{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T22:34:16Z","timestamp":1783636456988,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Project of Qingdao Postdoctoral Applied Research"},{"name":"The National Natural Science Foundation of China","award":["No.: 61802231; No.: 62006142"],"award-info":[{"award-number":["No.: 61802231; No.: 62006142"]}]},{"name":"The Shandong Provincial Natural Science Foundation","award":["No.: ZR2019QF001; No.:ZR2019JQ23"],"award-info":[{"award-number":["No.: ZR2019QF001; No.:ZR2019JQ23"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,10,17]]},"DOI":"10.1145\/3474085.3475609","type":"proceedings-article","created":{"date-parts":[[2021,10,18]],"date-time":"2021-10-18T06:57:34Z","timestamp":1634540254000},"page":"4528-4536","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Focal and Composed Vision-semantic Modeling for Visual Question Answering"],"prefix":"10.1145","author":[{"given":"Yudong","family":"Han","sequence":"first","affiliation":[{"name":"Shandong University, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yangyang","family":"Guo","sequence":"additional","affiliation":[{"name":"Shandong University, Qingdao, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianhua","family":"Yin","sequence":"additional","affiliation":[{"name":"Shandong University, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng","family":"Liu","sequence":"additional","affiliation":[{"name":"Shandong Jianzhu University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yupeng","family":"Hu","sequence":"additional","affiliation":[{"name":"Shandong University, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liqiang","family":"Nie","sequence":"additional","affiliation":[{"name":"Shandong University, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2021,10,17]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Don't Just Assume","author":"Agrawal Aishwarya"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","volume-title":"Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering","author":"Anderson Peter","DOI":"10.1109\/CVPR.2018.00636"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"e_1_3_2_1_4_1","volume-title":"Deep Attention Neural Tensor Network for Visual Question Answering","author":"Bai Yalong"},{"key":"e_1_3_2_1_5_1","volume-title":"MUTAN: Multimodal Tucker Fusion for Visual Question Answering","author":"Hedi","year":"2017"},{"key":"e_1_3_2_1_6_1","volume-title":"BLOCK: Bilinear Superdiagonal Fusion for Visual Question Answering and Visual Relationship Detection","author":"Hedi","year":"2019"},{"key":"e_1_3_2_1_7_1","volume-title":"MUREL: Multimodal Relational Reasoning for Visual Question Answering","author":"Cad\u00e8ne R\u00e9mi","year":"2019"},{"key":"e_1_3_2_1_8_1","volume-title":"IMRAM: Iterative Matching With Recurrent Attention Memory for Cross-Modal Image-Text Retrieval","author":"Chen Hui","year":"2020"},{"key":"e_1_3_2_1_9_1","unstructured":"Kyunghyun Cho Bart van Merrienboer \u00c7aglar G\u00fcl\u00e7ehre Dzmitry Bahdanau Fethi Bougares Holger Schwenk and Yoshua Bengio. 2014. Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. In EMNLP. ACL 1724--1734.  Kyunghyun Cho Bart van Merrienboer \u00c7aglar G\u00fcl\u00e7ehre Dzmitry Bahdanau Fethi Bougares Holger Schwenk and Yoshua Bengio. 2014. Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. In EMNLP. ACL 1724--1734."},{"key":"e_1_3_2_1_10_1","volume-title":"Dynamic Fusion With Intra- and Inter-Modality Attention Flow for Visual Question Answering","author":"Gao Peng"},{"key":"e_1_3_2_1_11_1","volume-title":"Multi-Modality Latent Interaction Network for Visual Question Answering","author":"Gao Peng"},{"key":"e_1_3_2_1_12_1","volume-title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","author":"Goyal Yash"},{"key":"e_1_3_2_1_13_1","volume-title":"Re-Attention for Visual Question Answering","author":"Guo Wenya"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331186"},{"key":"e_1_3_2_1_15_1","unstructured":"Yangyang Guo Liqiang Nie Zhiyong Cheng Feng Ji Ji Zhang and Alberto Del Bimbo. 2021. AdaVQA: Overcoming language priors with adapted margin cosine loss. In IJCAI. ACM.  Yangyang Guo Liqiang Nie Zhiyong Cheng Feng Ji Ji Zhang and Alberto Del Bimbo. 2021. AdaVQA: Overcoming language priors with adapted margin cosine loss. In IJCAI. ACM."},{"key":"e_1_3_2_1_16_1","volume-title":"Interpretable Visual Reasoning via Probabilistic Formulation Under Natural Supervision","author":"Han Xinzhe"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3073867"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3090521"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Qingbao Huang Jielong Wei Yi Cai Changmeng Zheng Junying Chen Ho-fung Leung and Qing Li. 2020. Aligned Dual Channel Graph Convolutional Network for Visual Question Answering. In ACL. ACL 7166--7176.  Qingbao Huang Jielong Wei Yi Cai Changmeng Zheng Junying Chen Ho-fung Leung and Qing Li. 2020. Aligned Dual Channel Graph Convolutional Network for Visual Question Answering. In ACL. ACL 7166--7176.","DOI":"10.18653\/v1\/2020.acl-main.642"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.5555\/3326943.3327087"},{"key":"e_1_3_2_1_21_1","volume-title":"Woosang Lim, Jeonghee Kim, Jung-Woo Ha, and Byoung-Tak Zhang.","author":"Kim Jin-Hwa","year":"2017"},{"key":"e_1_3_2_1_22_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2015"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_1_24_1","volume-title":"Relation-Aware Graph Attention Network for Visual Question Answering","author":"Li Linjie"},{"key":"e_1_3_2_1_25_1","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:1908.03557  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:1908.03557"},{"key":"e_1_3_2_1_26_1","volume-title":"Microsoft COCO: Common Objects in Context","author":"Lin Tsung-Yi"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2875363"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240549"},{"key":"e_1_3_2_1_29_1","volume-title":"Improving Referring Expression Grounding With Cross-Modal Attention-Guided Erasing","author":"Liu Xihui","year":"1950"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3454289"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157096.3157129"},{"key":"e_1_3_2_1_32_1","volume-title":"Dual Attention Networks for Multimodal Reasoning and Matching","author":"Nam Hyeonseob"},{"key":"e_1_3_2_1_33_1","volume-title":"Improved Fusion of Visual and Language Representations by Dense Symmetric Co-Attention for Visual Question Answering","author":"Nguyen Duy-Kien"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.5555\/3327757.3327926"},{"key":"e_1_3_2_1_35_1","volume-title":"MRANet: Improving VQA via Multi-modal Relation Attention Network. TPAMI","author":"Peng Liang","year":"2020"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350925"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.5555\/3326943.3327085"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.5555\/2969239.2969250"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295250"},{"key":"e_1_3_2_1_40_1","volume-title":"Conceptual Captions: A Cleaned, Hypernymed, Image Alt-text Dataset For Automatic Image Captioning. In ACL. ACL.","author":"Sharma Piyush","year":"2018"},{"key":"e_1_3_2_1_41_1","volume-title":"Where to Look: Focus Regions for Visual Question Answering","author":"Shih Kevin J."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"crossref","volume-title":"Answer Them All! Toward Universal Visual Question Answering Models","author":"Shrestha Robik","DOI":"10.1109\/CVPR.2019.01072"},{"key":"e_1_3_2_1_43_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.  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_44_1","volume-title":"Learning to Compose Dynamic Tree Structures for Visual Contexts","author":"Tang Kaihua"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_2_1_46_1","unstructured":"Petar Velickovic Guillem Cucurull Arantxa Casanova Adriana Romero Pietro Li\u00f2 and Yoshua Bengio. 2018. Graph Attention Networks. In ICLR.  Petar Velickovic Guillem Cucurull Arantxa Casanova Adriana Romero Pietro Li\u00f2 and Yoshua Bengio. 2018. Graph Attention Networks. In ICLR."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.5555\/3326943.3326969"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240513"},{"key":"e_1_3_2_1_49_1","volume-title":"Smola","author":"Yang Zichao","year":"2016"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"crossref","unstructured":"Zhuoqian Yang Zengchang Qin Jing Yu and Yue Hu. 2019. Scene Graph Reasoning with Prior Visual Relationship for Visual Question Answering. arXiv:1812.09681  Zhuoqian Yang Zengchang Qin Jing Yu and Yue Hu. 2019. Scene Graph Reasoning with Prior Visual Relationship for Visual Question Answering. arXiv:1812.09681","DOI":"10.1109\/ICIP40778.2020.9190771"},{"key":"e_1_3_2_1_51_1","unstructured":"Fisher Yu and Vladlen Koltun. 2016. Multi-Scale Context Aggregation by Dilated Convolutions. In ICLR.  Fisher Yu and Vladlen Koltun. 2016. Multi-Scale Context Aggregation by Dilated Convolutions. In ICLR."},{"key":"e_1_3_2_1_52_1","volume-title":"Deep Modular Co- Attention Networks for Visual Question Answering","author":"Yu Zhou"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2817340"},{"key":"e_1_3_2_1_55_1","unstructured":"Yan Zhang Jonathon S. Hare and Adam Pr\u00fcgel-Bennett. 2018. Learning to Count Objects in Natural Images for Visual Question Answering. In ICLR.  Yan Zhang Jonathon S. Hare and Adam Pr\u00fcgel-Bennett. 2018. Learning to Count Objects in Natural Images for Visual Question Answering. In ICLR."}],"event":{"name":"MM '21: ACM Multimedia Conference","location":"Virtual Event China","acronym":"MM '21","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 29th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475609","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3474085.3475609","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:48:24Z","timestamp":1750193304000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475609"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":55,"alternative-id":["10.1145\/3474085.3475609","10.1145\/3474085"],"URL":"https:\/\/doi.org\/10.1145\/3474085.3475609","relation":{},"subject":[],"published":{"date-parts":[[2021,10,17]]},"assertion":[{"value":"2021-10-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}