{"list":"other","total":67,"rows":[{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"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":"1711.07280","title":"Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments","created":"2017-11-20","cited_by_count":1027},{"id":"1811.00491","title":"A Corpus for Reasoning About Natural Language Grounded in Photographs","created":"2018-11-01","cited_by_count":459},{"id":"2010.07954","title":"Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding","created":"2020-10-15","cited_by_count":414},{"id":"1808.05326","title":"SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference","created":"2018-08-16","cited_by_count":333},{"id":"1605.00459","title":"Multi30K: Multilingual English-German Image Descriptions","created":"2016-05-02","cited_by_count":250},{"id":"1810.08272","title":"BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning","created":"2018-10-18","cited_by_count":244},{"id":"1606.01847","title":"Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding","created":"2016-06-06","cited_by_count":243},{"id":"2004.10151","title":"Experience Grounds Language","created":"2020-04-21","cited_by_count":242},{"id":"2004.05483","title":"Unsupervised Commonsense Question Answering with Self-Talk","created":"2020-04-11","cited_by_count":161},{"id":"1904.11574","title":"TVQA+: Spatio-Temporal Grounding for Video Question Answering","created":"2019-04-25","cited_by_count":154},{"id":"1805.04655","title":"Learning to Ask Good Questions: Ranking Clarification Questions using Neural Expected Value of Perfect Information","created":"2018-05-12","cited_by_count":115},{"id":"1611.08481","title":"GuessWhat?! Visual object discovery through multi-modal dialogue","created":"2016-11-23","cited_by_count":113},{"id":"1809.07358","title":"A Dataset for Document Grounded Conversations","created":"2018-09-19","cited_by_count":104},{"id":"1901.05415","title":"Learning from Dialogue after Deployment: Feed Yourself, Chatbot!","created":"2019-01-16","cited_by_count":102},{"id":"1811.00945","title":"Image Chat: Engaging Grounded Conversations","created":"2018-11-02","cited_by_count":77},{"id":"2009.07396","title":"Grounded Adaptation for Zero-shot Executable Semantic Parsing","created":"2020-09-16","cited_by_count":76},{"id":"1906.02549","title":"Weakly-Supervised Spatio-Temporally Grounding Natural Sentence in Video","created":"2019-06-06","cited_by_count":60},{"id":"1911.02707","title":"Grounded Conversation Generation as Guided Traverses in Commonsense Knowledge Graphs","created":"2019-11-07","cited_by_count":59},{"id":"2009.11352","title":"ConvAI3: Generating Clarifying Questions for Open-Domain Dialogue Systems (ClariQ)","created":"2020-09-23","cited_by_count":58},{"id":"1703.10186","title":"Colors in Context: A Pragmatic Neural Model for Grounded Language Understanding","created":"2017-03-29","cited_by_count":57},{"id":"1906.00347","title":"Are You Looking? Grounding to Multiple Modalities in Vision-and-Language Navigation","created":"2019-06-02","cited_by_count":55},{"id":"1906.02890","title":"Visually Grounded Neural Syntax Acquisition","created":"2019-06-07","cited_by_count":48},{"id":"1705.00823","title":"STAIR Captions: Constructing a Large-Scale Japanese Image Caption Dataset","created":"2017-05-02","cited_by_count":47},{"id":"1906.01530","title":"The PhotoBook Dataset: Building Common Ground through Visually-Grounded Dialogue","created":"2019-06-04","cited_by_count":46},{"id":"1702.01991","title":"Representations of language in a model of visually grounded speech signal","created":"2017-02-07","cited_by_count":37},{"id":"1505.06289","title":"Text to 3D Scene Generation with Rich Lexical Grounding","created":"2015-05-23","cited_by_count":36},{"id":"1907.08854","title":"Incremental Transformer with Deliberation Decoder for Document Grounded Conversations","created":"2019-07-20","cited_by_count":35},{"id":"2009.12404","title":"Visually Grounded Compound PCFGs","created":"2020-09-25","cited_by_count":34},{"id":"1909.08782","title":"Large-scale representation learning from visually grounded untranscribed speech","created":"2019-09-19","cited_by_count":33},{"id":"2004.05569","title":"Explaining Question Answering Models through Text Generation","created":"2020-04-12","cited_by_count":33},{"id":"2005.01655","title":"Words aren't enough, their order matters: On the Robustness of Grounding Visual Referring Expressions","created":"2020-05-04","cited_by_count":33},{"id":"2005.00728","title":"RMM: A Recursive Mental Model for Dialog Navigation","created":"2020-05-02","cited_by_count":32},{"id":"2006.05986","title":"ClarQ: A large-scale and diverse dataset for Clarification Question Generation","created":"2020-06-10","cited_by_count":31},{"id":"1706.03815","title":"Encoding of phonology in a recurrent neural model of grounded speech","created":"2017-06-12","cited_by_count":27},{"id":"1707.03938","title":"Representation Learning for Grounded Spatial Reasoning","created":"2017-07-13","cited_by_count":23},{"id":"1808.08266","title":"A Visual Attention Grounding Neural Model for Multimodal Machine Translation","created":"2018-08-24","cited_by_count":22},{"id":"2004.09544","title":"Grounding Conversations with Improvised Dialogues","created":"2020-04-20","cited_by_count":22},{"id":"2011.04554","title":"Refer, Reuse, Reduce: Generating Subsequent References in Visual and Conversational Contexts","created":"2020-11-09","cited_by_count":22},{"id":"1907.03228","title":"Zero-Shot Open Entity Typing as Type-Compatible Grounding","created":"2019-07-07","cited_by_count":19},{"id":"2004.05704","title":"Visual Grounding Methods for VQA are Working for the Wrong Reasons!","created":"2020-04-12","cited_by_count":18},{"id":"1906.06401","title":"\"My Way of Telling a Story\": Persona based Grounded Story Generation","created":"2019-06-14","cited_by_count":17},{"id":"1909.08491","title":"Word Recognition, Competition, and Activation in a Model of Visually Grounded Speech","created":"2019-09-18","cited_by_count":13},{"id":"2104.08964","title":"A recipe for annotating grounded clarifications","created":"2021-04-18","cited_by_count":13},{"id":"1806.05645","title":"Grounded Textual Entailment","created":"2018-06-14","cited_by_count":10},{"id":"1812.09244","title":"Symbolic inductive bias for visually grounded learning of spoken language","created":"2018-12-21","cited_by_count":10},{"id":"1609.08824","title":"Equation Parsing: Mapping Sentences to Grounded Equations","created":"2016-09-28","cited_by_count":9},{"id":"1905.05293","title":"Towards Content Transfer through Grounded Text Generation","created":"2019-05-13","cited_by_count":9},{"id":"2006.08387","title":"Catplayinginthesnow: Impact of Prior Segmentation on a Model of Visually Grounded Speech","created":"2020-06-15","cited_by_count":9},{"id":"2005.00696","title":"Robust and Interpretable Grounding of Spatial References with Relation Networks","created":"2020-05-02","cited_by_count":8},{"id":"2006.02174","title":"CompGuessWhat?!: A Multi-task Evaluation Framework for Grounded Language Learning","created":"2020-06-03","cited_by_count":8},{"id":"1904.05426","title":"A Grounded Unsupervised Universal Part-of-Speech Tagger for Low-Resource Languages","created":"2019-04-10","cited_by_count":7},{"id":"2010.03127","title":"A Linguistic Analysis of Visually Grounded Dialogues Based on Spatial Expressions","created":"2020-10-07","cited_by_count":6},{"id":"1608.04147","title":"Numerically Grounded Language Models for Semantic Error Correction","created":"2016-08-14","cited_by_count":5},{"id":"2005.00246","title":"Cross-modal Language Generation using Pivot Stabilization for Web-scale Language Coverage","created":"2020-05-01","cited_by_count":5},{"id":"2009.11523","title":"Grounded Compositional Outputs for Adaptive Language Modeling","created":"2020-09-24","cited_by_count":5},{"id":"2010.02384","title":"Fine-Grained Grounding for Multimodal Speech Recognition","created":"2020-10-05","cited_by_count":5},{"id":"1703.01720","title":"Sound-Word2Vec: Learning Word Representations Grounded in Sounds","created":"2017-03-06","cited_by_count":4},{"id":"2005.00458","title":"Style Variation as a Vantage Point for Code-Switching","created":"2020-05-01","cited_by_count":4},{"id":"1609.09405","title":"Evaluating Induced CCG Parsers on Grounded Semantic Parsing","created":"2016-09-29","cited_by_count":2},{"id":"2004.14338","title":"Beyond Instructional Videos: Probing for More Diverse Visual-Textual Grounding on YouTube","created":"2020-04-29","cited_by_count":2},{"id":"1509.03488","title":"Verbs Taking Clausal and Non-Finite Arguments as Signals of Modality - Revisiting the Issue of Meaning Grounded in Syntax","created":"2015-09-11","cited_by_count":1},{"id":"1806.04284","title":"iParaphrasing: Extracting Visually Grounded Paraphrases via an Image","created":"2018-06-12","cited_by_count":1},{"id":"1906.03753","title":"Out-of-Vocabulary Embedding Imputation with Grounded Language Information by Graph Convolutional Networks","created":"2019-06-10","cited_by_count":1},{"id":"1909.09699","title":"Induction and Reference of Entities in a Visual Story","created":"2019-09-15","cited_by_count":1}],"next_cursor":null}