{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T13:38:48Z","timestamp":1771594728712,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":98,"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\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2023A1515012914"],"award-info":[{"award-number":["2023A1515012914"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]},{"name":"PCNL KEY project","award":["PCL2021A07"],"award-info":[{"award-number":["PCL2021A07"]}]},{"name":"Major Key Project of PCL for Experiments and Applications","award":["PCL2021A06"],"award-info":[{"award-number":["PCL2021A06"]}]},{"name":"Overseas Cooperation Research Fund of Tsinghua Shenzhen International Graduate School","award":["HW2021008"],"award-info":[{"award-number":["HW2021008"]}]},{"name":"Shenzhen Science and Technology Program","award":["JCYJ20220818101012025"],"award-info":[{"award-number":["JCYJ20220818101012025"]}]},{"name":"Basic Research Fund of Shenzhen City","award":["JSGG20210802154402007"],"award-info":[{"award-number":["JSGG20210802154402007"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62171248, 62276154"],"award-info":[{"award-number":["62171248, 62276154"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611967","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T19:52:54Z","timestamp":1698436374000},"page":"6548-6557","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":51,"title":["MISSRec: Pre-training and Transferring Multi-modal Interest-aware Sequence Representation for Recommendation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4352-4897","authenticated-orcid":false,"given":"Jinpeng","family":"Wang","sequence":"first","affiliation":[{"name":"Tsinghua University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5903-4462","authenticated-orcid":false,"given":"Ziyun","family":"Zeng","sequence":"additional","affiliation":[{"name":"Tsinghua University, Shenzhen, China"}]},{"given":"Yunxiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Shenzhen, China"}]},{"given":"Yuting","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Shenzhen, China"}]},{"given":"Xingyu","family":"Lu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Shenzhen, China"}]},{"given":"Tianxiang","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University, Shenzhen, China"}]},{"given":"Jun","family":"Yuan","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8132-6250","authenticated-orcid":false,"given":"Rui","family":"Zhang","sequence":"additional","affiliation":[{"name":"www.ruizhang.info, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5128-5649","authenticated-orcid":false,"given":"Hai-Tao","family":"Zheng","sequence":"additional","affiliation":[{"name":"Tsinghua University & Peng Cheng Laboratory, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8639-982X","authenticated-orcid":false,"given":"Shu-Tao","family":"Xia","sequence":"additional","affiliation":[{"name":"Tsinghua University & Peng Cheng Laboratory, Shenzhen, China"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Himan Abdollahpouri Masoud Mansoury Robin Burke and Bamshad Mobasher. 2020. The connection between popularity bias calibration and fairness in recommendation. In RecSys.","DOI":"10.1145\/3383313.3418487"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Ankur Bapna and Orhan Firat. 2019. Simple Scalable Adaptation for Neural Machine Translation. In EMNLP.","DOI":"10.18653\/v1\/N19-1191"},{"key":"e_1_3_2_1_3_1","volume-title":"Heterogeneous hierarchical feature aggregation network for personalized micro-video recommendation","author":"Cai Desheng","year":"2021","unstructured":"Desheng Cai, Shengsheng Qian, Quan Fang, and Changsheng Xu. 2021. Heterogeneous hierarchical feature aggregation network for personalized micro-video recommendation. IEEE TMM (2021)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Yukuo Cen Jianwei Zhang Xu Zou Chang Zhou Hongxia Yang and Jie Tang. 2020. Controllable multi-interest framework for recommendation. In KDD.","DOI":"10.1145\/3394486.3403344"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Jingyuan Chen Hanwang Zhang Xiangnan He Liqiang Nie Wei Liu and Tat-Seng Chua 2017. Attentive collaborative filtering: Multimedia recommendation with item-and component-level attention. In SIGIR.","DOI":"10.1145\/3077136.3080797"},{"key":"e_1_3_2_1_6_1","unstructured":"Ting Chen Simon Kornblith Mohammad Norouzi and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In ICML."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Yongjun Chen Zhiwei Liu Jia Li Julian McAuley and Caiming Xiong. 2022. Intent contrastive learning for sequential recommendation. In WWW.","DOI":"10.1145\/3485447.3512090"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Mingyue Cheng Fajie Yuan Qi Liu Xin Xin and Enhong Chen. 2021. Learning transferable user representations with sequential behaviors via contrastive pre-training. In ICDM.","DOI":"10.1109\/ICDM51629.2021.00015"},{"key":"e_1_3_2_1_9_1","volume-title":"LCD: Adaptive Label Correction for Denoising Music Recommendation. In CIKM.","author":"Dai Quanyu","year":"2022","unstructured":"Quanyu Dai, Yalei Lv, Jieming Zhu, Junjie Ye, Zhenhua Dong, Rui Zhang, Shu-Tao Xia, and Ruiming Tang. 2022. LCD: Adaptive Label Correction for Denoising Music Recommendation. In CIKM."},{"key":"e_1_3_2_1_10_1","volume-title":"Recommender systems leveraging multimedia content. ACM CSUR","author":"Deldjoo Yashar","year":"2020","unstructured":"Yashar Deldjoo, Markus Schedl, Paolo Cremonesi, and Gabriella Pasi. 2020. Recommender systems leveraging multimedia content. ACM CSUR (2020)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Yashar Deldjoo Markus Schedl Bal\u00e1zs Hidasi Yinwei Wei and Xiangnan He. 2021. Multimedia recommender systems: Algorithms and challenges. In Recommender systems handbook.","DOI":"10.1007\/978-1-0716-2197-4_25"},{"key":"e_1_3_2_1_12_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In 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 NAACL."},{"key":"e_1_3_2_1_13_1","volume-title":"Zero-Shot Recommender Systems. In ICLR Workshops.","author":"Ding Hao","year":"2022","unstructured":"Hao Ding, Yifei Ma, Anoop Deoras, Yuyang Wang, and Hao Wang. 2022. Zero-Shot Recommender Systems. In ICLR Workshops."},{"key":"e_1_3_2_1_14_1","volume-title":"Words: Transformers for Image Recognition at Scale. In ICLR.","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, et al. 2020. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In ICLR."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2016.02.001"},{"key":"e_1_3_2_1_16_1","unstructured":"Xiaoyu Du Xiang Wang Xiangnan He Zechao Li Jinhui Tang and Tat-Seng Chua. 2020. How to learn item representation for cold-start multimedia recommendation?. In MM."},{"key":"e_1_3_2_1_17_1","unstructured":"Kai Han Yunhe Wang Hanting Chen Xinghao Chen Jianyuan Guo Zhenhua Liu Yehui Tang An Xiao Chunjing Xu Yixing Xu et al. 2022. A survey on vision transformer. IEEE TPAMI (2022)."},{"key":"e_1_3_2_1_18_1","unstructured":"Junxian He Chunting Zhou Xuezhe Ma Taylor Berg-Kirkpatrick and Graham Neubig. 2022. Towards a Unified View of Parameter-Efficient Transfer Learning. In ICLR."},{"key":"e_1_3_2_1_19_1","unstructured":"Kaiming He Haoqi Fan Yuxin Wu Saining Xie and Ross Girshick. 2020b. Momentum contrast for unsupervised visual representation learning. In CVPR."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"Li He Hongxu Chen Dingxian Wang Shoaib Jameel Philip Yu and Guandong Xu. 2021. Click-through rate prediction with multi-modal hypergraphs. In CIKM.","DOI":"10.1145\/3459637.3482327"},{"key":"e_1_3_2_1_21_1","unstructured":"Ruining He and Julian McAuley. 2016a. Fusing similarity models with markov chains for sparse sequential recommendation. In ICDM."},{"key":"e_1_3_2_1_22_1","unstructured":"Ruining He and Julian McAuley. 2016b. VBPR: visual bayesian personalized ranking from implicit feedback. In AAAI."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401063"},{"key":"e_1_3_2_1_24_1","unstructured":"Bal\u00e1zs Hidasi Alexandros Karatzoglou Linas Baltrunas and Domonkos Tikk. 2016. Session-based recommendations with recurrent neural networks. In ICLR."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Yupeng Hou Zhankui He Julian McAuley and Wayne Xin Zhao. 2023. Learning vector-quantized item representation for transferable sequential recommenders. In WWW.","DOI":"10.1145\/3543507.3583434"},{"key":"e_1_3_2_1_26_1","volume-title":"Yaliang Li, Bolin Ding, and Ji-Rong Wen.","author":"Hou Yupeng","year":"2022","unstructured":"Yupeng Hou, Shanlei Mu, Wayne Xin Zhao, Yaliang Li, Bolin Ding, and Ji-Rong Wen. 2022. Towards Universal Sequence Representation Learning for Recommender Systems. In KDD."},{"key":"e_1_3_2_1_27_1","volume-title":"Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly.","author":"Houlsby Neil","year":"2019","unstructured":"Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin De Laroussilhe, Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. 2019. Parameter-efficient transfer learning for NLP. In ICML."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240609"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Hao Jiang Wenjie Wang Yinwei Wei Zan Gao Yinglong Wang and Liqiang Nie. 2020. What aspect do you like: Multi-scale time-aware user interest modeling for micro-video recommendation. In MM.","DOI":"10.1145\/3394171.3413653"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Xunqiang Jiang Yuanfu Lu Yuan Fang and Chuan Shi. 2021. Contrastive pre-training of gnns on heterogeneous graphs. In CIKM.","DOI":"10.1145\/3459637.3482332"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Wang-Cheng Kang and Julian McAuley. 2018. Self-attentive sequential recommendation. In ICDM.","DOI":"10.1109\/ICDM.2018.00035"},{"key":"e_1_3_2_1_32_1","volume-title":"Fahad Shahbaz Khan, and Mubarak Shah.","author":"Khan Salman","year":"2022","unstructured":"Salman Khan, Muzammal Naseer, Munawar Hayat, Syed Waqas Zamir, Fahad Shahbaz Khan, and Mubarak Shah. 2022. Transformers in vision: A survey. ACM CSUR (2022)."},{"key":"e_1_3_2_1_33_1","volume-title":"Semi: A sequential multi-modal information transfer network for e-commerce micro-video recommendations. In KDD. 3161--3171.","author":"Lei Chenyi","year":"2021","unstructured":"Chenyi Lei, Yong Liu, Lingzi Zhang, Guoxin Wang, Haihong Tang, Houqiang Li, and Chunyan Miao. 2021. Semi: A sequential multi-modal information transfer network for e-commerce micro-video recommendations. In KDD. 3161--3171."},{"key":"e_1_3_2_1_34_1","unstructured":"Chao Li Zhiyuan Liu Mengmeng Wu Yuchi Xu Huan Zhao Pipei Huang Guoliang Kang Qiwei Chen Wei Li and Dik Lun Lee. 2019. Multi-interest network with dynamic routing for recommendation at Tmall. In CIKM."},{"key":"e_1_3_2_1_35_1","unstructured":"Jiacheng Li Yujie Wang and Julian McAuley. 2020. Time interval aware self-attention for sequential recommendation. In WSDM."},{"key":"e_1_3_2_1_36_1","unstructured":"Jian Li Jieming Zhu Qiwei Bi Guohao Cai Lifeng Shang Zhenhua Dong Xin Jiang and Qun Liu. 2022. MINER: multi-interest matching network for news recommendation. In ACL Findings."},{"key":"e_1_3_2_1_37_1","volume-title":"MMMLP: Multi-modal Multilayer Perceptron for Sequential Recommendations. In WWW.","author":"Liang Jiahao","year":"2023","unstructured":"Jiahao Liang, Xiangyu Zhao, Muyang Li, Zijian Zhang, Wanyu Wang, Haochen Liu, and Zitao Liu. 2023. MMMLP: Multi-modal Multilayer Perceptron for Sequential Recommendations. In WWW."},{"key":"e_1_3_2_1_38_1","unstructured":"Guanyu Lin Chen Gao Yu Zheng Jianxin Chang Yanan Niu Yang Song Zhiheng Li Depeng Jin and Yong Li. 2023. Dual-interest Factorization-heads Attention for Sequential Recommendation. In WWW."},{"key":"e_1_3_2_1_39_1","volume-title":"prompt, and predict: A systematic survey of prompting methods in natural language processing. ACM CSUR","author":"Liu Pengfei","year":"2023","unstructured":"Pengfei Liu, Weizhe Yuan, Jinlan Fu, Zhengbao Jiang, Hiroaki Hayashi, and Graham Neubig. 2023. Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. ACM CSUR (2023)."},{"key":"e_1_3_2_1_40_1","unstructured":"Qijiong Liu Jieming Zhu Quanyu Dai and Xiaoming Wu. 2022b. Boosting deep ctr prediction with a plug-and-play pre-trainer for news recommendation. In COLING."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"crossref","unstructured":"Yong Liu Susen Yang Chenyi Lei Guoxin Wang Haihong Tang Juyong Zhang Aixin Sun and Chunyan Miao. 2021. Pre-training graph transformer with multimodal side information for recommendation. In MM.","DOI":"10.1145\/3474085.3475709"},{"key":"e_1_3_2_1_42_1","unstructured":"Zhuang Liu Yunpu Ma Matthias Schubert Yuanxin Ouyang and Zhang Xiong. 2022a. Multi-Modal Contrastive Pre-training for Recommendation. In ICMR."},{"key":"e_1_3_2_1_43_1","unstructured":"Chen Ma Peng Kang and Xue Liu. 2019. Hierarchical gating networks for sequential recommendation. In KDD."},{"key":"e_1_3_2_1_44_1","unstructured":"Kelong Mao Jieming Zhu Jinpeng Wang Quanyu Dai Zhenhua Dong Xi Xiao and Xiuqiang He. 2021. SimpleX: A simple and strong baseline for collaborative filtering. In CIKM."},{"key":"e_1_3_2_1_45_1","unstructured":"Jianmo Ni Jiacheng Li and Julian McAuley. 2019. Justifying recommendations using distantly-labeled reviews and fine-grained aspects. In EMNLP."},{"key":"e_1_3_2_1_46_1","unstructured":"Yabo Ni Dan Ou Shichen Liu Xiang Li Wenwu Ou Anxiang Zeng and Luo Si. 2018. Perceive your users in depth: Learning universal user representations from multiple e-commerce tasks. In KDD."},{"key":"e_1_3_2_1_47_1","unstructured":"Xingyu Pan Yushuo Chen Changxin Tian Zihan Lin Jinpeng Wang He Hu and Wayne Xin Zhao. 2022. Multimodal Meta-Learning for Cold-Start Sequential Recommendation. In CIKM."},{"key":"e_1_3_2_1_48_1","unstructured":"Ruihong Qiu Zi Huang Hongzhi Yin and Zijian Wang. 2022. Contrastive learning for representation degeneration problem in sequential recommendation. In CIKM."},{"key":"e_1_3_2_1_49_1","unstructured":"Zhaopeng Qiu Xian Wu Jingyue Gao and Wei Fan. 2021. U-BERT: Pre-training user representations for improved recommendation. In AAAI."},{"key":"e_1_3_2_1_50_1","volume-title":"Sequence-aware recommender systems. ACM CSUR","author":"Quadrana Massimo","year":"2018","unstructured":"Massimo Quadrana, Paolo Cremonesi, and Dietmar Jannach. 2018. Sequence-aware recommender systems. ACM CSUR (2018)."},{"key":"e_1_3_2_1_51_1","volume-title":"Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al.","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 ICML."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"crossref","unstructured":"Steffen Rendle Christoph Freudenthaler and Lars Schmidt-Thieme. 2010. Factorizing personalized markov chains for next-basket recommendation. In WWW.","DOI":"10.1145\/1772690.1772773"},{"key":"e_1_3_2_1_53_1","volume-title":"Recommender systems. Commun. ACM","author":"Resnick Paul","year":"1997","unstructured":"Paul Resnick and Hal R Varian. 1997. Recommender systems. Commun. ACM (1997)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"crossref","unstructured":"Andrew I Schein Alexandrin Popescul Lyle H Ungar and David M Pennock. 2002. Methods and metrics for cold-start recommendations. In SIGIR.","DOI":"10.1145\/564418.564421"},{"key":"e_1_3_2_1_55_1","volume-title":"2023 a. Self-Supervised Multi-Modal Sequential Recommendation. arXiv preprint arXiv:2304.13277","author":"Song Kunzhe","year":"2023","unstructured":"Kunzhe Song, Qingfeng Sun, Can Xu, Kai Zheng, and Yaming Yang. 2023 a. Self-Supervised Multi-Modal Sequential Recommendation. arXiv preprint arXiv:2304.13277 (2023)."},{"key":"e_1_3_2_1_56_1","volume-title":"2023 b. MM-FRec: Multi-Modal Enhanced Fashion Item Recommendation","author":"Song Xuemeng","year":"2023","unstructured":"Xuemeng Song, Chun Wang, Changchang Sun, Shanshan Feng, Min Zhou, and Liqiang Nie. 2023 b. MM-FRec: Multi-Modal Enhanced Fashion Item Recommendation. IEEE TKDE (2023)."},{"key":"e_1_3_2_1_57_1","volume-title":"Dropout: a simple way to prevent neural networks from overfitting. JMLR","author":"Srivastava Nitish","year":"2014","unstructured":"Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. 2014. Dropout: a simple way to prevent neural networks from overfitting. JMLR (2014)."},{"key":"e_1_3_2_1_58_1","unstructured":"Weijie Su Xizhou Zhu Yue Cao Bin Li Lewei Lu Furu Wei and Jifeng Dai. 2020. VL-BERT: Pre-training of Generic Visual-Linguistic Representations. In ICLR."},{"key":"e_1_3_2_1_59_1","unstructured":"Yixin Su Rui Zhang Sarah Erfani and Zhenghua Xu. 2021. Detecting beneficial feature interactions for recommender systems. In AAAI."},{"key":"e_1_3_2_1_60_1","unstructured":"Yixin Su Yunxiang Zhao Sarah Erfani Junhao Gan and Rui Zhang. 2022. Detecting arbitrary order beneficial feature interactions for recommender systems. In KDD."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"crossref","unstructured":"Fei Sun Jun Liu Jian Wu Changhua Pei Xiao Lin Wenwu Ou and Peng Jiang. 2019. BERT4Rec: Sequential recommendation with bidirectional encoder representations from transformer. In CIKM.","DOI":"10.1145\/3357384.3357895"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"crossref","unstructured":"Rui Sun Xuezhi Cao Yan Zhao Junchen Wan Kun Zhou Fuzheng Zhang Zhongyuan Wang and Kai Zheng. 2020. Multi-modal knowledge graphs for recommender systems. In CIKM.","DOI":"10.1145\/3340531.3411947"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"crossref","unstructured":"Jiaxi Tang and Ke Wang. 2018. Personalized top-n sequential recommendation via convolutional sequence embedding. In WSDM.","DOI":"10.1145\/3159652.3159656"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3187556"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"crossref","unstructured":"Changxin Tian Zihan Lin Shuqing Bian Jinpeng Wang and Wayne Xin Zhao. 2022. Temporal Contrastive Pre-Training for Sequential Recommendation. In CIKM.","DOI":"10.1145\/3511808.3557468"},{"key":"e_1_3_2_1_66_1","volume-title":"Mlp-mixer: An all-mlp architecture for vision. NIPS","author":"Tolstikhin Ilya O","year":"2021","unstructured":"Ilya O Tolstikhin, Neil Houlsby, Alexander Kolesnikov, Lucas Beyer, Xiaohua Zhai, Thomas Unterthiner, Jessica Yung, Andreas Steiner, Daniel Keysers, Jakob Uszkoreit, et al. 2021. Mlp-mixer: An all-mlp architecture for vision. NIPS (2021)."},{"key":"e_1_3_2_1_67_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez ?ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In NIPS."},{"key":"e_1_3_2_1_68_1","volume-title":"2023 a. Sequential recommendation with multiple contrast signals. ACM TOIS","author":"Wang Chenyang","year":"2023","unstructured":"Chenyang Wang, Weizhi Ma, Chong Chen, Min Zhang, Yiqun Liu, and Shaoping Ma. 2023 a. Sequential recommendation with multiple contrast signals. ACM TOIS (2023)."},{"key":"e_1_3_2_1_69_1","volume-title":"2023 b. Curriculum Pre-Training Heterogeneous Subgraph Transformer for Top-N Recommendation. ACM TOIS","author":"Wang Hui","year":"2023","unstructured":"Hui Wang, Kun Zhou, Xin Zhao, Jingyuan Wang, and Ji-Rong Wen. 2023 b. Curriculum Pre-Training Heterogeneous Subgraph Transformer for Top-N Recommendation. ACM TOIS (2023)."},{"key":"e_1_3_2_1_70_1","volume-title":"TransRec: Learning Transferable Recommendation from Mixture-of-Modality Feedback. arXiv preprint arXiv:2206.06190","author":"Wang Jie","year":"2022","unstructured":"Jie Wang, Fajie Yuan, Mingyue Cheng, Joemon M Jose, Chenyun Yu, Beibei Kong, Zhijin Wang, Bo Hu, and Zang Li. 2022a. TransRec: Learning Transferable Recommendation from Mixture-of-Modality Feedback. arXiv preprint arXiv:2206.06190 (2022)."},{"key":"e_1_3_2_1_71_1","unstructured":"Jinpeng Wang Ziyun Zeng Bin Chen Yuting Wang Dongliang Liao Gongfu Li Yiru Wang Shu-Tao Xia and Peng Cheng Intelligence. 2022b. Hugs Are Better Than Handshakes: Unsupervised Cross-Modal Transformer Hashing with Multi-granularity Alignment. In BMVC."},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"crossref","unstructured":"Shoujin Wang Liang Hu Yan Wang Longbing Cao Quan Z. Sheng and Mehmet Orgun. 2019. Sequential Recommender Systems: Challenges Progress and Prospects. In IJCAI.","DOI":"10.24963\/ijcai.2019\/883"},{"key":"e_1_3_2_1_73_1","volume-title":"Multi-Modal Self-Supervised Learning for Recommendation. arXiv preprint arXiv:2302.10632","author":"Wei Wei","year":"2023","unstructured":"Wei Wei, Chao Huang, Lianghao Xia, and Chuxu Zhang. 2023. Multi-Modal Self-Supervised Learning for Recommendation. arXiv preprint arXiv:2302.10632 (2023)."},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"crossref","unstructured":"Yinwei Wei Xiang Wang Liqiang Nie Xiangnan He and Tat-Seng Chua. 2020. Graph-refined convolutional network for multimedia recommendation with implicit feedback. In MM.","DOI":"10.1145\/3394171.3413556"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351034"},{"key":"e_1_3_2_1_76_1","unstructured":"Chuhan Wu Fangzhao Wu Tao Qi Chao Zhang Yongfeng Huang and Tong Xu. 2022. MM-Rec: Visiolinguistic Model Empowered Multimodal News Recommendation. In SIGIR."},{"key":"e_1_3_2_1_77_1","volume-title":"UPRec: User-aware Pre-training for Recommender Systems. arXiv preprint arXiv:2102.10989","author":"Xiao Chaojun","year":"2021","unstructured":"Chaojun Xiao, Ruobing Xie, Yuan Yao, Zhiyuan Liu, Maosong Sun, Xu Zhang, and Leyu Lin. 2021. UPRec: User-aware Pre-training for Recommender Systems. arXiv preprint arXiv:2102.10989 (2021)."},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"crossref","unstructured":"Xu Xie Fei Sun Zhaoyang Liu Shiwen Wu Jinyang Gao Jiandong Zhang Bolin Ding and Bin Cui. 2022. Contrastive learning for sequential recommendation. In ICDE.","DOI":"10.1109\/ICDE53745.2022.00099"},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"crossref","unstructured":"Jiahao Xun Shengyu Zhang Zhou Zhao Jieming Zhu Qi Zhang Jingjie Li Xiuqiang He Xiaofei He Tat-Seng Chua and Fei Wu. 2021. Why do we click: visual impression-aware news recommendation. In MM.","DOI":"10.1145\/3474085.3475514"},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"crossref","unstructured":"Shiquan Yang Rui Zhang Sarah M Erfani and Jey Han Lau. 2021. UniMF: A Unified Framework to Incorporate Multimodal Knowledge Bases into End-to-End Task-Oriented Dialogue Systems.. In IJCAI.","DOI":"10.24963\/ijcai.2021\/548"},{"key":"e_1_3_2_1_81_1","unstructured":"Zixuan Yi Xi Wang Iadh Ounis and Craig Macdonald. 2022. Multi-modal graph contrastive learning for micro-video recommendation. In SIGIR."},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"crossref","unstructured":"Fajie Yuan Xiangnan He Alexandros Karatzoglou and Liguang Zhang. 2020. Parameter-efficient transfer from sequential behaviors for user modeling and recommendation. In SIGIR.","DOI":"10.1145\/3397271.3401156"},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"crossref","unstructured":"Fajie Yuan Alexandros Karatzoglou Ioannis Arapakis Joemon M Jose and Xiangnan He. 2019. A simple convolutional generative network for next item recommendation. In WSDM.","DOI":"10.1145\/3289600.3290975"},{"key":"e_1_3_2_1_84_1","doi-asserted-by":"crossref","unstructured":"Zheng Yuan Fajie Yuan Yu Song Youhua Li Junchen Fu Fei Yang Yunzhu Pan and Yongxin Ni. 2023. Where to Go Next for Recommender Systems? ID-vs. Modality-based recommender models revisited. In SIGIR.","DOI":"10.1145\/3539618.3591932"},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"crossref","unstructured":"Jinghao Zhang Yanqiao Zhu Qiang Liu Shu Wu Shuhui Wang and Liang Wang. 2021c. Mining latent structures for multimedia recommendation. In MM.","DOI":"10.1145\/3474085.3475259"},{"key":"e_1_3_2_1_86_1","volume-title":"Multimodal Pre-training Framework for Sequential Recommendation via Contrastive Learning. arXiv preprint arXiv:2303.11879","author":"Zhang Lingzi","year":"2023","unstructured":"Lingzi Zhang, Xin Zhou, and Zhiqi Shen. 2023. Multimodal Pre-training Framework for Sequential Recommendation via Contrastive Learning. arXiv preprint arXiv:2303.11879 (2023)."},{"key":"e_1_3_2_1_87_1","volume-title":"UNBERT: User-News Matching BERT for News Recommendation.. In IJCAI.","author":"Zhang Qi","year":"2021","unstructured":"Qi Zhang, Jingjie Li, Qinglin Jia, Chuyuan Wang, Jieming Zhu, Zhaowei Wang, and Xiuqiang He. 2021b. UNBERT: User-News Matching BERT for News Recommendation.. In IJCAI."},{"key":"e_1_3_2_1_88_1","doi-asserted-by":"crossref","unstructured":"Shengyu Zhang Lingxiao Yang Dong Yao Yujie Lu Fuli Feng Zhou Zhao Tat-Seng Chua and Fei Wu. 2022. Re4: Learning to Re-contrast Re-attend Re-construct for Multi-interest Recommendation. In WWW.","DOI":"10.1145\/3485447.3512094"},{"key":"e_1_3_2_1_89_1","doi-asserted-by":"crossref","unstructured":"Tingting Zhang Pengpeng Zhao Yanchi Liu Victor S Sheng Jiajie Xu Deqing Wang Guanfeng Liu Xiaofang Zhou et al. 2019. Feature-level Deeper Self-Attention Network for Sequential Recommendation.. In IJCAI.","DOI":"10.24963\/ijcai.2019\/600"},{"key":"e_1_3_2_1_90_1","doi-asserted-by":"crossref","unstructured":"Yang Zhang Fuli Feng Xiangnan He Tianxin Wei Chonggang Song Guohui Ling and Yongdong Zhang. 2021a. Causal intervention for leveraging popularity bias in recommendation. In SIGIR.","DOI":"10.1145\/3404835.3462875"},{"key":"e_1_3_2_1_91_1","doi-asserted-by":"crossref","unstructured":"Qihang Zhao. 2022. RESETBERT4Rec: A pre-training model integrating time and user historical behavior for sequential recommendation. In SIGIR.","DOI":"10.1145\/3477495.3532054"},{"key":"e_1_3_2_1_92_1","unstructured":"Wayne Xin Zhao Kun Zhou Junyi Li Tianyi Tang Xiaolei Wang Yupeng Hou Yingqian Min Beichen Zhang Junjie Zhang Zican Dong et al. 2023. A survey of large language models. arXiv preprint arXiv:2303.18223 (2023)."},{"key":"e_1_3_2_1_93_1","doi-asserted-by":"crossref","unstructured":"Guorui Zhou Xiaoqiang Zhu Chenru Song Ying Fan Han Zhu Xiao Ma Yanghui Yan Junqi Jin Han Li and Kun Gai. 2018. Deep interest network for click-through rate prediction. In KDD.","DOI":"10.1145\/3219819.3219823"},{"key":"e_1_3_2_1_94_1","volume-title":"2023 b. A Comprehensive Survey on Multimodal Recommender Systems: Taxonomy, Evaluation, and Future Directions. arXiv preprint arXiv:2302.04473","author":"Zhou Hongyu","year":"2023","unstructured":"Hongyu Zhou, Xin Zhou, Zhiwei Zeng, Lingzi Zhang, and Zhiqi Shen. 2023 b. A Comprehensive Survey on Multimodal Recommender Systems: Taxonomy, Evaluation, and Future Directions. arXiv preprint arXiv:2302.04473 (2023)."},{"key":"e_1_3_2_1_95_1","volume-title":"Yutao Zhu, Sirui Wang, Fuzheng Zhang, Zhongyuan Wang, and Ji-Rong Wen.","author":"Zhou Kun","year":"2020","unstructured":"Kun Zhou, Hui Wang, Wayne Xin Zhao, Yutao Zhu, Sirui Wang, Fuzheng Zhang, Zhongyuan Wang, and Ji-Rong Wen. 2020. S3-Rec: Self-supervised Learning for Sequential Recommendation with Mutual Information Maximization. In CIKM."},{"key":"e_1_3_2_1_96_1","volume-title":"Wayne Xin Zhao, and Ji-Rong Wen","author":"Zhou Kun","year":"2022","unstructured":"Kun Zhou, Hui Yu, Wayne Xin Zhao, and Ji-Rong Wen. 2022. Filter-enhanced MLP is all you need for sequential recommendation. In WWW."},{"key":"e_1_3_2_1_97_1","doi-asserted-by":"crossref","unstructured":"Xin Zhou Hongyu Zhou Yong Liu Zhiwei Zeng Chunyan Miao Pengwei Wang Yuan You and Feijun Jiang. 2023 a. Bootstrap Latent Representations for Multi-Modal Recommendation. In WWW.","DOI":"10.1145\/3543507.3583251"},{"key":"e_1_3_2_1_98_1","doi-asserted-by":"crossref","unstructured":"Feng Zhu Yan Wang Chaochao Chen Jun Zhou Longfei Li and Guanfeng Liu. 2021. Cross-domain recommendation: challenges progress and prospects. In IJCAI.","DOI":"10.24963\/ijcai.2021\/639"}],"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\/3581783.3611967","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611967","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:10:54Z","timestamp":1755821454000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611967"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":98,"alternative-id":["10.1145\/3581783.3611967","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611967","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"}}]}}