{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T15:32:27Z","timestamp":1761060747698,"version":"3.37.3"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2019,2,13]],"date-time":"2019-02-13T00:00:00Z","timestamp":1550016000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,2,13]],"date-time":"2019-02-13T00:00:00Z","timestamp":1550016000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100004731","name":"Natural Science Foundation of Zhejiang Province","doi-asserted-by":"publisher","award":["LR19F020002","LZ17F020001"],"award-info":[{"award-number":["LR19F020002","LZ17F020001"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61572431"],"award-info":[{"award-number":["61572431"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key R&D Program of Zhejiang Province","award":["2018C01006"],"award-info":[{"award-number":["2018C01006"]}]},{"name":"Chinese Knowledge Center for Engineering Sciences and Technology"},{"name":"Joint Research Program of ZJU & Hikvision Research Institute"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"published-print":{"date-parts":[[2020,10]]},"DOI":"10.1007\/s11063-019-10003-1","type":"journal-article","created":{"date-parts":[[2019,2,13]],"date-time":"2019-02-13T16:04:53Z","timestamp":1550073893000},"page":"993-1003","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Hierarchical Temporal Fusion of Multi-grained Attention Features for Video Question Answering"],"prefix":"10.1007","volume":"52","author":[{"given":"Shaoning","family":"Xiao","sequence":"first","affiliation":[]},{"given":"Yimeng","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yunan","family":"Ye","sequence":"additional","affiliation":[]},{"given":"Long","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Shiliang","family":"Pu","sequence":"additional","affiliation":[]},{"given":"Zhou","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Jian","family":"Shao","sequence":"additional","affiliation":[]},{"given":"Jun","family":"Xiao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,2,13]]},"reference":[{"key":"10003_CR1","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1007\/s11263-016-0966-6","volume":"123","author":"A Agrawal","year":"2017","unstructured":"Agrawal A, Lu J, Antol S, Mitchell M, Zitnick CL, Parikh D, Batra D (2017) VQA: visual question answering. Int J Compu Vis 123:431","journal-title":"Int J Compu Vis"},{"key":"10003_CR2","doi-asserted-by":"crossref","unstructured":"Kafle K, Kanan C (2016) Answer-type prediction for visual question answering. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp 4976\u20134984","DOI":"10.1109\/CVPR.2016.538"},{"key":"10003_CR3","doi-asserted-by":"crossref","unstructured":"Teney D, Liu L, Van Den Hengel A (2017) Graph-structured representations for visual question answering. In: IEEE conference on computer vision and pattern recognition, pp 3233\u20133241","DOI":"10.1109\/CVPR.2017.344"},{"key":"10003_CR4","first-page":"21","volume":"2016","author":"Z Yang","year":"2015","unstructured":"Yang Z, He X, Gao J, Deng L, Smola A (2015) Stacked attention networks for image question answering. CVPR 2016:21\u201329","journal-title":"CVPR"},{"key":"10003_CR5","doi-asserted-by":"publisher","first-page":"320","DOI":"10.1016\/j.cviu.2017.06.005","volume":"163","author":"K Kafle","year":"2017","unstructured":"Kafle K, Kanan C (2017) Visual question answering: datasets, algorithms, and future challenges. Comput Vis Image Underst 163:320","journal-title":"Comput Vis Image Underst"},{"key":"10003_CR6","first-page":"4187","volume":"2017","author":"D Yu","year":"2017","unstructured":"Yu D, Fu J, Mei T, Rui Y (2017) Multi-level attention networks for visual question answering. CVPR 2017:4187\u20134195","journal-title":"CVPR"},{"key":"10003_CR7","doi-asserted-by":"crossref","unstructured":"Zhang H, Zha Z, Yang Y (2013) Attribute-augmented semantic hierarchy: towards bridging semantic gap and intention gap in image retrieval. In: Proceedings of the 21st ACM international conference on multimedia, pp 33\u201342","DOI":"10.1145\/2502081.2502093"},{"issue":"9","key":"10003_CR8","doi-asserted-by":"publisher","first-page":"4128","DOI":"10.1109\/TIP.2017.2710635","volume":"26","author":"R Hong","year":"2017","unstructured":"Hong R, Li L, Cai J (2017) Coherent semantic-visual indexing for large-scale image retrieval in the cloud. IEEE Trans Image Process 26(9):4128\u20134138","journal-title":"IEEE Trans Image Process"},{"key":"10003_CR9","doi-asserted-by":"crossref","unstructured":"Ye Y, Zhao Z, Li Y, Chen L, Xiao J, Zhuang Y (2017) Video question answering via attribute-augmented attention network learning. In Proceedings of the 40th international ACM SIGIR conference on research and development in information retrieval. ACM, Cambridge, pp 829\u2013832","DOI":"10.1145\/3077136.3080655"},{"key":"10003_CR10","doi-asserted-by":"crossref","unstructured":"Xu D, Zhao Z, Xiao J, Wu F, Zhang H, He X, Zhuang Y (2017) Video question answering via gradually refined attention over appearance and motion. In: ACM multimedia conference, pp 1645\u20131653","DOI":"10.1145\/3123266.3123427"},{"key":"10003_CR11","doi-asserted-by":"crossref","unstructured":"Zhao Z, Yang Q, Cai D, He X, Zhuang Y (2017) Video question answering via hierarchical spatio-temporal attention networks. In: IJCAI international joint conference on artificial intelligence, pp 3518\u20133524","DOI":"10.24963\/ijcai.2017\/492"},{"issue":"3","key":"10003_CR12","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1007\/s11263-017-1033-7","volume":"124","author":"L Zhu","year":"2017","unstructured":"Zhu L, Xu Z, Yang Y, Hauptmann AG (2017) Uncovering the temporal context for video question answering. Int J Comput Vis 124(3):409\u2013421","journal-title":"Int J Comput Vis"},{"issue":"4","key":"10003_CR13","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1109\/MMUL.2011.53","volume":"19","author":"R Hong","year":"2012","unstructured":"Hong R, Wang M, Li G (2012) Multimedia question answering. IEEE Multimedia 19(4):72\u201378","journal-title":"IEEE Multimedia"},{"key":"10003_CR14","doi-asserted-by":"crossref","unstructured":"Song J, Gao L, Guo Z, Liu W, Zhang D, Shen HT (2017) Hierarchical LSTM with adjusted temporal attention for video captioning. In: IJCAI international joint conference on artificial intelligence, pp 2737\u20132743","DOI":"10.24963\/ijcai.2017\/381"},{"key":"10003_CR15","unstructured":"Xu K, Ba J, Kiros R, Cho K, Courville A, Salakhutdinov R, Zemel RS, Bengio Y (2015) Show, attend and tell: neural image caption generation with visual attention. In: ICML"},{"key":"10003_CR16","doi-asserted-by":"crossref","unstructured":"Yao L, Torabi A, Cho K, Ballas N, Pal C, Larochelle H, Courville A (2015) Describing videos by exploiting temporal structure. In: ICCV","DOI":"10.1109\/ICCV.2015.512"},{"key":"10003_CR17","doi-asserted-by":"crossref","unstructured":"Chen L, Zhang H, Xiao J, Nie L, Shao J, Liu W, Chua T-S (2017) SCA-CNN: spatial and channel-wise attention in convolutional networks for image captioning. In: CVPR","DOI":"10.1109\/CVPR.2017.667"},{"key":"10003_CR18","unstructured":"Chen K, Wang J, Chen L-C, Gao H, Xu W, Nevatia R (2016) ABCCNN: an attention based convolutional neural network for visual question answering. arXiv preprint arXiv:1511.05960"},{"key":"10003_CR19","doi-asserted-by":"crossref","unstructured":"Yang Z, He X, Gao J, Deng L, Smola A (2016) Stacked attention networks for image question answering. In: CVPR","DOI":"10.1109\/CVPR.2016.10"},{"key":"10003_CR20","doi-asserted-by":"crossref","unstructured":"Xu H, Saenko K (2016) Ask, attend and answer: exploring question- guided spatial attention for visual question answering. In: ECCV","DOI":"10.1007\/978-3-319-46478-7_28"},{"key":"10003_CR21","unstructured":"Zeng K-H, Chen T-H, Chuang C-Y, Liao, Y-H, Niebles JC, Sun M (2016) Leveraging video descriptions to learn video question answering. arXiv preprint arXiv:1611.04021"},{"key":"10003_CR22","unstructured":"Backhouse J (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556"},{"issue":"8","key":"10003_CR23","doi-asserted-by":"publisher","first-page":"1839","DOI":"10.1109\/TCSVT.2017.2682196","volume":"28","author":"S Zhao","year":"2018","unstructured":"Zhao S, Liu Y, Han Y (2018) Pooling the convolutional layers in deep convnets for video action recognition. IEEE Trans Circ Syst Video Technol 28(8):1839\u20131849","journal-title":"IEEE Trans Circ Syst Video Technol"},{"issue":"2","key":"10003_CR24","doi-asserted-by":"publisher","first-page":"554","DOI":"10.1016\/j.neucom.2014.06.085","volume":"151","author":"Z Gao","year":"2015","unstructured":"Gao Z, Zhang H, Xu G (2015) Multi-perspective and multi-modality joint representation and recognition model for 3D action recognition. Neurocomputing 151(2):554\u2013564","journal-title":"Neurocomputing"},{"key":"10003_CR25","doi-asserted-by":"crossref","unstructured":"Xiao S, Li Y, Ye Y (2018) Video question answering via multi-granularity temporal attention network learning. In: ICIMCS","DOI":"10.1145\/3240876.3240885"},{"key":"10003_CR26","unstructured":"Lu J, Yang J, Batra D, Parikh D (2016) Hierarchical question-image co-attention for visual question answering. arXiv Preprint arXiv:1606.00061"},{"key":"10003_CR27","doi-asserted-by":"crossref","unstructured":"Heilbron FC, Escorcia V, Ghanem B, Niebles JC (2015) Activitynet: a large-scale video benchmark for human activity understanding. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition, pp. 961\u2013970","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"10003_CR28","doi-asserted-by":"crossref","unstructured":"Kong T, Yao A, Chen Y, Sun F (2016) Hypernet: towards accurate region proposal generation and joint object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 845\u2013853","DOI":"10.1109\/CVPR.2016.98"},{"issue":"6","key":"10003_CR29","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren S, He K, Girshick R, Sun J (2017) Faster R-CNN: towards real-time object detection with. IEEE Trans Pattern Anal Mach Intel 39(6):1137\u20131149","journal-title":"IEEE Trans Pattern Anal Mach Intel"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11063-019-10003-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-019-10003-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-019-10003-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,13]],"date-time":"2023-09-13T16:22:20Z","timestamp":1694622140000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11063-019-10003-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,2,13]]},"references-count":29,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2020,10]]}},"alternative-id":["10003"],"URL":"https:\/\/doi.org\/10.1007\/s11063-019-10003-1","relation":{},"ISSN":["1370-4621","1573-773X"],"issn-type":[{"type":"print","value":"1370-4621"},{"type":"electronic","value":"1573-773X"}],"subject":[],"published":{"date-parts":[[2019,2,13]]},"assertion":[{"value":"13 February 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}