{"list":"other","total":54,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"1906.00067","title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge","created":"2019-05-31","cited_by_count":1121},{"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":"1906.10770","title":"Deep Modular Co-Attention Networks for Visual Question Answering","created":"2019-06-25","cited_by_count":339},{"id":"1511.03416","title":"Visual7W: Grounded Question Answering in Images","created":"2015-11-11","cited_by_count":318},{"id":"1711.11575","title":"Relation Networks for Object Detection","created":"2017-11-30","cited_by_count":305},{"id":"1810.02338","title":"Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding","created":"2018-10-04","cited_by_count":304},{"id":"1805.07932","title":"Bilinear Attention Networks","created":"2018-05-21","cited_by_count":280},{"id":"1511.02274","title":"Stacked Attention Networks for Image Question Answering","created":"2015-11-07","cited_by_count":273},{"id":"1809.07041","title":"Exploring Visual Relationship for Image Captioning","created":"2018-09-19","cited_by_count":215},{"id":"1606.05433","title":"FVQA: Fact-based Visual Question Answering","created":"2016-06-17","cited_by_count":181},{"id":"1903.03326","title":"Knowledge-Embedded Routing Network for Scene Graph Generation","created":"2019-03-08","cited_by_count":164},{"id":"1712.03316","title":"IQA: Visual Question Answering in Interactive Environments","created":"2017-12-09","cited_by_count":155},{"id":"2001.03615","title":"In Defense of Grid Features for Visual Question Answering","created":"2020-01-10","cited_by_count":155},{"id":"1709.07326","title":"AffordanceNet: An End-to-End Deep Learning Approach for Object Affordance Detection","created":"2017-09-21","cited_by_count":128},{"id":"1609.05600","title":"Graph-Structured Representations for Visual Question Answering","created":"2016-09-19","cited_by_count":123},{"id":"1903.12314","title":"Relation-Aware Graph Attention Network for Visual Question Answering","created":"2019-03-29","cited_by_count":119},{"id":"1812.05252","title":"Dynamic Fusion with Intra- and Inter- Modality Attention Flow for Visual Question Answering","created":"2018-12-13","cited_by_count":114},{"id":"1907.03950","title":"Learning by Abstraction: The Neural State Machine","created":"2019-07-09","cited_by_count":113},{"id":"1812.04794","title":"Neighbourhood Watch: Referring Expression Comprehension via Language-guided Graph Attention Networks","created":"2018-12-12","cited_by_count":102},{"id":"1904.00560","title":"Scene Graph Generation with External Knowledge and Image Reconstruction","created":"2019-04-01","cited_by_count":102},{"id":"1708.02711","title":"Tips and Tricks for Visual Question Answering: Learnings from the 2017 Challenge","created":"2017-08-09","cited_by_count":76},{"id":"2106.00245","title":"Adversarial VQA: A New Benchmark for Evaluating the Robustness of VQA Models","created":"2021-06-01","cited_by_count":75},{"id":"1902.09487","title":"MUREL: Multimodal Relational Reasoning for Visual Question Answering","created":"2019-02-25","cited_by_count":68},{"id":"1807.09956","title":"Pythia v0.1: the Winning Entry to the VQA Challenge 2018","created":"2018-07-26","cited_by_count":62},{"id":"1905.09998","title":"Self-Critical Reasoning for Robust Visual Question Answering","created":"2019-05-24","cited_by_count":61},{"id":"2105.08913","title":"Multiple Meta-model Quantifying for Medical Visual Question Answering","created":"2021-05-19","cited_by_count":54},{"id":"1803.05268","title":"Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual Reasoning","created":"2018-03-14","cited_by_count":51},{"id":"2003.13962","title":"Multi-Modal Graph Neural Network for Joint Reasoning on Vision and Scene Text","created":"2020-03-31","cited_by_count":46},{"id":"1910.03230","title":"Meta Module Network for Compositional Visual Reasoning","created":"2019-10-08","cited_by_count":39},{"id":"2002.11894","title":"Unshuffling Data for Improved Generalization","created":"2020-02-27","cited_by_count":35},{"id":"2006.11524","title":"Neuro-Symbolic Visual Reasoning: Disentangling \"Visual\" from \"Reasoning\"","created":"2020-06-20","cited_by_count":35},{"id":"1703.03054","title":"Deep Variation-structured Reinforcement Learning for Visual Relationship and Attribute Detection","created":"2017-03-08","cited_by_count":28},{"id":"1909.11874","title":"Compact Trilinear Interaction for Visual Question Answering","created":"2019-09-26","cited_by_count":24},{"id":"1805.09701","title":"R-VQA: Learning Visual Relation Facts with Semantic Attention for Visual Question Answering","created":"2018-05-24","cited_by_count":23},{"id":"2105.04836","title":"Found a Reason for me? Weakly-supervised Grounded Visual Question Answering using Capsules","created":"2021-05-11","cited_by_count":22},{"id":"2007.15945","title":"Autonomous Navigation in Complex Environments with Deep Multimodal Fusion Network","created":"2020-07-31","cited_by_count":16},{"id":"2011.13160","title":"Transformation Driven Visual Reasoning","created":"2020-11-26","cited_by_count":14},{"id":"2104.06770","title":"Graph-based Person Signature for Person Re-Identifications","created":"2021-04-14","cited_by_count":14},{"id":"2110.01293","title":"Light-weight Deformable Registration using Adversarial Learning with Distilling Knowledge","created":"2021-10-04","cited_by_count":12},{"id":"1806.03724","title":"Learning Answer Embeddings for Visual Question Answering","created":"2018-06-10","cited_by_count":11},{"id":"2005.06035","title":"Cross-Modality Relevance for Reasoning on Language and Vision","created":"2020-05-12","cited_by_count":10},{"id":"2103.15022","title":"'Just because you are right, doesn't mean I am wrong': Overcoming a Bottleneck in the Development and Evaluation of Open-Ended Visual Question Answering (VQA) Tasks","created":"2021-03-28","cited_by_count":10},{"id":"2004.14603","title":"Dynamic Language Binding in Relational Visual Reasoning","created":"2020-04-30","cited_by_count":7},{"id":"1803.06152","title":"Object Captioning and Retrieval with Natural Language","created":"2018-03-16","cited_by_count":6},{"id":"1903.10869","title":"V2CNet: A Deep Learning Framework to Translate Videos to Commands for Robotic Manipulation","created":"2019-03-23","cited_by_count":5},{"id":"1801.07853","title":"Structured Triplet Learning with POS-tag Guided Attention for Visual Question Answering","created":"2018-01-24","cited_by_count":4}],"next_cursor":null}