{"list":"other","total":60,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"1805.01978","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","created":"2018-05-05","cited_by_count":1845},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"1808.06670","title":"Learning deep representations by mutual information estimation and maximization","created":"2018-08-20","cited_by_count":1273},{"id":"1901.05555","title":"Class-Balanced Loss Based on Effective Number of Samples","created":"2019-01-16","cited_by_count":1245},{"id":"1809.10341","title":"Deep Graph Infomax","created":"2018-09-27","cited_by_count":1106},{"id":"1912.01991","title":"Self-Supervised Learning of Pretext-Invariant Representations","created":"2019-12-04","cited_by_count":808},{"id":"1906.00910","title":"Learning Representations by Maximizing Mutual Information Across Views","created":"2019-06-03","cited_by_count":734},{"id":"1708.01641","title":"Localizing Moments in Video with Natural Language","created":"2017-08-04","cited_by_count":663},{"id":"1805.00932","title":"Exploring the Limits of Weakly Supervised Pretraining","created":"2018-05-02","cited_by_count":605},{"id":"1705.02101","title":"TALL: Temporal Activity Localization via Language Query","created":"2017-05-05","cited_by_count":584},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"1809.01696","title":"TVQA: Localized, Compositional Video Question Answering","created":"2018-09-05","cited_by_count":467},{"id":"1908.01000","title":"InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization","created":"2019-07-31","cited_by_count":441},{"id":"2007.10639","title":"Multi-modal Transformer for Video Retrieval","created":"2020-07-21","cited_by_count":395},{"id":"2002.11949","title":"Unbiased Scene Graph Generation from Biased Training","created":"2020-02-27","cited_by_count":356},{"id":"1906.10770","title":"Deep Modular Co-Attention Networks for Visual Question Answering","created":"2019-06-25","cited_by_count":339},{"id":"1905.11979","title":"Causal Confusion in Imitation Learning","created":"2019-05-28","cited_by_count":288},{"id":"1912.03590","title":"Learning 2D Temporal Adjacent Networks for Moment Localization with Natural Language","created":"2019-12-08","cited_by_count":285},{"id":"1611.01603","title":"Bidirectional Attention Flow for Machine Comprehension","created":"2016-11-05","cited_by_count":278},{"id":"2006.04315","title":"Counterfactual VQA: A Cause-Effect Look at Language Bias","created":"2020-06-08","cited_by_count":266},{"id":"2009.12991","title":"Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect","created":"2020-09-28","cited_by_count":256},{"id":"2004.13931","title":"Span-based Localizing Network for Natural Language Video Localization","created":"2020-04-29","cited_by_count":235},{"id":"2009.12547","title":"Causal Intervention for Weakly-Supervised Semantic Segmentation","created":"2020-09-26","cited_by_count":229},{"id":"1906.06725","title":"Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good","created":"2019-06-16","cited_by_count":209},{"id":"1903.12355","title":"Local Aggregation for Unsupervised Learning of Visual Embeddings","created":"2019-03-29","cited_by_count":204},{"id":"2004.07514","title":"Local-Global Video-Text Interactions for Temporal Grounding","created":"2020-04-16","cited_by_count":188},{"id":"2004.03545","title":"Dense Regression Network for Video Grounding","created":"2020-04-07","cited_by_count":176},{"id":"1804.07014","title":"To Find Where You Talk: Temporal Sentence Localization in Video with Attention Based Location Regression","created":"2018-04-19","cited_by_count":157},{"id":"2003.06576","title":"Counterfactual Samples Synthesizing for Robust Visual Question Answering","created":"2020-03-14","cited_by_count":153},{"id":"1812.00087","title":"MAN: Moment Alignment Network for Natural Language Moment Retrieval via Iterative Graph Adjustment","created":"2018-11-30","cited_by_count":145},{"id":"1804.05113","title":"Multilevel Language and Vision Integration for Text-to-Clip Retrieval","created":"2018-04-13","cited_by_count":128},{"id":"2009.13000","title":"Interventional Few-Shot Learning","created":"2020-09-28","cited_by_count":112},{"id":"1912.07538","title":"Towards Causal VQA: Revealing and Reducing Spurious Correlations by Invariant and Covariant Semantic Editing","created":"2019-12-16","cited_by_count":108},{"id":"2007.11978","title":"The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentation","created":"2020-07-23","cited_by_count":108},{"id":"2002.12204","title":"Visual Commonsense R-CNN","created":"2020-02-27","cited_by_count":106},{"id":"1712.00961","title":"Learning Independent Causal Mechanisms","created":"2017-12-04","cited_by_count":105},{"id":"2103.00887","title":"Counterfactual Zero-Shot and Open-Set Visual Recognition","created":"2021-03-01","cited_by_count":95},{"id":"1904.03282","title":"Weakly Supervised Video Moment Retrieval From Text Queries","created":"2019-04-05","cited_by_count":85},{"id":"1811.08925","title":"MAC: Mining Activity Concepts for Language-based Temporal Localization","created":"2018-11-21","cited_by_count":84},{"id":"1809.01337","title":"Localizing Moments in Video with Temporal Language","created":"2018-09-05","cited_by_count":83},{"id":"1904.02755","title":"ExCL: Extractive Clip Localization Using Natural Language Descriptions","created":"2019-04-04","cited_by_count":82},{"id":"1605.08179","title":"Discovering Causal Signals in Images","created":"2016-05-26","cited_by_count":79},{"id":"1911.10496","title":"Two Causal Principles for Improving Visual Dialog","created":"2019-11-24","cited_by_count":75},{"id":"1911.08199","title":"Weakly-Supervised Video Moment Retrieval via Semantic Completion Network","created":"2019-11-19","cited_by_count":69},{"id":"2003.03923","title":"Deconfounded Image Captioning: A Causal Retrospect","created":"2020-03-09","cited_by_count":65},{"id":"1903.01306","title":"Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks","created":"2019-03-04","cited_by_count":61},{"id":"1901.06829","title":"Read, Watch, and Move: Reinforcement Learning for Temporally Grounding Natural Language Descriptions in Videos","created":"2019-01-21","cited_by_count":60},{"id":"1412.2309","title":"Visual Causal Feature Learning","created":"2014-12-07","cited_by_count":59},{"id":"1806.06270","title":"Stable Prediction across Unknown Environments","created":"2018-06-16","cited_by_count":55},{"id":"1907.01166","title":"Multimodal Transformer Networks for End-to-End Video-Grounded Dialogue Systems","created":"2019-07-02","cited_by_count":52},{"id":"1812.03253","title":"Counterfactuals uncover the modular structure of deep generative models","created":"2018-12-08","cited_by_count":51},{"id":"2007.02503","title":"Tree-Augmented Cross-Modal Encoding for Complex-Query Video Retrieval","created":"2020-07-06","cited_by_count":47},{"id":"1904.09936","title":"Tripping through time: Efficient Localization of Activities in Videos","created":"2019-04-22","cited_by_count":33},{"id":"2006.15874","title":"Decorrelated Clustering with Data Selection Bias","created":"2020-06-29","cited_by_count":6}],"next_cursor":null}