{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:57:16Z","timestamp":1777568236288,"version":"3.51.4"},"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:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Tianjin Natural Science Foundation","award":["22JCQNJC00940"],"award-info":[{"award-number":["22JCQNJC00940"]}]},{"name":"Program for Young Talents of Science and Technology in Universities of Inner Mongolia Autonomous Region","award":["NJYT23105"],"award-info":[{"award-number":["NJYT23105"]}]},{"name":"Beijing Natural Science Foundation","award":["L221004"],"award-info":[{"award-number":["L221004"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206137, 62201297, 62206200, 62106262, 62276257 and 62036012"],"award-info":[{"award-number":["62206137, 62201297, 62206200, 62106262, 62276257 and 62036012"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Inner Mongolia Natural Science Foundation","award":["2022MS06025"],"award-info":[{"award-number":["2022MS06025"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611919","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:40Z","timestamp":1698391660000},"page":"8963-8974","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["C2MR: Continual Cross-Modal Retrieval for Streaming Multi-modal Data"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3183-9218","authenticated-orcid":false,"given":"Huaiwen","family":"Zhang","sequence":"first","affiliation":[{"name":"Inner Mongolia University, Hohhot, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2690-7180","authenticated-orcid":false,"given":"Yang","family":"Yang","sequence":"additional","affiliation":[{"name":"Inner Mongolia University, Hohhot, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1461-7100","authenticated-orcid":false,"given":"Fan","family":"Qi","sequence":"additional","affiliation":[{"name":"Tianjin University of Technology, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9488-2208","authenticated-orcid":false,"given":"Shengsheng","family":"Qian","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8343-9665","authenticated-orcid":false,"given":"Changsheng","family":"Xu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering. In 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018","author":"Anderson Peter","year":"2018","unstructured":"Peter Anderson, Xiaodong He, Chris Buehler, Damien Teney, Mark Johnson, Stephen Gould, and Lei Zhang. 2018. Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering. In 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, June 18-22, 2018. Computer Vision Foundation \/ IEEE Computer Society, 6077--6086."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00812"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00233"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3206549"},{"key":"e_1_3_2_1_5_1","volume-title":"Subset Replay Based Continual Learning for Scalable Improvement of Autonomous Systems. In 2018 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2018","author":"Brahma Pratik Prabhanjan","year":"2018","unstructured":"Pratik Prabhanjan Brahma and Adrienne Othon. 2018. Subset Replay Based Continual Learning for Scalable Improvement of Autonomous Systems. In 2018 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2018, Salt Lake City, UT, USA, June 18-22, 2018. Computer Vision Foundation \/ IEEE Computer Society, 1066--1074."},{"key":"e_1_3_2_1_6_1","volume-title":"Munich, Germany","volume":"572","author":"Chaudhry Arslan","year":"2018","unstructured":"Arslan Chaudhry, Puneet Kumar Dokania, Thalaiyasingam Ajanthan, and Philip H. S. Torr. 2018. Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence. In Computer Vision - ECCV 2018 - 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part XI (Lecture Notes in Computer Science, Vol. 11215). Springer, 556--572."},{"key":"e_1_3_2_1_7_1","volume-title":"Cross-Modal Retrieval with Heterogeneous Graph Embedding. In MM '22: The 30th ACM International Conference on Multimedia","author":"Chen Dapeng","year":"2022","unstructured":"Dapeng Chen, Min Wang, Haobin Chen, Lin Wu, Jing Qin, and Wei Peng. 2022. Cross-Modal Retrieval with Heterogeneous Graph Embedding. In MM '22: The 30th ACM International Conference on Multimedia, Lisboa, Portugal, October 10 - 14, 2022. ACM, 3291--3300."},{"key":"e_1_3_2_1_8_1","volume-title":"IMRAM: Iterative Matching With Recurrent Attention Memory for Cross-Modal Image-Text Retrieval. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020","author":"Chen Hui","year":"2020","unstructured":"Hui Chen, Guiguang Ding, Xudong Liu, Zijia Lin, Ji Liu, and Jungong Han. 2020a. IMRAM: Iterative Matching With Recurrent Attention Memory for Cross-Modal Image-Text Retrieval. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, June 13--19, 2020. Computer Vision Foundation \/ IEEE, 12652--12660."},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the 37th International Conference on Machine Learning, ICML 2020","volume":"1607","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey E. Hinton. 2020b. A Simple Framework for Contrastive Learning of Visual Representations. In Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13-18 July 2020, Virtual Event (Proceedings of Machine Learning Research, Vol. 119). PMLR, 1597--1607."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"e_1_3_2_1_11_1","volume-title":"VSE: Improving Visual-Semantic Embeddings with Hard Negatives. In British Machine Vision Conference 2018, BMVC 2018","author":"Faghri Fartash","year":"2018","unstructured":"Fartash Faghri, David J. Fleet, Jamie Ryan Kiros, and Sanja Fidler. 2018. VSE: Improving Visual-Semantic Embeddings with Hard Negatives. In British Machine Vision Conference 2018, BMVC 2018, Newcastle, UK, September 3-6, 2018. BMVA Press, 12."},{"key":"e_1_3_2_1_12_1","volume-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022","author":"Fini Enrico","year":"2022","unstructured":"Enrico Fini, Victor G. Turrisi da Costa, Xavier Alameda-Pineda, Elisa Ricci, Karteek Alahari, and Julien Mairal. 2022. Self-Supervised Models are Continual Learners. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18-24, 2022. IEEE, 9611--9620."},{"key":"e_1_3_2_1_13_1","volume-title":"Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems","author":"Frome Andrea","year":"2013","unstructured":"Andrea Frome, Gregory S. Corrado, Jonathon Shlens, Samy Bengio, Jeffrey Dean, Marc'Aurelio Ranzato, and Tom\u00e1 s Mikolov. 2013. DeViSE: A Deep Visual-Semantic Embedding Model. In Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013, Lake Tahoe, Nevada, United States. 2121--2129."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548320"},{"key":"e_1_3_2_1_15_1","volume-title":"Continually Learning Self-Supervised Representations with Projected Functional Regularization. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2022","author":"Gomez-Villa Alex","year":"2022","unstructured":"Alex Gomez-Villa, Bartlomiej Twardowski, Lu Yu, Andrew D. Bagdanov, and Joost van de Weijer. 2022. Continually Learning Self-Supervised Representations with Projected Functional Regularization. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2022, New Orleans, LA, USA, June 19-20, 2022. IEEE, 3866--3876."},{"key":"e_1_3_2_1_16_1","volume-title":"Memory Efficient Experience Replay for Streaming Learning. In International Conference on Robotics and Automation, ICRA 2019","author":"Hayes Tyler L.","year":"2019","unstructured":"Tyler L. Hayes, Nathan D. Cahill, and Christopher Kanan. 2019. Memory Efficient Experience Replay for Streaming Learning. In International Conference on Robotics and Automation, ICRA 2019, Montreal, QC, Canada, May 20-24, 2019. IEEE, 9769--9776."},{"key":"e_1_3_2_1_17_1","volume-title":"Momentum Contrast for Unsupervised Visual Representation Learning. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020","author":"He Kaiming","year":"2020","unstructured":"Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, and Ross B. Girshick. 2020. Momentum Contrast for Unsupervised Visual Representation Learning. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, June 13-19, 2020. Computer Vision Foundation \/ IEEE, 9726--9735."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01560"},{"key":"e_1_3_2_1_19_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"e_1_3_2_1_21_1","first-page":"3366","article-title":"A Continual Learning Survey: Defying Forgetting in Classification Tasks","volume":"44","author":"Lange Matthias De","year":"2022","unstructured":"Matthias De Lange, Rahaf Aljundi, Marc Masana, Sarah Parisot, Xu Jia, Ales Leonardis, Gregory G. Slabaugh, and Tinne Tuytelaars. 2022a. A Continual Learning Survey: Defying Forgetting in Classification Tasks. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 44, 7 (2022), 3366--3385.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_1_22_1","first-page":"3366","article-title":"A Continual Learning Survey: Defying Forgetting in Classification Tasks","volume":"44","author":"Lange Matthias De","year":"2022","unstructured":"Matthias De Lange, Rahaf Aljundi, Marc Masana, Sarah Parisot, Xu Jia, Ales Leonardis, Gregory G. Slabaugh, and Tinne Tuytelaars. 2022b. A Continual Learning Survey: Defying Forgetting in Classification Tasks. IEEE Trans. Pattern Anal. Mach. Intell., Vol. 44, 7 (2022), 3366--3385.","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"e_1_3_2_1_23_1","volume-title":"Munich","volume":"228","author":"Lee Kuang-Huei","year":"2018","unstructured":"Kuang-Huei Lee, Xi Chen, Gang Hua, Houdong Hu, and Xiaodong He. 2018. Stacked Cross Attention for Image-Text Matching. In Computer Vision - ECCV 2018 - 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part IV (Lecture Notes in Computer Science, Vol. 11208), Vittorio Ferrari, Martial Hebert, Cristian Sminchisescu, and Yair Weiss (Eds.). Springer, 212--228."},{"key":"e_1_3_2_1_24_1","volume-title":"Visual Semantic Reasoning for Image-Text Matching. In 2019 IEEE\/CVF International Conference on Computer Vision, ICCV 2019","author":"Li Kunpeng","year":"2019","unstructured":"Kunpeng Li, Yulun Zhang, Kai Li, Yuanyuan Li, and Yun Fu. 2019. Visual Semantic Reasoning for Image-Text Matching. In 2019 IEEE\/CVF International Conference on Computer Vision, ICCV 2019, Seoul, Korea (South), October 27 - November 2, 2019. IEEE, 4653--4661."},{"key":"e_1_3_2_1_25_1","volume-title":"Invariant Grounding for Video Question Answering. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022","author":"Li Yicong","year":"2022","unstructured":"Yicong Li, Xiang Wang, Junbin Xiao, Wei Ji, and Tat-Seng Chua. 2022. Invariant Grounding for Video Question Answering. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18-24, 2022. IEEE, 2918--2927."},{"key":"e_1_3_2_1_26_1","first-page":"740","article-title":"Microsoft COCO: Common Objects in Context","volume":"8693","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, Serge J. Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C. Lawrence Zitnick. 2014. Microsoft COCO: Common Objects in Context. In ECCV, Vol. 8693. 740--755.","journal-title":"ECCV"},{"key":"e_1_3_2_1_27_1","volume-title":"Mnemonics Training: Multi-Class Incremental Learning Without Forgetting. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020","author":"Liu Yaoyao","year":"2020","unstructured":"Yaoyao Liu, Yuting Su, An-An Liu, Bernt Schiele, and Qianru Sun. 2020. Mnemonics Training: Multi-Class Incremental Learning Without Forgetting. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, June 13-19, 2020. Computer Vision Foundation \/ IEEE, 12242--12251."},{"key":"e_1_3_2_1_28_1","volume-title":"SGDR: Stochastic Gradient Descent with Warm Restarts. In 5th International Conference on Learning Representations, ICLR","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. SGDR: Stochastic Gradient Descent with Warm Restarts. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings. OpenReview.net."},{"key":"e_1_3_2_1_29_1","volume-title":"MM '22: The 30th ACM International Conference on Multimedia","author":"Jo\u00e3o","year":"2022","unstructured":"Jo\u00e3o Magalh a es, Alberto Del Bimbo, Shin'ichi Satoh, Nicu Sebe, Xavier Alameda-Pineda, Qin Jin, Vincent Oria, and Laura Toni (Eds.). 2022. MM '22: The 30th ACM International Conference on Multimedia, Lisboa, Portugal, October 10 - 14, 2022. ACM."},{"key":"e_1_3_2_1_30_1","volume-title":"Class-incremental learning: survey and performance evaluation. CoRR","author":"Masana Marc","year":"2020","unstructured":"Marc Masana, Xialei Liu, Bartlomiej Twardowski, Mikel Menta, Andrew D. Bagdanov, and Joost van de Weijer. 2020. Class-incremental learning: survey and performance evaluation. CoRR , Vol. abs\/2010.15277 (2020). [arXiv]2010.15277"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3213473"},{"key":"e_1_3_2_1_32_1","volume-title":"1st International Conference on Learning Representations, ICLR","author":"Mikolov Tom\u00e1s","year":"2013","unstructured":"Tom\u00e1s Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient Estimation of Word Representations in Vector Space. In 1st International Conference on Learning Representations, ICLR 2013, Scottsdale, Arizona, USA, May 2-4, 2013, Workshop Track Proceedings."},{"key":"e_1_3_2_1_33_1","volume-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017","author":"Rebuffi Sylvestre-Alvise","year":"2017","unstructured":"Sylvestre-Alvise Rebuffi, Alexander Kolesnikov, Georg Sperl, and Christoph H. Lampert. 2017. iCaRL: Incremental Classifier and Representation Learning. In 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, July 21-26, 2017. IEEE Computer Society, 5533--5542."},{"key":"e_1_3_2_1_34_1","volume-title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. In Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015","author":"Ren Shaoqing","year":"2015","unstructured":"Shaoqing Ren, Kaiming He, Ross B. Girshick, and Jian Sun. 2015. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. In Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, December 7-12, 2015, Montreal, Quebec, Canada, Corinna Cortes, Neil D. Lawrence, Daniel D. Lee, Masashi Sugiyama, and Roman Garnett (Eds.). 91--99."},{"key":"e_1_3_2_1_35_1","volume-title":"Progressive Neural Networks. CoRR","author":"Rusu Andrei A.","year":"2016","unstructured":"Andrei A. Rusu, Neil C. Rabinowitz, Guillaume Desjardins, Hubert Soyer, James Kirkpatrick, Koray Kavukcuoglu, Razvan Pascanu, and Raia Hadsell. 2016. Progressive Neural Networks. CoRR, Vol. abs\/1606.04671 (2016). [arXiv]1606.04671"},{"key":"e_1_3_2_1_36_1","volume-title":"Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsm\u00e4ssan","author":"Schwarz Jonathan","year":"2018","unstructured":"Jonathan Schwarz, Wojciech Czarnecki, Jelena Luketina, Agnieszka Grabska-Barwinska, Yee Whye Teh, Razvan Pascanu, and Raia Hadsell. 2018. Progress & Compress: A scalable framework for continual learning. In Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsm\u00e4ssan, Stockholm, Sweden, July 10-15, 2018 (Proceedings of Machine Learning Research, Vol. 80). PMLR, 4535--4544."},{"key":"e_1_3_2_1_37_1","volume-title":"Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsm\u00e4ssan","author":"Serr\u00e0 Joan","year":"2018","unstructured":"Joan Serr\u00e0, Didac Suris, Marius Miron, and Alexandros Karatzoglou. 2018. Overcoming Catastrophic Forgetting with Hard Attention to the Task. In Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsm\u00e4ssan, Stockholm, Sweden, July 10-15, 2018 (Proceedings of Machine Learning Research, Vol. 80). PMLR, 4555--4564."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-022-01603-6"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/137"},{"key":"e_1_3_2_1_40_1","volume-title":"On Generalizing Beyond Domains in Cross-Domain Continual Learning. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022","author":"Simon Christian","year":"2022","unstructured":"Christian Simon, Masoud Faraki, Yi-Hsuan Tsai, Xiang Yu, Samuel Schulter, Yumin Suh, Mehrtash Harandi, and Manmohan Chandraker. 2022. On Generalizing Beyond Domains in Cross-Domain Continual Learning. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18-24, 2022. IEEE, 9255--9264."},{"key":"e_1_3_2_1_41_1","unstructured":"Qing Sun Fan Lyu Fanhua Shang Wei Feng and Liang Wan. 2022. Exploring Example Influence in Continual Learning. In NeurIPS."},{"key":"e_1_3_2_1_42_1","volume-title":"ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022","author":"Tewel Yoad","year":"2022","unstructured":"Yoad Tewel, Yoav Shalev, Idan Schwartz, and Lior Wolf. 2022. ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18-24, 2022. IEEE, 17897--17907."},{"key":"e_1_3_2_1_43_1","volume-title":"Representation Learning with Contrastive Predictive Coding. CoRR","author":"van den Oord A\u00e4ron","year":"2018","unstructured":"A\u00e4ron van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation Learning with Contrastive Predictive Coding. CoRR, Vol. abs\/1807.03748 (2018). showeprint[arXiv]1807.03748"},{"key":"e_1_3_2_1_44_1","volume-title":"Continual Learning for Visual Search with Backward Consistent Feature Embedding. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022","author":"Wan Timmy S. T.","year":"2022","unstructured":"Timmy S. T. Wan, Jun-Cheng Chen, Tzer-Yi Wu, and Chu-Song Chen. 2022. Continual Learning for Visual Search with Backward Consistent Feature Embedding. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18-24, 2022. IEEE, 16681--16690."},{"key":"e_1_3_2_1_45_1","volume-title":"Paired Cross-Modal Data Augmentation for Fine-Grained Image-to-Text Retrieval. In MM '22: The 30th ACM International Conference on Multimedia","author":"Wang Hao","year":"2022","unstructured":"Hao Wang, Guosheng Lin, Steven C. H. Hoi, and Chunyan Miao. 2022b. Paired Cross-Modal Data Augmentation for Fine-Grained Image-to-Text Retrieval. In MM '22: The 30th ACM International Conference on Multimedia, Lisboa, Portugal, October 10 - 14, 2022. ACM, 5517--5526."},{"key":"e_1_3_2_1_46_1","volume-title":"Continual Learning in Cross-Modal Retrieval. In IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2021","author":"Wang Kai","year":"2021","unstructured":"Kai Wang, Luis Herranz, and Joost van de Weijer. 2021. Continual Learning in Cross-Modal Retrieval. In IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2021, virtual, June 19-25, 2021. Computer Vision Foundation \/ IEEE, 3628--3638."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548237"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548223"},{"key":"e_1_3_2_1_49_1","volume-title":"General Incremental Learning with Domain-aware Categorical Representations. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022","author":"Xie Jiangwei","year":"2022","unstructured":"Jiangwei Xie, Shipeng Yan, and Xuming He. 2022. General Incremental Learning with Domain-aware Categorical Representations. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18--24, 2022. IEEE, 14331--14340."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"e_1_3_2_1_51_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021","volume":"12320","author":"Zbontar Jure","year":"2021","unstructured":"Jure Zbontar, Li Jing, Ishan Misra, Yann LeCun, and St\u00e9phane Deny. 2021. Barlow Twins: Self-Supervised Learning via Redundancy Reduction. In Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event (Proceedings of Machine Learning Research, Vol. 139). PMLR, 12310--12320."},{"key":"e_1_3_2_1_52_1","volume-title":"Proceedings of the 34th International Conference on Machine Learning, ICML 2017","author":"Zenke Friedemann","year":"2017","unstructured":"Friedemann Zenke, Ben Poole, and Surya Ganguli. 2017. Continual Learning Through Synaptic Intelligence. In Proceedings of the 34th International Conference on Machine Learning, ICML 2017, Sydney, NSW, Australia, 6-11 August 2017 (Proceedings of Machine Learning Research, Vol. 70). PMLR, 3987--3995."},{"key":"e_1_3_2_1_53_1","volume-title":"Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identification. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022","author":"Zhu Haowei","year":"2022","unstructured":"Haowei Zhu, Wenjing Ke, Dong Li, Ji Liu, Lu Tian, and Yi Shan. 2022. Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identification. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18-24, 2022. IEEE, 4682--4692."}],"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\/3581783.3611919","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611919","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:12:13Z","timestamp":1755821533000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611919"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":53,"alternative-id":["10.1145\/3581783.3611919","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611919","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"}}]}}