{"list":"other","total":59,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1411.1784","title":"Conditional Generative Adversarial Nets","created":"2014-11-06","cited_by_count":2162},{"id":"2004.10934","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","created":"2020-04-23","cited_by_count":1630},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"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":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"1412.2306","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","created":"2014-12-07","cited_by_count":968},{"id":"1511.02283","title":"Generation and Comprehension of Unambiguous Object Descriptions","created":"2015-11-07","cited_by_count":904},{"id":"1801.08186","title":"MAttNet: Modular Attention Network for Referring Expression Comprehension","created":"2018-01-24","cited_by_count":431},{"id":"2002.11949","title":"Unbiased Scene Graph Generation from Biased Training","created":"2020-02-27","cited_by_count":356},{"id":"1912.02315","title":"12-in-1: Multi-Task Vision and Language Representation Learning","created":"2019-12-05","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":"1608.00525","title":"Modeling Context Between Objects for Referring Expression Understanding","created":"2016-08-01","cited_by_count":251},{"id":"1911.10500","title":"Causality for Machine Learning","created":"2019-11-24","cited_by_count":243},{"id":"2009.12547","title":"Causal Intervention for Weakly-Supervised Semantic Segmentation","created":"2020-09-26","cited_by_count":229},{"id":"2003.08813","title":"Multi-task Collaborative Network for Joint Referring Expression Comprehension and Segmentation","created":"2020-03-19","cited_by_count":204},{"id":"1908.06354","title":"A Fast and Accurate One-Stage Approach to Visual Grounding","created":"2019-08-18","cited_by_count":195},{"id":"1802.08139","title":"Path-Specific Counterfactual Fairness","created":"2018-02-22","cited_by_count":181},{"id":"1812.03299","title":"Learning to Assemble Neural Module Tree Networks for Visual Grounding","created":"2018-12-08","cited_by_count":140},{"id":"2008.01059","title":"Improving One-stage Visual Grounding by Recursive Sub-query Construction","created":"2020-08-03","cited_by_count":138},{"id":"1511.04164","title":"Natural Language Object Retrieval","created":"2015-11-13","cited_by_count":124},{"id":"2009.13000","title":"Interventional Few-Shot Learning","created":"2020-09-28","cited_by_count":112},{"id":"1909.07072","title":"A Real-Time Cross-modality Correlation Filtering Method for Referring Expression Comprehension","created":"2019-09-16","cited_by_count":111},{"id":"1909.08164","title":"Dynamic Graph Attention for Referring Expression Comprehension","created":"2019-09-18","cited_by_count":111},{"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":"1805.06826","title":"The Blessings of Multiple Causes","created":"2018-05-17","cited_by_count":104},{"id":"1406.5679","title":"Deep Fragment Embeddings for Bidirectional Image Sentence Mapping","created":"2014-06-22","cited_by_count":99},{"id":"1906.01784","title":"Learning to Compose and Reason with Language Tree Structures for Visual Grounding","created":"2019-06-05","cited_by_count":98},{"id":"1903.00839","title":"Improving Referring Expression Grounding with Cross-modal Attention-guided Erasing","created":"2019-03-03","cited_by_count":88},{"id":"1712.01892","title":"Grounding Referring Expressions in Images by Variational Context","created":"2017-12-05","cited_by_count":82},{"id":"1908.07129","title":"Zero-Shot Grounding of Objects from Natural Language Queries","created":"2019-08-20","cited_by_count":79},{"id":"1503.01603","title":"External Validity: From Do-Calculus to Transportability Across Populations","created":"2015-03-05","cited_by_count":75},{"id":"1911.10496","title":"Two Causal Principles for Improving Visual Dialog","created":"2019-11-24","cited_by_count":75},{"id":"2007.02731","title":"SurVAE Flows: Surjections to Bridge the Gap between VAEs and Flows","created":"2020-07-06","cited_by_count":71},{"id":"2003.03923","title":"Deconfounded Image Captioning: A Causal Retrospect","created":"2020-03-09","cited_by_count":65},{"id":"1812.03426","title":"Real-Time Referring Expression Comprehension by Single-Stage Grounding Network","created":"2018-12-09","cited_by_count":56},{"id":"2104.04386","title":"Look Before You Leap: Learning Landmark Features for One-Stage Visual Grounding","created":"2021-04-09","cited_by_count":52},{"id":"1711.08389","title":"Conditional Image-Text Embedding Networks","created":"2017-11-22","cited_by_count":50},{"id":"2009.01449","title":"Ref-NMS: Breaking Proposal Bottlenecks in Two-Stage Referring Expression Grounding","created":"2020-09-03","cited_by_count":50},{"id":"1911.09042","title":"Learning Cross-modal Context Graph for Visual Grounding","created":"2019-11-20","cited_by_count":49},{"id":"1908.10568","title":"Adaptive Reconstruction Network for Weakly Supervised Referring Expression Grounding","created":"2019-08-28","cited_by_count":37},{"id":"1708.01676","title":"Query-guided Regression Network with Context Policy for Phrase Grounding","created":"2017-08-04","cited_by_count":34},{"id":"1908.07553","title":"Phrase Localization Without Paired Training Examples","created":"2019-08-20","cited_by_count":24},{"id":"1902.10286","title":"On Multi-Cause Causal Inference with Unobserved Confounding: Counterexamples, Impossibility, and Alternatives","created":"2019-02-27","cited_by_count":20},{"id":"1903.07669","title":"Neural Sequential Phrase Grounding (SeqGROUND)","created":"2019-03-18","cited_by_count":20},{"id":"1904.03589","title":"Modularized Textual Grounding for Counterfactual Resilience","created":"2019-04-07","cited_by_count":17},{"id":"1907.03609","title":"Variational Context: Exploiting Visual and Textual Context for Grounding Referring Expressions","created":"2019-07-08","cited_by_count":12},{"id":"2105.02061","title":"Proposal-free One-stage Referring Expression via Grid-Word Cross-Attention","created":"2021-05-05","cited_by_count":5},{"id":"2006.03776","title":"MAGNet: Multi-Region Attention-Assisted Grounding of Natural Language Queries at Phrase Level","created":"2020-06-06","cited_by_count":2}],"next_cursor":null}