiv:2302.04269","author":"Zhang Yuhui","year":"2023","unstructured":"Yuhui Zhang, Jeff Z HaoChen, Shih-Cheng Huang, Kuan-Chieh Wang, James Zou, and Serena Yeung. 2023. Diagnosing and rectifying vision models using language. arXiv preprint arXiv:2302.04269 (2023)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2020.3037456"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612116"},{"key":"e_1_3_2_1_45_1","volume-title":"LAFITE: Towards Language-Free Training for Text-to-Image Generation. arXiv e-prints","author":"Zhou Yufan","year":"2021","unstructured":"Yufan Zhou, Ruiyi Zhang, Changyou Chen, Chunyuan Li, Chris Tensmeyer, Tong Yu, Jiuxiang Gu, Jinhui Xu, and Tong Sun. 2021. LAFITE: Towards Language-Free Training for Text-to-Image Generation. arXiv e-prints (2021)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3512527.3531417"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755850","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:15:47Z","timestamp":1765340147000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755850"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":46,"alternative-id":["10.1145\/3746027.3755850","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755850","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}