{"list":"other","total":66,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"1707.07998","title":"Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering","created":"2017-07-25","cited_by_count":1312},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"id":"1609.09430","title":"CNN Architectures for Large-Scale Audio Classification","created":"2016-09-29","cited_by_count":704},{"id":"1612.00563","title":"Self-critical Sequence Training for Image Captioning","created":"2016-12-02","cited_by_count":547},{"id":"1909.11059","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","created":"2019-09-24","cited_by_count":494},{"id":"1611.08669","title":"Visual Dialog","created":"2016-11-26","cited_by_count":377},{"id":"1912.08226","title":"Meshed-Memory Transformer for Image Captioning","created":"2019-12-17","cited_by_count":343},{"id":"1804.03641","title":"Audio-Visual Scene Analysis with Self-Supervised Multisensory Features","created":"2018-04-10","cited_by_count":335},{"id":"1606.00061","title":"Hierarchical Question-Image Co-Attention for Visual Question Answering","created":"2016-05-31","cited_by_count":278},{"id":"1511.02274","title":"Stacked Attention Networks for Image Question Answering","created":"2015-11-07","cited_by_count":273},{"id":"1603.03925","title":"Image Captioning with Semantic Attention","created":"2016-03-12","cited_by_count":260},{"id":"1804.03160","title":"The Sound of Pixels","created":"2018-04-09","cited_by_count":259},{"id":"1712.06651","title":"Objects that Sound","created":"2017-12-18","cited_by_count":256},{"id":"1612.01887","title":"Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning","created":"2016-12-06","cited_by_count":232},{"id":"1611.05594","title":"SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning","created":"2016-11-17","cited_by_count":219},{"id":"1804.00819","title":"End-to-End Dense Video Captioning with Masked Transformer","created":"2018-04-03","cited_by_count":214},{"id":"2003.14080","title":"X-Linear Attention Networks for Image Captioning","created":"2020-03-31","cited_by_count":198},{"id":"1803.03849","title":"Learning to Localize Sound Source in Visual Scenes","created":"2018-03-10","cited_by_count":189},{"id":"1912.04487","title":"Listen to Look: Action Recognition by Previewing Audio","created":"2019-12-10","cited_by_count":163},{"id":"2003.06576","title":"Counterfactual Samples Synthesizing for Robust Visual Question Answering","created":"2020-03-14","cited_by_count":153},{"id":"1901.09107","title":"Audio-Visual Scene-Aware Dialog","created":"2019-01-25","cited_by_count":123},{"id":"1804.01665","title":"Learning to Separate Object Sounds by Watching Unlabeled Video","created":"2018-04-05","cited_by_count":114},{"id":"1611.08481","title":"GuessWhat?! Visual object discovery through multi-modal dialogue","created":"2016-11-23","cited_by_count":113},{"id":"1606.03556","title":"Human Attention in Visual Question Answering: Do Humans and Deep Networks Look at the Same Regions?","created":"2016-06-11","cited_by_count":111},{"id":"1912.07538","title":"Towards Causal VQA: Revealing and Reducing Spurious Correlations by Invariant and Covariant Semantic Editing","created":"2019-12-16","cited_by_count":108},{"id":"1803.11438","title":"Reconstruction Network for Video Captioning","created":"2018-03-30","cited_by_count":98},{"id":"1805.00145","title":"Dialog-based Interactive Image Retrieval","created":"2018-05-01","cited_by_count":84},{"id":"1611.01646","title":"Boosting Image Captioning with Attributes","created":"2016-11-05","cited_by_count":76},{"id":"1911.10496","title":"Two Causal Principles for Improving Visual Dialog","created":"2019-11-24","cited_by_count":75},{"id":"1703.06585","title":"Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning","created":"2017-03-20","cited_by_count":71},{"id":"1804.00100","title":"Bidirectional Attentive Fusion with Context Gating for Dense Video Captioning","created":"2018-03-31","cited_by_count":68},{"id":"1712.07271","title":"Learning Sight from Sound: Ambient Sound Provides Supervision for Visual Learning","created":"2017-12-20","cited_by_count":67},{"id":"1511.05234","title":"Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering","created":"2015-11-17","cited_by_count":66},{"id":"1511.07394","title":"Where To Look: Focus Regions for Visual Question Answering","created":"2015-11-23","cited_by_count":64},{"id":"2003.08897","title":"Normalized and Geometry-Aware Self-Attention Network for Image Captioning","created":"2020-03-19","cited_by_count":63},{"id":"1603.01417","title":"Dynamic Memory Networks for Visual and Textual Question Answering","created":"2016-03-04","cited_by_count":62},{"id":"1912.02379","title":"Large-scale Pretraining for Visual Dialog: A Simple State-of-the-Art Baseline","created":"2019-12-05","cited_by_count":61},{"id":"2004.13278","title":"VD-BERT: A Unified Vision and Dialog Transformer with BERT","created":"2020-04-28","cited_by_count":55},{"id":"1904.05876","title":"A Simple Baseline for Audio-Visual Scene-Aware Dialog","created":"2019-04-11","cited_by_count":52},{"id":"1611.07675","title":"Video Captioning with Transferred Semantic Attributes","created":"2016-11-23","cited_by_count":46},{"id":"1904.09013","title":"Self-Supervised Audio-Visual Co-Segmentation","created":"2019-04-18","cited_by_count":44},{"id":"1902.00579","title":"Multi-step Reasoning via Recurrent Dual Attention for Visual Dialog","created":"2019-02-01","cited_by_count":41},{"id":"1904.05880","title":"Factor Graph Attention","created":"2019-04-11","cited_by_count":41},{"id":"1806.08409","title":"End-to-End Audio Visual Scene-Aware Dialog using Multimodal Attention-Based Video Features","created":"2018-06-21","cited_by_count":37},{"id":"2008.06581","title":"Audio-Visual Event Localization via Recursive Fusion by Joint Co-Attention","created":"2020-08-14","cited_by_count":37},{"id":"1711.07068","title":"Diverse and Accurate Image Description Using a Variational Auto-Encoder with an Additive Gaussian Encoding Space","created":"2017-11-19","cited_by_count":33},{"id":"2005.07493","title":"History for Visual Dialog: Do we really need it?","created":"2020-05-08","cited_by_count":32},{"id":"1709.07992","title":"Visual Reference Resolution using Attention Memory for Visual Dialog","created":"2017-09-23","cited_by_count":28},{"id":"1703.05423","title":"End-to-end optimization of goal-driven and visually grounded dialogue systems","created":"2017-03-15","cited_by_count":17},{"id":"2004.02194","title":"Iterative Context-Aware Graph Inference for Visual Dialog","created":"2020-04-05","cited_by_count":16},{"id":"1804.03803","title":"Decoupled Novel Object Captioner","created":"2018-04-11","cited_by_count":15},{"id":"1711.07613","title":"Are You Talking to Me? Reasoned Visual Dialog Generation through Adversarial Learning","created":"2017-11-21","cited_by_count":14},{"id":"1907.12021","title":"What Should I Ask? Using Conversationally Informative Rewards for Goal-Oriented Visual Dialog","created":"2019-07-28","cited_by_count":14},{"id":"2102.03424","title":"Learning Audio-Visual Correlations from Variational Cross-Modal Generation","created":"2021-02-05","cited_by_count":14},{"id":"1803.11186","title":"Two can play this Game: Visual Dialog with Discriminative Question Generation and Answering","created":"2018-03-29","cited_by_count":13},{"id":"1802.03881","title":"Answerer in Questioner's Mind: Information Theoretic Approach to Goal-Oriented Visual Dialog","created":"2018-02-12","cited_by_count":11},{"id":"2008.07935","title":"Describing Unseen Videos via Multi-Modal Cooperative Dialog Agents","created":"2020-08-18","cited_by_count":11},{"id":"1711.07614","title":"Asking the Difficult Questions: Goal-Oriented Visual Question Generation via Intermediate Rewards","created":"2017-11-21","cited_by_count":7},{"id":"1802.03803","title":"FlipDial: A Generative Model for Two-Way Visual Dialogue","created":"2018-02-11","cited_by_count":6},{"id":"1904.04166","title":"Revisiting EmbodiedQA: A Simple Baseline and Beyond","created":"2019-04-08","cited_by_count":6},{"id":"1808.09996","title":"Learning End-to-End Goal-Oriented Dialog with Multiple Answers","created":"2018-08-24","cited_by_count":4}],"next_cursor":null}