{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T12:38:11Z","timestamp":1780317491771,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":40,"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":[{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["BX2021055 and 2021M690027"],"award-info":[{"award-number":["BX2021055 and 2021M690027"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Sichuan Science and Technology Program, China","award":["2020YFS0057"],"award-info":[{"award-number":["2020YFS0057"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["ZYGX2019Z015"],"award-info":[{"award-number":["ZYGX2019Z015"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U20B2063"],"award-info":[{"award-number":["U20B2063"]}],"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":[[2021,10,17]]},"DOI":"10.1145\/3474085.3475193","type":"proceedings-article","created":{"date-parts":[[2021,10,18]],"date-time":"2021-10-18T10:23:20Z","timestamp":1634552600000},"page":"2871-2879","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":44,"title":["Progressive Graph Attention Network for Video Question Answering"],"prefix":"10.1145","author":[{"given":"Liang","family":"Peng","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China, chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuangji","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Bin","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guoqing","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2021,10,17]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"e_1_3_2_1_2_1","volume-title":"Nicolas Thome, and Matthieu Cord.","author":"Ben-Younes Hedi","year":"2017"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018110"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123391"},{"key":"e_1_3_2_1_5_1","volume-title":"Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio.","author":"Cho Kyunghyun","year":"2014"},{"key":"e_1_3_2_1_6_1","unstructured":"Chenyou Fan Xiaofan Zhang Shu Zhang Wensheng Wang Chi Zhang and Heng Huang. 2019. Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answering. In CVPR. 1999--2007.  Chenyou Fan Xiaofan Zhang Shu Zhang Wensheng Wang Chi Zhang and Heng Huang. 2019. Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answering. In CVPR. 1999--2007."},{"key":"e_1_3_2_1_7_1","volume-title":"Daylen Yang, Anna Rohrbach, Trevor Darrell, and Marcus Rohrbach.","author":"Fukui Akira","year":"2016"},{"key":"e_1_3_2_1_8_1","unstructured":"Jiyang Gao Runzhou Ge Kan Chen and Ram Nevatia. 2018. Motion-appearance Co-memory Networks for Video Question Answering. In CVPR. 6576--6585.  Jiyang Gao Runzhou Ge Kan Chen and Ram Nevatia. 2018. Motion-appearance Co-memory Networks for Video Question Answering. In CVPR. 6576--6585."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","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. In CVPR. 6904--6913.  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. In CVPR. 6904--6913.","DOI":"10.1109\/CVPR.2017.670"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"K. Hara H. Kataoka and Y. Satoh. 2018. Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?. In CVPR. 6546--6555.  K. Hara H. Kataoka and Y. Satoh. 2018. Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?. In CVPR. 6546--6555.","DOI":"10.1109\/CVPR.2018.00685"},{"key":"e_1_3_2_1_11_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In CVPR. 770--778.  Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In CVPR. 770--778."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6737"},{"key":"e_1_3_2_1_14_1","volume-title":"Tgif-qa: Toward Spatio-temporal Reasoning in Visual Question Answering. In CVPR. 2758--2766.","author":"Jang Yunseok","year":"2017"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6766"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6767"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351065"},{"key":"e_1_3_2_1_18_1","unstructured":"Jin-Hwa Kim Kyoung-Woon On Jeonghee Kim Jung-Woo Ha and Byoung-Tak Zhang. 2017. Hadamard Product for Low-rank Bilinear Pooling. In ICLR. 1--10.  Jin-Hwa Kim Kyoung-Woon On Jeonghee Kim Jung-Woo Ha and Byoung-Tak Zhang. 2017. Hadamard Product for Low-rank Bilinear Pooling. In ICLR. 1--10."},{"key":"e_1_3_2_1_19_1","unstructured":"Thao Minh Le Vuong Le Svetha Venkatesh and Truyen Tran. 2020. Hierarchical Conditional Relation Networks for Video Question Answering. In CVPR. 9972--9981.  Thao Minh Le Vuong Le Svetha Venkatesh and Truyen Tran. 2020. Hierarchical Conditional Relation Networks for Video Question Answering. In CVPR. 9972--9981."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157382.3157618"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350971"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018658"},{"key":"e_1_3_2_1_23_1","volume-title":"TGIF: A New Aataset and Benchmark on Animated GIF Description. In CVPR. 4641--4650.","author":"Li Yuncheng","year":"2016"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.9"},{"key":"e_1_3_2_1_25_1","volume-title":"2020 a. MRA-Net: Improving VQA via Multi-modal Relation Attention Network","author":"Peng Liang","year":"2020"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350925"},{"key":"e_1_3_2_1_27_1","volume-title":"2020 b. Answer Again: Imporving VQA with Cascaded-Answering Model","author":"Peng Liang","year":"2020"},{"key":"e_1_3_2_1_28_1","volume-title":"Glove: Global Vectors for Word Representation. In EMNLP. 1532--1543.","author":"Pennington Jeffrey","year":"2014"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.5555\/2969239.2969250"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295250"},{"key":"e_1_3_2_1_31_1","volume-title":"Very Deep Convolutional Networks for Large-scale Image Recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Damien Teney Peter Anderson Xiaodong He and Anton van den Hengel. 2018. Tips and Tricks for Visual Question Answering: Learnings From the 2017 Challenge. In CVPR. 4223--4232.  Damien Teney Peter Anderson Xiaodong He and Anton van den Hengel. 2018. Tips and Tricks for Visual Question Answering: Learnings From the 2017 Challenge. In CVPR. 4223--4232.","DOI":"10.1109\/CVPR.2018.00444"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01425-9"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3088863"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","unstructured":"Zichao Yang Xiaodong He Jianfeng Gao Li Deng and Alex Smola. 2016. Stacked Attention Networks for Image Question Answering. In CVPR. 21--29.  Zichao Yang Xiaodong He Jianfeng Gao Li Deng and Alex Smola. 2016. Stacked Attention Networks for Image Question Answering. In CVPR. 21--29.","DOI":"10.1109\/CVPR.2016.10"},{"key":"e_1_3_2_1_37_1","unstructured":"Dongfei Yu Jianlong Fu Tao Mei and Yong Rui. 2017a. Multi-level Attention Networks for Visual Question Answering. In CVPR. 4709--4717.  Dongfei Yu Jianlong Fu Tao Mei and Yong Rui. 2017a. Multi-level Attention Networks for Visual Question Answering. In CVPR. 4709--4717."},{"key":"e_1_3_2_1_38_1","unstructured":"Zhou Yu Jun Yu Jianping Fan and Dacheng Tao. 2017b. Multi-modal Factorized Bilinear Pooling with Co-Attention Learning for Visual Question Answering. In ICCV. 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. In ICCV. 1839--1848."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Junchao Zhang and Yuxin Peng. 2019. Object-aware Aggregation with Bidirectional Temporal Graph for Video Captioning. In CVPR. 8327--8336.  Junchao Zhang and Yuxin Peng. 2019. Object-aware Aggregation with Bidirectional Temporal Graph for Video Captioning. In CVPR. 8327--8336.","DOI":"10.1109\/CVPR.2019.00852"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"Mingxing Zhang Yang Yang Hanwang Zhang Yanli Ji Ning Xie and Heng Tao Shen. 2017. Deep Semantic Indexing using Convolutional Localization Network with Region-based Visual Attention for Image Database. In ADC. 261--272.  Mingxing Zhang Yang Yang Hanwang Zhang Yanli Ji Ning Xie and Heng Tao Shen. 2017. Deep Semantic Indexing using Convolutional Localization Network with Region-based Visual Attention for Image Database. In ADC. 261--272.","DOI":"10.1007\/978-3-319-68155-9_20"}],"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\/3474085.3475193","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3474085.3475193","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:48:47Z","timestamp":1750193327000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475193"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":40,"alternative-id":["10.1145\/3474085.3475193","10.1145\/3474085"],"URL":"https:\/\/doi.org\/10.1145\/3474085.3475193","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"}}]}}