{"list":"other","total":61,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"1411.7766","title":"Deep Learning Face Attributes in the Wild","created":"2014-11-28","cited_by_count":3693},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"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":"1610.02136","title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","created":"2016-10-07","cited_by_count":2385},{"id":"1805.01978","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","created":"2018-05-05","cited_by_count":1845},{"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":"1707.07998","title":"Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering","created":"2017-07-25","cited_by_count":1312},{"id":"1906.05849","title":"Contrastive Multiview Coding","created":"2019-06-13","cited_by_count":1301},{"id":"2010.03759","title":"Energy-based Out-of-distribution Detection","created":"2020-10-08","cited_by_count":1299},{"id":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1296},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819},{"id":"1906.00910","title":"Learning Representations by Maximizing Mutual Information Across Views","created":"2019-06-03","cited_by_count":734},{"id":"1905.09272","title":"Data-Efficient Image Recognition with Contrastive Predictive Coding","created":"2019-05-22","cited_by_count":673},{"id":"2003.10286","title":"PathVQA: 30000+ Questions for Medical Visual Question Answering","created":"2020-03-07","cited_by_count":475},{"id":"1912.03263","title":"Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One","created":"2019-12-06","cited_by_count":405},{"id":"1903.12355","title":"Local Aggregation for Unsupervised Learning of Visual Embeddings","created":"2019-03-29","cited_by_count":204},{"id":"2104.03135","title":"Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning","created":"2021-04-07","cited_by_count":187},{"id":"1904.09770","title":"Learning Non-Convergent Non-Persistent Short-Run MCMC Toward Energy-Based Model","created":"2019-04-22","cited_by_count":148},{"id":"1505.02074","title":"Exploring Models and Data for Image Question Answering","created":"2015-05-08","cited_by_count":139},{"id":"2012.01316","title":"Improved Contrastive Divergence Training of Energy Based Models","created":"2020-12-02","cited_by_count":130},{"id":"1607.05910","title":"Visual Question Answering: A Survey of Methods and Datasets","created":"2016-07-20","cited_by_count":123},{"id":"1903.12370","title":"On the Anatomy of MCMC-Based Maximum Likelihood Learning of Energy-Based Models","created":"2019-03-29","cited_by_count":105},{"id":"2010.00654","title":"VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Models","created":"2020-10-01","cited_by_count":104},{"id":"2103.02221","title":"Energy-Based Learning for Scene Graph Generation","created":"2021-03-03","cited_by_count":104},{"id":"2004.11714","title":"Residual Energy-Based Models for Text Generation","created":"2020-04-22","cited_by_count":95},{"id":"2106.01804","title":"E2E-VLP: End-to-End Vision-Language Pre-training Enhanced by Visual Learning","created":"2021-06-03","cited_by_count":85},{"id":"2006.14610","title":"A causal view of compositional zero-shot recognition","created":"2020-06-25","cited_by_count":78},{"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":"2005.09241","title":"On the Value of Out-of-Distribution Testing: An Example of Goodhart's Law","created":"2020-05-19","cited_by_count":74},{"id":"2003.05033","title":"Generalized Energy Based Models","created":"2020-03-10","cited_by_count":73},{"id":"2104.03149","title":"Beyond Question-Based Biases: Assessing Multimodal Shortcut Learning in Visual Question Answering","created":"2021-04-07","cited_by_count":71},{"id":"2004.09034","title":"Learning What Makes a Difference from Counterfactual Examples and Gradient Supervision","created":"2020-04-20","cited_by_count":66},{"id":"1610.01465","title":"Visual Question Answering: Datasets, Algorithms, and Future Challenges","created":"2016-10-05","cited_by_count":56},{"id":"1505.01121","title":"Ask Your Neurons: A Neural-based Approach to Answering Questions about Images","created":"2015-05-05","cited_by_count":51},{"id":"2204.05626","title":"X-DETR: A Versatile Architecture for Instance-wise Vision-Language Tasks","created":"2022-04-12","cited_by_count":43},{"id":"2002.11894","title":"Unshuffling Data for Improved Generalization","created":"2020-02-27","cited_by_count":35},{"id":"1812.10907","title":"Divergence Triangle for Joint Training of Generator Model, Energy-based Model, and Inference Model","created":"2018-12-28","cited_by_count":34},{"id":"1908.04342","title":"Why Does a Visual Question Have Different Answers?","created":"2019-08-12","cited_by_count":34},{"id":"2005.00850","title":"ENGINE: Energy-Based Inference Networks for Non-Autoregressive Machine Translation","created":"2020-05-02","cited_by_count":34},{"id":"2011.12216","title":"Energy-Based Models for Continual Learning","created":"2020-11-24","cited_by_count":32},{"id":"2003.12511","title":"Assessing Image Quality Issues for Real-World Problems","created":"2020-03-27","cited_by_count":28},{"id":"1904.09317","title":"Challenges and Prospects in Vision and Language Research","created":"2019-04-19","cited_by_count":24},{"id":"2107.09106","title":"Separating Skills and Concepts for Novel Visual Question Answering","created":"2021-07-19","cited_by_count":24},{"id":"2005.01698","title":"How to Train Your Energy-Based Model for Regression","created":"2020-05-04","cited_by_count":23},{"id":"2107.08785","title":"On Out-of-distribution Detection with Energy-based Models","created":"2021-07-03","cited_by_count":17},{"id":"2101.06829","title":"Joint Energy-based Model Training for Better Calibrated Natural Language Understanding Models","created":"2021-01-18","cited_by_count":14},{"id":"2205.09256","title":"Training Vision-Language Transformers from Captions","created":"2022-05-19","cited_by_count":11},{"id":"2109.04422","title":"TxT: Crossmodal End-to-End Learning with Transformers","created":"2021-09-09","cited_by_count":2}],"next_cursor":null}