{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T16:00:49Z","timestamp":1772208049551,"version":"3.50.1"},"reference-count":81,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,6]]},"DOI":"10.1109\/cvpr.2019.01283","type":"proceedings-article","created":{"date-parts":[[2020,1,9]],"date-time":"2020-01-09T21:06:13Z","timestamp":1578603973000},"page":"12540-12550","source":"Crossref","is-referenced-by-count":51,"title":["A Simple Baseline for Audio-Visual Scene-Aware Dialog"],"prefix":"10.1109","author":[{"given":"Idan","family":"Schwartz","sequence":"first","affiliation":[{"name":"Technion"}]},{"given":"Alexander G.","family":"Schwing","sequence":"additional","affiliation":[{"name":"UIUC"}]},{"given":"Tamir","family":"Hazan","sequence":"additional","affiliation":[{"name":"Technion"}]}],"member":"263","reference":[{"key":"ref73","article-title":"Dynamic memory networks for visual and textual question answering","author":"xiong","year":"2016","journal-title":"Proc ICML"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00639"},{"key":"ref71","article-title":"Are you talking to me? reasoned visual dialog generation through adversarial learning","author":"wu","year":"2017"},{"key":"ref70","article-title":"Temporal segment networks: Towards good practices for deep action recognition","author":"wang","year":"2016","journal-title":"Proc ECCV"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref74","article-title":"Ask, attend and answer: Exploring question-guided spatial attention for visual question answering","author":"xu","year":"2016","journal-title":"Proc ECCV"},{"key":"ref39","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"Proc ECCV"},{"key":"ref75","article-title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","author":"xu","year":"2015","journal-title":"Proc ICML"},{"key":"ref38","article-title":"Rouge: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Workshop on Text Summarization Branches Out"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.496"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.233"},{"key":"ref33","article-title":"Hadamard product for low-rank bilinear pooling","author":"kim","year":"2016"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.494"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.10.011"},{"key":"ref36","article-title":"Visual Question Generation as Dual Task of Visual Question Answering","author":"li","year":"2017"},{"key":"ref35","article-title":"Visual coreference resolution in visual dialog using neural module networks","author":"kottur","year":"2018","journal-title":"Proc ECCV"},{"key":"ref34","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00790"},{"key":"ref62","article-title":"Two-Stream Convolutional Networks for Action Recognition in Videos","author":"simonyan","year":"2014","journal-title":"Proc NIPS"},{"key":"ref61","article-title":"Hollywood in homes: Crowdsourcing data collection for activity understanding","author":"sigurdsson","year":"2016","journal-title":"Proc ECCV"},{"key":"ref63","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc ICLR"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.575"},{"key":"ref64","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc NIPS"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00603"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref67","article-title":"Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models","author":"vijayakumar","year":"2018","journal-title":"Proc AAAI"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref69","article-title":"Diverse and Accurate Image Description Using a Variational Auto-Encoder with an Additive Gaussian Encoding Space","author":"wang","year":"2017","journal-title":"Proc NIPS"},{"key":"ref2","article-title":"Audio Visual Scene-Aware Dialog (AVSD) Challenge at DSTC7","author":"alamri","year":"2018"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00774"},{"key":"ref20","article-title":"Learning to Separate Object Sounds by Watching Unlabeled Video","author":"gao","year":"2018","journal-title":"Proc CVPR Workshop"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref21","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proc AISTATS"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref26","article-title":"Revisiting Visual Question Answering Baselines","author":"jabri","year":"2016","journal-title":"Proc ECCV"},{"key":"ref25","article-title":"End-to-End Audio Visual Scene-Aware Dialog using Multimodal Attention-Based Video Features","author":"hori","year":"2018"},{"key":"ref50","article-title":"Straight to the Facts: Learning Knowledge Base Retrieval for Factual Visual Question Answering","author":"narasimhan","year":"2018","journal-title":"Proc ECCV"},{"key":"ref51","article-title":"Audio-Visual Scene Analysis with Self-Supervised Multisensory Features","author":"owens","year":"2018","journal-title":"Proc ECCV"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.499"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00214"},{"key":"ref57","article-title":"High-Order Attention Models for Visual Question Answering","author":"schwartz","year":"2017","journal-title":"Proc NIPS"},{"key":"ref56","article-title":"A simple neural network module for relational reasoning","author":"santoro","year":"2017","journal-title":"Proc NIPS"},{"key":"ref55","article-title":"Cmu sinbadas submission for the dstc7 avsd challenge","author":"sanabria","year":"2019","journal-title":"DSTC7 workshop at AAAI"},{"key":"ref54","article-title":"Exploring models and data for image question answering","author":"ren","year":"2015","journal-title":"Proc NIPS"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1083-5"},{"key":"ref10","article-title":"Diverse and Coherent Paragraph Generation from Images","author":"chatterjee","year":"2018","journal-title":"Proc ECCV"},{"key":"ref11","article-title":"Mind’s eye: A recurrent visual representation for image caption generation","author":"chen","year":"2015","journal-title":"Proc CVPR"},{"key":"ref40","article-title":"Best of both worlds: Transferring knowledge from discriminative learning to a generative visual dialog model","author":"lu","year":"2017","journal-title":"Proc NIPS"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1092"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.121"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.321"},{"key":"ref15","article-title":"Diverse and Controllable Image Captioning with Part-of-Speech Guidance","author":"deshpande","year":"2019","journal-title":"Proc CVPR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.540"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.1145\/3197517.3201357","article-title":"Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation","author":"ephrat","year":"2018","journal-title":"Proc Siggraph"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref19","article-title":"Are you talking to a machine? Dataset and Methods for Multilingual Image Question Answering","author":"gao","year":"2015","journal-title":"Proc NIPS"},{"key":"ref80","article-title":"Temporal relational reasoning in videos","author":"zhou","year":"2017"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00583"},{"key":"ref3","article-title":"Deep compositional question answering with neural module networks","author":"andreas","year":"2016","journal-title":"Proc CVPR"},{"key":"ref6","article-title":"Soundnet: Learning sound representations from unlabeled video","author":"aytar","year":"2016","journal-title":"Proc NIPS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref7","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","author":"banerjee","year":"2005","journal-title":"Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization"},{"key":"ref49","article-title":"Out of the Box: Reasoning with Graph Convolution Nets for Factual Visual Question Answering","author":"narasimhan","year":"2018","journal-title":"Proc NIPS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref46","article-title":"FlipDial: A Generative Model for Two-Way Visual Dialogue","author":"massiceti","year":"2018"},{"key":"ref45","article-title":"Deep Captioning with Multimodal Recurrent Neural Networks (m-rnn)","author":"mao","year":"2015","journal-title":"Proc ICLR"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1170"},{"key":"ref47","article-title":"Image-grounded conversations: Multimodal context for natural question and response generation","author":"mostafazadeh","year":"2017"},{"key":"ref42","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v30i1.10442","article-title":"Learning to answer questions from image using convolutional neural network","author":"ma","year":"2016","journal-title":"Proc AAAI"},{"key":"ref41","article-title":"Hierarchical question-image co-attention for visual question answering","author":"lu","year":"2016","journal-title":"Proc NIPS"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.9"},{"key":"ref43","article-title":"A Multi-World Approach to Question Answering about Real-World Scenes based on Uncertain Input","author":"malinowski","year":"2014","journal-title":"Proc NIPS"}],"event":{"name":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","location":"Long Beach, CA, USA","start":{"date-parts":[[2019,6,15]]},"end":{"date-parts":[[2019,6,20]]}},"container-title":["2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8938205\/8953184\/08953318.pdf?arnumber=8953318","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:23:10Z","timestamp":1755800590000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8953318\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6]]},"references-count":81,"URL":"https:\/\/doi.org\/10.1109\/cvpr.2019.01283","relation":{},"subject":[],"published":{"date-parts":[[2019,6]]}}}