{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T02:21:16Z","timestamp":1785291676698,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":65,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T00:00:00Z","timestamp":1602460800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Natural Science Foundation of China","award":["61702143, 61836002, 61725203, 61732008"],"award-info":[{"award-number":["61702143, 61836002, 61725203, 61732008"]}]},{"name":"National Key R&D Program of China","award":["2018AAA0100603"],"award-info":[{"award-number":["2018AAA0100603"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,10,12]]},"DOI":"10.1145\/3394171.3413977","type":"proceedings-article","created":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T13:12:00Z","timestamp":1602508320000},"page":"3743-3752","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":77,"title":["Deep Multimodal Neural Architecture Search"],"prefix":"10.1145","author":[{"given":"Zhou","family":"Yu","sequence":"first","affiliation":[{"name":"Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhao","family":"Cui","sequence":"additional","affiliation":[{"name":"Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Yu","sequence":"additional","affiliation":[{"name":"Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng","family":"Wang","sequence":"additional","affiliation":[{"name":"Hefei University of Technology, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[{"name":"The University of Sydney, Sydney, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Tian","sequence":"additional","affiliation":[{"name":"Huawei Cloud & AI, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2020,10,12]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering. IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","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. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018). 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. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"e_1_3_2_2_3_1","volume-title":"Jamie Ryan Kiros, and Geoffrey E Hinton","author":"Ba Jimmy Lei","year":"2016","unstructured":"Jimmy Lei Ba , Jamie Ryan Kiros, and Geoffrey E Hinton . 2016 . Layer normalization. arXiv preprint arXiv:1607.06450 (2016). Jimmy Lei Ba, Jamie Ryan Kiros, and Geoffrey E Hinton. 2016. Layer normalization. arXiv preprint arXiv:1607.06450 (2016)."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"e_1_3_2_2_5_1","volume-title":"Understanding and Simplifying One-Shot Architecture Search. In International Conference on Machine Learning (ICML). 550--559","author":"Bender Gabriel","year":"2018","unstructured":"Gabriel Bender , Pieter-Jan Kindermans , Barret Zoph , Vijay Vasudevan , and Quoc Le . 2018 . Understanding and Simplifying One-Shot Architecture Search. In International Conference on Machine Learning (ICML). 550--559 . Gabriel Bender, Pieter-Jan Kindermans, Barret Zoph, Vijay Vasudevan, and Quoc Le. 2018. Understanding and Simplifying One-Shot Architecture Search. In International Conference on Machine Learning (ICML). 550--559."},{"key":"e_1_3_2_2_6_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Brock Andrew","year":"2018","unstructured":"Andrew Brock , Theodore Lim , James Millar Ritchie , and Nicholas J Weston . 2018 . SMASH: One-Shot Model Architecture Search through HyperNetworks . In International Conference on Learning Representations (ICLR). Andrew Brock, Theodore Lim, James Millar Ritchie, and Nicholas J Weston. 2018. SMASH: One-Shot Model Architecture Search through HyperNetworks. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_2_7_1","volume-title":"Proxylessnas: Direct neural architecture search on target task and hardware. arXiv preprint arXiv:1812.00332","author":"Cai Han","year":"2018","unstructured":"Han Cai , Ligeng Zhu , and Song Han . 2018 . Proxylessnas: Direct neural architecture search on target task and hardware. arXiv preprint arXiv:1812.00332 (2018). Han Cai, Ligeng Zhu, and Song Han. 2018. Proxylessnas: Direct neural architecture search on target task and hardware. arXiv preprint arXiv:1812.00332 (2018)."},{"key":"e_1_3_2_2_8_1","volume-title":"Microsoft coco captions: Data collection and evaluation server. arXiv preprint arXiv:1504.00325","author":"Chen Xinlei","year":"2015","unstructured":"Xinlei Chen , Hao Fang , Tsung-Yi Lin , Ramakrishna Vedantam , Saurabh Gupta , Piotr Doll\u00e1r , and C Lawrence Zitnick . 2015. Microsoft coco captions: Data collection and evaluation server. arXiv preprint arXiv:1504.00325 ( 2015 ). Xinlei Chen, Hao Fang, Tsung-Yi Lin, Ramakrishna Vedantam, Saurabh Gupta, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2015. Microsoft coco captions: Data collection and evaluation server. arXiv preprint arXiv:1504.00325 (2015)."},{"key":"e_1_3_2_2_9_1","volume-title":"Faisal Ahmed, Zhe Gan, Yu Cheng, and Jingjing Liu.","author":"Chen Yen-Chun","year":"2019","unstructured":"Yen-Chun Chen , Linjie Li , Licheng Yu , Ahmed El Kholy , Faisal Ahmed, Zhe Gan, Yu Cheng, and Jingjing Liu. 2019 . Uniter : Learning universal image-text representations. arXiv preprint arXiv:1909.11740 (2019). Yen-Chun Chen, Linjie Li, Licheng Yu, Ahmed El Kholy, Faisal Ahmed, Zhe Gan, Yu Cheng, and Jingjing Liu. 2019. Uniter: Learning universal image-text representations. arXiv preprint arXiv:1909.11740 (2019)."},{"key":"e_1_3_2_2_10_1","volume-title":"Fairnas: Rethinking evaluation fairness of weight sharing neural architecture search. arXiv preprint arXiv:1907.01845","author":"Chu Xiangxiang","year":"2019","unstructured":"Xiangxiang Chu , Bo Zhang , Ruijun Xu , and Jixiang Li . 2019 . Fairnas: Rethinking evaluation fairness of weight sharing neural architecture search. arXiv preprint arXiv:1907.01845 (2019). Xiangxiang Chu, Bo Zhang, Ruijun Xu, and Jixiang Li. 2019. Fairnas: Rethinking evaluation fairness of weight sharing neural architecture search. arXiv preprint arXiv:1907.01845 (2019)."},{"key":"e_1_3_2_2_11_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Conference of the NAACL-HLT. 4171--4186","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 Conference of the NAACL-HLT. 4171--4186 . Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Conference of the NAACL-HLT. 4171--4186."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/6046.865479"},{"key":"e_1_3_2_2_13_1","volume-title":"Jamie Ryan Kiros, and Sanja Fidler","author":"Faghri Fartash","year":"2017","unstructured":"Fartash Faghri , David J Fleet , Jamie Ryan Kiros, and Sanja Fidler . 2017 . Vse+: Improving visual-semantic embeddings with hard negatives. arXiv preprint arXiv:1707.05612 (2017). Fartash Faghri, David J Fleet, Jamie Ryan Kiros, and Sanja Fidler. 2017. Vse+: Improving visual-semantic embeddings with hard negatives. arXiv preprint arXiv:1707.05612 (2017)."},{"key":"e_1_3_2_2_14_1","volume-title":"Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding. Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Fukui Akira","year":"2016","unstructured":"Akira Fukui , Dong Huk Park , Daylen Yang , Anna Rohrbach , Trevor Darrell , and Marcus Rohrbach . 2016 . Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding. Conference on Empirical Methods in Natural Language Processing (EMNLP) (2016). Akira Fukui, Dong Huk Park, Daylen Yang, Anna Rohrbach, Trevor Darrell, and Marcus Rohrbach. 2016. Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding. Conference on Empirical Methods in Natural Language Processing (EMNLP) (2016)."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00680"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00720"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_3_2_2_18_1","volume-title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering. IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Goyal Yash","year":"2017","unstructured":"Yash Goyal , Tejas Khot , Douglas Summers-Stay , Dhruv Batra , and Devi Parikh . 2017 . Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017). Yash Goyal, Tejas Khot, Douglas Summers-Stay, Dhruv Batra, and Devi Parikh. 2017. Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00378"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.470"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00645"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"e_1_3_2_2_26_1","unstructured":"Jin-Hwa Kim Jaehyun Jun and Byoung-Tak Zhang. 2018. Bilinear attention networks. In Advances in Neural Information Processing Systems (NIPS). 1564--1574.  Jin-Hwa Kim Jaehyun Jun and Byoung-Tak Zhang. 2018. Bilinear attention networks. In Advances in Neural Information Processing Systems (NIPS). 1564--1574."},{"key":"e_1_3_2_2_27_1","volume-title":"Hadamard Product for Low-rank Bilinear Pooling. In International Conference on Learning Representation (ICLR).","author":"Kim Jin-Hwa","year":"2017","unstructured":"Jin-Hwa Kim , Kyoung Woon On , Woosang Lim , Jeonghee Kim , Jung-Woo Ha , and Byoung-Tak Zhang . 2017 . Hadamard Product for Low-rank Bilinear Pooling. In International Conference on Learning Representation (ICLR). Jin-Hwa Kim, Kyoung Woon On, Woosang Lim, Jeonghee Kim, Jung-Woo Ha, and Byoung-Tak Zhang. 2017. Hadamard Product for Low-rank Bilinear Pooling. In International Conference on Learning Representation (ICLR)."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"e_1_3_2_2_30_1","volume-title":"Visualbert: A simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557","author":"Li Liunian Harold","year":"2019","unstructured":"Liunian Harold Li , Mark Yatskar , Da Yin , Cho-Jui Hsieh , and Kai-Wei Chang . 2019 . Visualbert: A simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557 (2019). Liunian Harold Li, Mark Yatskar, Da Yin, Cho-Jui Hsieh, and Kai-Wei Chang. 2019. Visualbert: A simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557 (2019)."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_2_32_1","volume-title":"Darts: Differentiable architecture search. arXiv preprint arXiv:1806.09055","author":"Liu Hanxiao","year":"2018","unstructured":"Hanxiao Liu , Karen Simonyan , and Yiming Yang . 2018 . Darts: Differentiable architecture search. arXiv preprint arXiv:1806.09055 (2018). Hanxiao Liu, Karen Simonyan, and Yiming Yang. 2018. Darts: Differentiable architecture search. arXiv preprint arXiv:1806.09055 (2018)."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"e_1_3_2_2_34_1","volume-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In Advances in Neural Information Processing Systems (NIPS). 13--23.","author":"Lu Jiasen","year":"2019","unstructured":"Jiasen Lu , Dhruv Batra , Devi Parikh , and Stefan Lee . 2019 . Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In Advances in Neural Information Processing Systems (NIPS). 13--23. Jiasen Lu, Dhruv Batra, Devi Parikh, and Stefan Lee. 2019. Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In Advances in Neural Information Processing Systems (NIPS). 13--23."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00637"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00713"},{"key":"e_1_3_2_2_40_1","volume-title":"International Conference on Machine Learning (ICML). 4095--4104","author":"Pham Hieu","year":"2018","unstructured":"Hieu Pham , Melody Guan , Barret Zoph , Quoc Le , and Jeff Dean . 2018 . Efficient Neural Architecture Search via Parameters Sharing . In International Conference on Machine Learning (ICML). 4095--4104 . Hieu Pham, Melody Guan, Barret Zoph, Quoc Le, and Jeff Dean. 2018. Efficient Neural Architecture Search via Parameters Sharing. In International Conference on Machine Learning (ICML). 4095--4104."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"e_1_3_2_2_42_1","unstructured":"Shaoqing Ren Kaiming He Ross Girshick and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. In Advances in neural information processing systems (NIPS). 91--99.  Shaoqing Ren Kaiming He Ross Girshick and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. In Advances in neural information processing systems (NIPS). 91--99."},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_49"},{"key":"e_1_3_2_2_44_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman . 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 ( 2014 ). Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_2_45_1","volume-title":"The evolved transformer. arXiv preprint arXiv:1901.11117","author":"So David R","year":"2019","unstructured":"David R So , Chen Liang , and Quoc V Le. 2019. The evolved transformer. arXiv preprint arXiv:1901.11117 ( 2019 ). David R So, Chen Liang, and Quoc V Le. 2019. The evolved transformer. arXiv preprint arXiv:1901.11117 (2019)."},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/2998574"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00444"},{"key":"e_1_3_2_2_49_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems (NIPS). 6000--6010.  Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems (NIPS). 6000--6010."},{"key":"e_1_3_2_2_50_1","volume-title":"CAMP: Cross-Modal Adaptive Message Passing for Text-Image Retrieval. In IEEE International Conference on Computer Vision (ICCV). 5764--5773","author":"Wang Zihao","year":"2019","unstructured":"Zihao Wang , Xihui Liu , Hongsheng Li , Lu Sheng , Junjie Yan , Xiaogang Wang , and Jing Shao . 2019 . CAMP: Cross-Modal Adaptive Message Passing for Text-Image Retrieval. In IEEE International Conference on Computer Vision (ICCV). 5764--5773 . Zihao Wang, Xihui Liu, Hongsheng Li, Lu Sheng, Junjie Yan, Xiaogang Wang, and Jing Shao. 2019. CAMP: Cross-Modal Adaptive Message Passing for Text-Image Retrieval. In IEEE International Conference on Computer Vision (ICCV). 5764--5773."},{"key":"e_1_3_2_2_51_1","volume-title":"International Conference on Machine Learning (ICML)","volume":"14","author":"Xu Kelvin","year":"2015","unstructured":"Kelvin Xu , Jimmy Ba , Ryan Kiros , Kyunghyun Cho , Aaron C Courville , Ruslan Salakhutdinov , Richard S Zemel , and Yoshua Bengio . 2015 . Show, Attend and Tell: Neural Image Caption Generation with Visual Attention .. In International Conference on Machine Learning (ICML) , Vol. 14 . 77--81. Kelvin Xu, Jimmy Ba, Ryan Kiros, Kyunghyun Cho, Aaron C Courville, Ruslan Salakhutdinov, Richard S Zemel, and Yoshua Bengio. 2015. Show, Attend and Tell: Neural Image Caption Generation with Visual Attention.. In International Conference on Machine Learning (ICML), Vol. 14. 77--81."},{"key":"e_1_3_2_2_52_1","volume-title":"Pc-darts: Partial channel connections for memory-efficient differentiable architecture search. arXiv preprint arXiv:1907.05737","author":"Xu Yuhui","year":"2019","unstructured":"Yuhui Xu , Lingxi Xie , Xiaopeng Zhang , Xin Chen , Guo-Jun Qi , Qi Tian , and Hongkai Xiong . 2019 . Pc-darts: Partial channel connections for memory-efficient differentiable architecture search. arXiv preprint arXiv:1907.05737 (2019). Yuhui Xu, Lingxi Xie, Xiaopeng Zhang, Xin Chen, Guo-Jun Qi, Qi Tian, and Hongkai Xiong. 2019. Pc-darts: Partial channel connections for memory-efficient differentiable architecture search. arXiv preprint arXiv:1907.05737 (2019)."},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.375"},{"key":"e_1_3_2_2_56_1","volume-title":"Deep Modular Co-Attention Networks for Visual Question Answering. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 6281--6290","author":"Yu Zhou","year":"2019","unstructured":"Zhou Yu , Jun Yu , Yuhao Cui , Dacheng Tao , and Qi Tian . 2019 . Deep Modular Co-Attention Networks for Visual Question Answering. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 6281--6290 . Zhou Yu, Jun Yu, Yuhao Cui, Dacheng Tao, and Qi Tian. 2019. Deep Modular Co-Attention Networks for Visual Question Answering. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 6281--6290."},{"key":"e_1_3_2_2_57_1","volume-title":"Multi-modal Factorized Bilinear Pooling with Co-Attention Learning for Visual Question Answering. IEEE International Conference on Computer Vision (ICCV) (2017)","author":"Yu Zhou","year":"2017","unstructured":"Zhou Yu , Jun Yu , Jianping Fan , and Dacheng Tao . 2017 b. Multi-modal Factorized Bilinear Pooling with Co-Attention Learning for Visual Question Answering. IEEE International Conference on Computer Vision (ICCV) (2017) , 1839--1848. Zhou Yu, Jun Yu, Jianping Fan, and Dacheng Tao. 2017b. Multi-modal Factorized Bilinear Pooling with Co-Attention Learning for Visual Question Answering. IEEE International Conference on Computer Vision (ICCV) (2017), 1839--1848."},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2817340"},{"key":"e_1_3_2_2_59_1","volume-title":"Rethinking Diversified and Discriminative Proposal Generation for Visual Grounding. International Joint Conference on Artificial Intelligence (IJCAI)","author":"Yu Zhou","year":"2018","unstructured":"Zhou Yu , Jun Yu , Chenchao Xiang , Zhou Zhao , Qi Tian , and Dacheng Tao . 2018 c. Rethinking Diversified and Discriminative Proposal Generation for Visual Grounding. International Joint Conference on Artificial Intelligence (IJCAI) (2018). Zhou Yu, Jun Yu, Chenchao Xiang, Zhou Zhao, Qi Tian, and Dacheng Tao. 2018c. Rethinking Diversified and Discriminative Proposal Generation for Visual Grounding. International Joint Conference on Artificial Intelligence (IJCAI) (2018)."},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/35.41402"},{"key":"e_1_3_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00391"},{"key":"e_1_3_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00437"},{"key":"e_1_3_2_2_63_1","volume-title":"Dual-path convolutional image-text embedding with instance loss. arXiv preprint arXiv:1711.05535","author":"Zheng Zhedong","year":"2017","unstructured":"Zhedong Zheng , Liang Zheng , Michael Garrett , Yi Yang , and Yi-Dong Shen . 2017. Dual-path convolutional image-text embedding with instance loss. arXiv preprint arXiv:1711.05535 ( 2017 ). Zhedong Zheng, Liang Zheng, Michael Garrett, Yi Yang, and Yi-Dong Shen. 2017. Dual-path convolutional image-text embedding with instance loss. arXiv preprint arXiv:1711.05535 (2017)."},{"key":"e_1_3_2_2_64_1","volume-title":"Neural architecture search with reinforcement learning. arXiv preprint arXiv:1611.01578","author":"Zoph Barret","year":"2016","unstructured":"Barret Zoph and Quoc V Le. 2016. Neural architecture search with reinforcement learning. arXiv preprint arXiv:1611.01578 ( 2016 ). Barret Zoph and Quoc V Le. 2016. Neural architecture search with reinforcement learning. arXiv preprint arXiv:1611.01578 (2016)."},{"key":"e_1_3_2_2_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"}],"event":{"name":"MM '20: The 28th ACM International Conference on Multimedia","location":"Seattle WA USA","acronym":"MM '20","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 28th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3413977","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3394171.3413977","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:32:07Z","timestamp":1750195927000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3413977"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,12]]},"references-count":65,"alternative-id":["10.1145\/3394171.3413977","10.1145\/3394171"],"URL":"https:\/\/doi.org\/10.1145\/3394171.3413977","relation":{},"subject":[],"published":{"date-parts":[[2020,10,12]]},"assertion":[{"value":"2020-10-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}