{"list":"other","total":63,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"id":"1810.00278","title":"MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling","created":"2018-09-29","cited_by_count":766},{"id":"1705.02101","title":"TALL: Temporal Activity Localization via Language Query","created":"2017-05-05","cited_by_count":584},{"id":"1909.11059","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","created":"2019-09-24","cited_by_count":494},{"id":"1809.01696","title":"TVQA: Localized, Compositional Video Question Answering","created":"2018-09-05","cited_by_count":467},{"id":"1704.04497","title":"TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question Answering","created":"2017-04-14","cited_by_count":378},{"id":"1611.08669","title":"Visual Dialog","created":"2016-11-26","cited_by_count":377},{"id":"1511.03416","title":"Visual7W: Grounded Question Answering in Images","created":"2015-11-11","cited_by_count":318},{"id":"1604.04562","title":"A Network-based End-to-End Trainable Task-oriented Dialogue System","created":"2016-04-15","cited_by_count":252},{"id":"1907.04957","title":"Vision-and-Dialog Navigation","created":"2019-07-10","cited_by_count":250},{"id":"1905.08743","title":"Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems","created":"2019-05-21","cited_by_count":216},{"id":"1501.02530","title":"A Dataset for Movie Description","created":"2015-01-12","cited_by_count":195},{"id":"1606.03777","title":"Neural Belief Tracker: Data-Driven Dialogue State Tracking","created":"2016-06-12","cited_by_count":143},{"id":"1705.05414","title":"Key-Value Retrieval Networks for Task-Oriented Dialogue","created":"2017-05-15","cited_by_count":138},{"id":"1910.04744","title":"CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning","created":"2019-10-10","cited_by_count":137},{"id":"1511.04164","title":"Natural Language Object Retrieval","created":"2015-11-13","cited_by_count":124},{"id":"1901.09107","title":"Audio-Visual Scene-Aware Dialog","created":"2019-01-25","cited_by_count":123},{"id":"1611.08481","title":"GuessWhat?! Visual object discovery through multi-modal dialogue","created":"2016-11-23","cited_by_count":113},{"id":"1910.03544","title":"Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Tracking","created":"2019-10-08","cited_by_count":75},{"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":"1907.07421","title":"SUMBT: Slot-Utterance Matching for Universal and Scalable Belief Tracking","created":"2019-07-17","cited_by_count":63},{"id":"1908.01946","title":"Dialog State Tracking: A Neural Reading Comprehension Approach","created":"2019-08-06","cited_by_count":62},{"id":"2104.08667","title":"SIMMC 2.0: A Task-oriented Dialog Dataset for Immersive Multimodal Conversations","created":"2021-04-18","cited_by_count":56},{"id":"1807.08556","title":"Explainable Neural Computation via Stack Neural Module Networks","created":"2018-07-23","cited_by_count":54},{"id":"1809.01816","title":"Visual Coreference Resolution in Visual Dialog using Neural Module Networks","created":"2018-09-06","cited_by_count":54},{"id":"1907.01166","title":"Multimodal Transformer Networks for End-to-End Video-Grounded Dialogue Systems","created":"2019-07-02","cited_by_count":52},{"id":"1805.09655","title":"Global-Locally Self-Attentive Dialogue State Tracker","created":"2018-05-19","cited_by_count":45},{"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":"2106.00291","title":"Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialog State Tracking","created":"2021-06-01","cited_by_count":35},{"id":"2003.10469","title":"Learning Object Permanence from Video","created":"2020-03-23","cited_by_count":30},{"id":"1807.06517","title":"Large-Scale Multi-Domain Belief Tracking with Knowledge Sharing","created":"2018-07-17","cited_by_count":29},{"id":"1709.07992","title":"Visual Reference Resolution using Attention Memory for Visual Dialog","created":"2017-09-23","cited_by_count":28},{"id":"1805.01555","title":"An End-to-end Approach for Handling Unknown Slot Values in Dialogue State Tracking","created":"2018-05-03","cited_by_count":27},{"id":"1601.01530","title":"Leveraging Sentence-level Information with Encoder LSTM for Semantic Slot Filling","created":"2016-01-07","cited_by_count":25},{"id":"1712.10224","title":"Scalable Multi-Domain Dialogue State Tracking","created":"2017-12-29","cited_by_count":22},{"id":"2010.10095","title":"BiST: Bi-directional Spatio-Temporal Reasoning for Video-Grounded Dialogues","created":"2020-10-20","cited_by_count":22},{"id":"2002.00163","title":"Bridging Text and Video: A Universal Multimodal Transformer for Video-Audio Scene-Aware Dialog","created":"2020-02-01","cited_by_count":20},{"id":"2104.04466","title":"Knowledge-Aware Graph-Enhanced GPT-2 for Dialogue State Tracking","created":"2021-04-09","cited_by_count":20},{"id":"2004.14307","title":"UniConv: A Unified Conversational Neural Architecture for Multi-domain Task-oriented Dialogues","created":"2020-04-29","cited_by_count":19},{"id":"1708.05122","title":"Evaluating Visual Conversational Agents via Cooperative Human-AI Games","created":"2017-08-17","cited_by_count":17},{"id":"2002.08024","title":"Non-Autoregressive Dialog State Tracking","created":"2020-02-19","cited_by_count":15},{"id":"1911.07928","title":"Visual Dialogue State Tracking for Question Generation","created":"2019-11-12","cited_by_count":13},{"id":"2101.00151","title":"DVD: A Diagnostic Dataset for Multi-step Reasoning in Video Grounded Dialogue","created":"2021-01-01","cited_by_count":13},{"id":"2103.00820","title":"Learning Reasoning Paths over Semantic Graphs for Video-grounded Dialogues","created":"2021-03-01","cited_by_count":11},{"id":"1803.03347","title":"Tracking by Prediction: A Deep Generative Model for Mutli-Person localisation and Tracking","created":"2018-03-09","cited_by_count":9},{"id":"2001.06354","title":"Modality-Balanced Models for Visual Dialogue","created":"2020-01-17","cited_by_count":8},{"id":"2007.09903","title":"Multimodal Dialogue State Tracking By QA Approach with Data Augmentation","created":"2020-07-20","cited_by_count":7}],"next_cursor":null}