{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T06:16:51Z","timestamp":1775283411661,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,10,15]],"date-time":"2018-10-15T00:00:00Z","timestamp":1539561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"the National Basic Research Program of China (973 Program)","award":["2015CB352502"],"award-info":[{"award-number":["2015CB352502"]}]},{"name":"the Project of Thousand Youth Talents 2016"},{"name":"the National Research Foundation, Prime Minister?s Office, Singapore under its International Research Centre in Singapore Funding Initiative"},{"name":"the Tencent AI Lab Rhino-Bird Joint Research Program","award":["JR201805"],"award-info":[{"award-number":["JR201805"]}]},{"name":"National Natural Science Foundation of China","award":["61772310"],"award-info":[{"award-number":["61772310"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2018,10,15]]},"DOI":"10.1145\/3240508.3240541","type":"proceedings-article","created":{"date-parts":[[2018,10,18]],"date-time":"2018-10-18T17:52:08Z","timestamp":1539885128000},"page":"1865-1873","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":50,"title":["Multi-modal Preference Modeling for Product Search"],"prefix":"10.1145","author":[{"given":"Yangyang","family":"Guo","sequence":"first","affiliation":[{"name":"Shandong University, Qingdao , China"}]},{"given":"Zhiyong","family":"Cheng","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}]},{"given":"Liqiang","family":"Nie","sequence":"additional","affiliation":[{"name":"Shandong University, Qingdao, China"}]},{"given":"Xin-Shun","family":"Xu","sequence":"additional","affiliation":[{"name":"Shandong University, Jinan, China"}]},{"given":"Mohan","family":"Kankanhalli","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}]}],"member":"320","published-online":{"date-parts":[[2018,10,15]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080813"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159735"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939812"},{"key":"e_1_3_2_1_4_1","unstructured":"Zhangjie Cao Mingsheng Long Jianmin Wang and Qiang Yang. 2017. Transitive hashing network for heterogeneous multimedia retrieval. In AAAI. AAAI 81--87.  Zhangjie Cao Mingsheng Long Jianmin Wang and Qiang Yang. 2017. Transitive hashing network for heterogeneous multimedia retrieval. In AAAI. AAAI 81--87."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Zhiyong Cheng Ying Ding Xiangnan He Lei Zhu Xuemeng Song and Mohan S Kankanhalli. 2018. A^ 3NCF: An adaptive aspect attention model for rating prediction. In IJCAI. Morgan Kaufmann 3748--3754.  Zhiyong Cheng Ying Ding Xiangnan He Lei Zhu Xuemeng Song and Mohan S Kankanhalli. 2018. A^ 3NCF: An adaptive aspect attention model for rating prediction. In IJCAI. Morgan Kaufmann 3748--3754.","DOI":"10.24963\/ijcai.2018\/521"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Zhiyong Cheng Jialie Shen Lei Zhu Mohan S Kankanhalli and Liqiang Nie. 2017. Exploiting music play sequence for music recommendation. In IJCAI. Morgan Kaufmann 3654--3660.   Zhiyong Cheng Jialie Shen Lei Zhu Mohan S Kankanhalli and Liqiang Nie. 2017. Exploiting music play sequence for music recommendation. In IJCAI. Morgan Kaufmann 3654--3660.","DOI":"10.24963\/ijcai.2017\/511"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2806416.2806557"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2505515.2505578"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.14778\/2556549.2556562"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159691"},{"key":"e_1_3_2_1_11_1","unstructured":"Xavier Glorot and Yoshua Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks. In AISTATS. 249--256.  Xavier Glorot and Yoshua Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks. In AISTATS. 249--256."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959152"},{"key":"e_1_3_2_1_13_1","volume-title":"VBPR: Visual bayesian personalized ranking from implicit feedback. In AAAI. AAAI, 144--150.","author":"He Ruining","year":"2016"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052569"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"e_1_3_2_1_16_1","unstructured":"Peiguang Jing Yuting Su Liqiang Nie Xu Bai Jing Liu and Meng Wang. 2017. Low-rank multi-view embedding learning for micro-video popularity prediction. TKDE (2017).  Peiguang Jing Yuting Su Liqiang Nie Xu Bai Jing Liu and Meng Wang. 2017. Low-rank multi-view embedding learning for micro-video popularity prediction. TKDE (2017)."},{"key":"e_1_3_2_1_17_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159716"},{"key":"e_1_3_2_1_19_1","unstructured":"Quoc Le and Tomas Mikolov. 2014. Distributed representations of sentences and documents. In ICML. ACM 1188--1196.   Quoc Le and Tomas Mikolov. 2014. Distributed representations of sentences and documents. In ICML. ACM 1188--1196."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/MIC.2003.1167344"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123341"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210003"},{"key":"e_1_3_2_1_23_1","unstructured":"Junhua Mao Wei Xu Yi Yang Jiang Wang Zhiheng Huang and Alan Yuille. 2014. Deep captioning with multimodal recurrent neural networks (m-rnn). In arXiv preprint arXiv:1412.6632 .  Junhua Mao Wei Xu Yi Yang Jiang Wang Zhiheng Huang and Alan Yuille. 2014. Deep captioning with multimodal recurrent neural networks (m-rnn). In arXiv preprint arXiv:1412.6632 ."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783381"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767755"},{"key":"e_1_3_2_1_26_1","unstructured":"Tomas Mikolov Kai Chen Greg Corrado and Jeffrey Dean. 2013. Efficient estimation of word representations in vector space. In arXiv preprint arXiv:1301.3781 .  Tomas Mikolov Kai Chen Greg Corrado and Jeffrey Dean. 2013. Efficient estimation of word representations in vector space. In arXiv preprint arXiv:1301.3781 ."},{"key":"e_1_3_2_1_27_1","unstructured":"Jiquan Ngiam Aditya Khosla Mingyu Kim Juhan Nam Honglak Lee and Andrew Y Ng. 2011. Multimodal deep learning. In ICML. ACM 689--696.   Jiquan Ngiam Aditya Khosla Mingyu Kim Juhan Nam Honglak Lee and Andrew Y Ng. 2011. Multimodal deep learning. In ICML. ACM 689--696."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123313"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1108\/07363760010309528"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123314"},{"key":"e_1_3_2_1_31_1","volume-title":"ICML workshop","volume":"79","author":"Srivastava Nitish","year":"2012"},{"key":"e_1_3_2_1_32_1","unstructured":"Nitish Srivastava and Ruslan R Salakhutdinov. 2012b. Multimodal learning with deep boltzmann machines. In NIPS. MIT Press 2222--2230.   Nitish Srivastava and Ruslan R Salakhutdinov. 2012b. Multimodal learning with deep boltzmann machines. In NIPS. MIT Press 2222--2230."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159714"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2983323.2983702"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939753"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-015-0391-4"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806222"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/984321.984322"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Hanwang Zhang Zawlin Kyaw Shih-Fu Chang and Tat-Seng Chua. 2017b. Visual translation embedding network for visual relation detection. In CVPR. IEEE 3107--3115.  Hanwang Zhang Zawlin Kyaw Shih-Fu Chang and Tat-Seng Chua. 2017b. Visual translation embedding network for visual relation detection. In CVPR. IEEE 3107--3115.","DOI":"10.1109\/CVPR.2017.331"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"Hanwang Zhang Yulei Niu and Shih-Fu Chang. 2018. Grounding referring expressions in images by variational context. In CVPR. IEEE 4158--4166.  Hanwang Zhang Yulei Niu and Shih-Fu Chang. 2018. Grounding referring expressions in images by variational context. In CVPR. IEEE 4158--4166.","DOI":"10.1109\/CVPR.2018.00437"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654915"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502093"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3132892"}],"event":{"name":"MM '18: ACM Multimedia Conference","location":"Seoul Republic of Korea","acronym":"MM '18","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 26th ACM international conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3240508.3240541","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3240508.3240541","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:44:01Z","timestamp":1750207441000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3240508.3240541"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10,15]]},"references-count":43,"alternative-id":["10.1145\/3240508.3240541","10.1145\/3240508"],"URL":"https:\/\/doi.org\/10.1145\/3240508.3240541","relation":{},"subject":[],"published":{"date-parts":[[2018,10,15]]},"assertion":[{"value":"2018-10-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}