{"list":"other","total":52,"rows":[{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"1412.2306","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","created":"2014-12-07","cited_by_count":968},{"id":"1910.01442","title":"CLEVRER: CoLlision Events for Video REpresentation and Reasoning","created":"2019-10-03","cited_by_count":484},{"id":"1901.11390","title":"MONet: Unsupervised Scene Decomposition and Representation","created":"2019-01-22","cited_by_count":392},{"id":"1511.02799","title":"Neural Module Networks","created":"2015-11-09","cited_by_count":376},{"id":"1904.12584","title":"The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision","created":"2019-04-26","cited_by_count":372},{"id":"1902.10178","title":"Unmasking Clever Hans Predictors and Assessing What Machines Really Learn","created":"2019-02-26","cited_by_count":365},{"id":"1706.01427","title":"A simple neural network module for relational reasoning","created":"2017-06-05","cited_by_count":346},{"id":"1904.01557","title":"Analysing Mathematical Reasoning Abilities of Neural Models","created":"2019-04-02","cited_by_count":335},{"id":"1502.05698","title":"Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks","created":"2015-02-19","cited_by_count":314},{"id":"1810.02338","title":"Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding","created":"2018-10-04","cited_by_count":304},{"id":"1912.09713","title":"Measuring Compositional Generalization: A Comprehensive Method on Realistic Data","created":"2019-12-20","cited_by_count":284},{"id":"2012.00451","title":"Just Ask: Learning to Answer Questions from Millions of Narrated Videos","created":"2020-12-01","cited_by_count":248},{"id":"1903.02741","title":"RAVEN: A Dataset for Relational and Analogical Visual rEasoNing","created":"2019-03-07","cited_by_count":226},{"id":"1911.12247","title":"Contrastive Learning of Structured World Models","created":"2019-11-27","cited_by_count":209},{"id":"1803.03067","title":"Compositional Attention Networks for Machine Reasoning","created":"2018-03-08","cited_by_count":183},{"id":"1807.04225","title":"Measuring abstract reasoning in neural networks","created":"2018-07-11","cited_by_count":166},{"id":"1603.08507","title":"Generating Visual Explanations","created":"2016-03-28","cited_by_count":158},{"id":"2003.06576","title":"Counterfactual Samples Synthesizing for Robust Visual Question Answering","created":"2020-03-14","cited_by_count":153},{"id":"1908.05656","title":"PHYRE: A New Benchmark for Physical Reasoning","created":"2019-08-15","cited_by_count":137},{"id":"1705.03633","title":"Inferring and Executing Programs for Visual Reasoning","created":"2017-05-10","cited_by_count":130},{"id":"1704.05526","title":"Learning to Reason: End-to-End Module Networks for Visual Question Answering","created":"2017-04-18","cited_by_count":125},{"id":"1907.03950","title":"Learning by Abstraction: The Neural State Machine","created":"2019-07-09","cited_by_count":113},{"id":"2003.00330","title":"Graph Neural Networks Meet Neural-Symbolic Computing: A Survey and Perspective","created":"2020-02-29","cited_by_count":95},{"id":"1601.01705","title":"Learning to Compose Neural Networks for Question Answering","created":"2016-01-07","cited_by_count":85},{"id":"1912.05783","title":"CLOSURE: Assessing Systematic Generalization of CLEVR Models","created":"2019-12-12","cited_by_count":63},{"id":"2009.08566","title":"MUTANT: A Training Paradigm for Out-of-Distribution Generalization in Visual Question Answering","created":"2020-09-18","cited_by_count":63},{"id":"2010.00763","title":"Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning","created":"2020-10-02","cited_by_count":63},{"id":"1909.01068","title":"CGC-Net: Cell Graph Convolutional Network for Grading of Colorectal Cancer Histology Images","created":"2019-09-03","cited_by_count":57},{"id":"1906.02890","title":"Visually Grounded Neural Syntax Acquisition","created":"2019-06-07","cited_by_count":48},{"id":"2002.01464","title":"Visual Concept-Metaconcept Learning","created":"2020-02-04","cited_by_count":39},{"id":"1704.04517","title":"ShapeWorld - A new test methodology for multimodal language understanding","created":"2017-04-14","cited_by_count":37},{"id":"2004.12906","title":"Towards causal generative scene models via competition of experts","created":"2020-04-27","cited_by_count":37},{"id":"2006.11197","title":"Abstract Diagrammatic Reasoning with Multiplex Graph Networks","created":"2020-06-19","cited_by_count":37},{"id":"2009.12404","title":"Visually Grounded Compound PCFGs","created":"2020-09-25","cited_by_count":34},{"id":"1712.01238","title":"Learning by Asking Questions","created":"2017-12-04","cited_by_count":25},{"id":"1704.08243","title":"C-VQA: A Compositional Split of the Visual Question Answering (VQA) v1.0 Dataset","created":"2017-04-26","cited_by_count":24},{"id":"1907.12271","title":"V-PROM: A Benchmark for Visual Reasoning Using Visual Progressive Matrices","created":"2019-07-29","cited_by_count":24},{"id":"2010.02855","title":"CURI: A Benchmark for Productive Concept Learning Under Uncertainty","created":"2020-10-06","cited_by_count":21},{"id":"1906.00657","title":"Kandinsky Patterns","created":"2019-06-03","cited_by_count":16},{"id":"2012.11587","title":"Object-Centric Diagnosis of Visual Reasoning","created":"2020-12-21","cited_by_count":16},{"id":"2005.01678","title":"What is Learned in Visually Grounded Neural Syntax Acquisition","created":"2020-05-04","cited_by_count":15},{"id":"2011.14036","title":"Differences between human and machine perception in medical diagnosis","created":"2020-11-28","cited_by_count":13},{"id":"1806.02453","title":"Visual Reasoning by Progressive Module Networks","created":"2018-06-06","cited_by_count":7},{"id":"2008.06457","title":"Abstracting Deep Neural Networks into Concept Graphs for Concept Level Interpretability","created":"2020-08-14","cited_by_count":6},{"id":"1911.02133","title":"Contextual Grounding of Natural Language Entities in Images","created":"2019-11-05","cited_by_count":2},{"id":"2011.07193","title":"Data-Efficient Learning for Complex and Real-Time Physical Problem Solving using Augmented Simulation","created":"2020-11-14","cited_by_count":2}],"next_cursor":null}