{"list":"other","total":170,"rows":[{"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":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"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":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"1904.01355","title":"FCOS: Fully Convolutional One-Stage Object Detection","created":"2019-04-02","cited_by_count":1577},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"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":"1906.00067","title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge","created":"2019-05-31","cited_by_count":1121},{"id":"1612.03975","title":"ConceptNet 5.5: An Open Multilingual Graph of General Knowledge","created":"2016-12-12","cited_by_count":1067},{"id":"1506.03340","title":"Teaching Machines to Read and Comprehend","created":"2015-06-10","cited_by_count":1049},{"id":"1606.06031","title":"The LAMBADA dataset: Word prediction requiring a broad discourse context","created":"2016-06-20","cited_by_count":992},{"id":"1908.08530","title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations","created":"2019-08-22","cited_by_count":954},{"id":"1412.6575","title":"Embedding Entities and Relations for Learning and Inference in Knowledge Bases","created":"2014-12-20","cited_by_count":932},{"id":"1511.02283","title":"Generation and Comprehension of Unambiguous Object Descriptions","created":"2015-11-07","cited_by_count":904},{"id":"1606.06357","title":"Complex Embeddings for Simple Link Prediction","created":"2016-06-20","cited_by_count":902},{"id":"1411.4555","title":"Show and Tell: A Neural Image Caption Generator","created":"2014-11-17","cited_by_count":879},{"id":"1802.09691","title":"Link Prediction Based on Graph Neural Networks","created":"2018-02-27","cited_by_count":832},{"id":"1511.05493","title":"Gated Graph Sequence Neural Networks","created":"2015-11-17","cited_by_count":796},{"id":"1412.1897","title":"Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images","created":"2014-12-05","cited_by_count":776},{"id":"1404.7828","title":"Deep Learning in Neural Networks: An Overview","created":"2014-04-30","cited_by_count":770},{"id":"1803.10892","title":"Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks","created":"2018-03-29","cited_by_count":690},{"id":"1709.00103","title":"Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning","created":"2017-08-31","cited_by_count":687},{"id":"1705.08039","title":"Poincar\\'e Embeddings for Learning Hierarchical Representations","created":"2017-05-22","cited_by_count":684},{"id":"1802.04364","title":"Junction Tree Variational Autoencoder for Molecular Graph Generation","created":"2018-02-12","cited_by_count":652},{"id":"1410.5401","title":"Neural Turing Machines","created":"2014-10-20","cited_by_count":644},{"id":"1703.09788","title":"Towards Automatic Learning of Procedures from Web Instructional Videos","created":"2017-03-28","cited_by_count":619},{"id":"1712.07040","title":"The NarrativeQA Reading Comprehension Challenge","created":"2017-12-19","cited_by_count":597},{"id":"1811.10830","title":"From Recognition to Cognition: Visual Commonsense Reasoning","created":"2018-11-27","cited_by_count":556},{"id":"1912.13318","title":"LayoutLM: Pre-training of Text and Layout for Document Image Understanding","created":"2019-12-31","cited_by_count":553},{"id":"1807.05511","title":"Object Detection with Deep Learning: A Review","created":"2018-07-15","cited_by_count":528},{"id":"1910.01442","title":"CLEVRER: CoLlision Events for Video REpresentation and Reasoning","created":"2019-10-03","cited_by_count":484},{"id":"1502.04681","title":"Unsupervised Learning of Video Representations using LSTMs","created":"2015-02-16","cited_by_count":435},{"id":"1606.05908","title":"Tutorial on Variational Autoencoders","created":"2016-06-19","cited_by_count":409},{"id":"1907.08194","title":"Neural Probabilistic Logic Programming in DeepProbLog","created":"2019-07-18","cited_by_count":394},{"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":"1609.02612","title":"Generating Videos with Scene Dynamics","created":"2016-09-08","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":"1906.02361","title":"Explain Yourself! Leveraging Language Models for Commonsense Reasoning","created":"2019-06-06","cited_by_count":367},{"id":"1903.00450","title":"Multi-Object Representation Learning with Iterative Variational Inference","created":"2019-03-01","cited_by_count":360},{"id":"1908.07836","title":"PubLayNet: largest dataset ever for document layout analysis","created":"2019-08-16","cited_by_count":351},{"id":"1808.05326","title":"SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference","created":"2018-08-16","cited_by_count":333},{"id":"1503.00075","title":"Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks","created":"2015-02-28","cited_by_count":306},{"id":"1810.02338","title":"Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding","created":"2018-10-04","cited_by_count":304},{"id":"1511.05440","title":"Deep multi-scale video prediction beyond mean square error","created":"2015-11-17","cited_by_count":300},{"id":"1912.04488","title":"SOLO: Segmenting Objects by Locations","created":"2019-12-10","cited_by_count":289},{"id":"1606.00061","title":"Hierarchical Question-Image Co-Attention for Visual Question Answering","created":"2016-05-31","cited_by_count":278},{"id":"1503.00759","title":"A Review of Relational Machine Learning for Knowledge Graphs","created":"2015-03-02","cited_by_count":265},{"id":"1806.03417","title":"Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometry","created":"2018-06-09","cited_by_count":265},{"id":"1709.07604","title":"A Comprehensive Survey of Graph Embedding: Problems, Techniques and Applications","created":"2017-09-22","cited_by_count":260},{"id":"2004.10151","title":"Experience Grounds Language","created":"2020-04-21","cited_by_count":242},{"id":"1911.10683","title":"Image-based table recognition: data, model, and evaluation","created":"2019-11-25","cited_by_count":237},{"id":"1907.13052","title":"GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations","created":"2019-07-30","cited_by_count":227},{"id":"1909.02151","title":"KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning","created":"2019-09-04","cited_by_count":216},{"id":"1603.08575","title":"Attend, Infer, Repeat: Fast Scene Understanding with Generative Models","created":"2016-03-28","cited_by_count":209},{"id":"1804.03329","title":"Representation Tradeoffs for Hyperbolic Embeddings","created":"2018-04-10","cited_by_count":206},{"id":"1911.06667","title":"CenterMask : Real-Time Anchor-Free Instance Segmentation","created":"2019-11-15","cited_by_count":201},{"id":"1810.12885","title":"ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension","created":"2018-10-30","cited_by_count":200},{"id":"1711.03902","title":"Neural-Symbolic Learning and Reasoning: A Survey and Interpretation","created":"2017-11-10","cited_by_count":196},{"id":"2002.06177","title":"The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence","created":"2020-02-14","cited_by_count":195},{"id":"1502.04623","title":"DRAW: A Recurrent Neural Network For Image Generation","created":"2015-02-16","cited_by_count":191},{"id":"2001.02407","title":"SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition","created":"2020-01-08","cited_by_count":190},{"id":"1510.04935","title":"Holographic Embeddings of Knowledge Graphs","created":"2015-10-16","cited_by_count":181},{"id":"1807.04225","title":"Measuring abstract reasoning in neural networks","created":"2018-07-11","cited_by_count":166},{"id":"1804.01882","title":"Hyperbolic Entailment Cones for Learning Hierarchical Embeddings","created":"2018-04-03","cited_by_count":162},{"id":"1905.06088","title":"Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning","created":"2019-05-15","cited_by_count":151},{"id":"1611.01989","title":"DeepCoder: Learning to Write Programs","created":"2016-11-07","cited_by_count":149},{"id":"2001.00309","title":"BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation","created":"2020-01-02","cited_by_count":145},{"id":"1603.06318","title":"Harnessing Deep Neural Networks with Logic Rules","created":"2016-03-21","cited_by_count":135},{"id":"1707.03587","title":"Cooperative Game Theory Approaches for Network Partitioning","created":"2017-07-12","cited_by_count":135},{"id":"2001.11770","title":"Break It Down: A Question Understanding Benchmark","created":"2020-01-31","cited_by_count":131},{"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":"1905.05908","title":"Task-Driven Modular Networks for Zero-Shot Compositional Learning","created":"2019-05-15","cited_by_count":121},{"id":"1710.10723","title":"Simple and Effective Multi-Paragraph Reading Comprehension","created":"2017-10-29","cited_by_count":120},{"id":"1506.09215","title":"Unsupervised Learning from Narrated Instruction Videos","created":"2015-06-30","cited_by_count":116},{"id":"1907.03950","title":"Learning by Abstraction: The Neural State Machine","created":"2019-07-09","cited_by_count":113},{"id":"1410.0210","title":"A Multi-World Approach to Question Answering about Real-World Scenes based on Uncertain Input","created":"2014-10-01","cited_by_count":112},{"id":"1901.06033","title":"Continuous Hierarchical Representations with Poincar\\'e Variational Auto-Encoders","created":"2019-01-17","cited_by_count":112},{"id":"1611.09978","title":"Modeling Relationships in Referential Expressions with Compositional Modular Networks","created":"2016-11-30","cited_by_count":106},{"id":"1904.12165","title":"Improved Conditional VRNNs for Video Prediction","created":"2019-04-27","cited_by_count":104},{"id":"1812.01855","title":"Explainable and Explicit Visual Reasoning over Scene Graphs","created":"2018-12-05","cited_by_count":103},{"id":"1511.06279","title":"Neural Programmer-Interpreters","created":"2015-11-19","cited_by_count":101},{"id":"1412.6604","title":"Video (language) modeling: a baseline for generative models of natural videos","created":"2014-12-20","cited_by_count":92},{"id":"1703.09684","title":"An Analysis of Visual Question Answering Algorithms","created":"2017-03-28","cited_by_count":90},{"id":"1705.00053","title":"The Pose Knows: Video Forecasting by Generating Pose Futures","created":"2017-04-28","cited_by_count":88},{"id":"1911.01655","title":"High Fidelity Video Prediction with Large Stochastic Recurrent Neural Networks","created":"2019-11-05","cited_by_count":88},{"id":"1601.01705","title":"Learning to Compose Neural Networks for Question Answering","created":"2016-01-07","cited_by_count":85},{"id":"1805.06939","title":"Event2Mind: Commonsense Inference on Events, Intents, and Reactions","created":"2018-05-17","cited_by_count":82}],"next_cursor":"100"}