{"list":"other","total":56,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"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":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"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":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013},{"id":"1908.08530","title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations","created":"2019-08-22","cited_by_count":954},{"id":"1802.08218","title":"VizWiz Grand Challenge: Answering Visual Questions from Blind People","created":"2018-02-22","cited_by_count":858},{"id":"1710.09829","title":"Dynamic Routing Between Capsules","created":"2017-10-26","cited_by_count":689},{"id":"1908.06066","title":"Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training","created":"2019-08-16","cited_by_count":451},{"id":"2006.06666","title":"VirTex: Learning Visual Representations from Textual Annotations","created":"2020-06-11","cited_by_count":339},{"id":"1608.00507","title":"Top-down Neural Attention by Excitation Backprop","created":"2016-08-01","cited_by_count":321},{"id":"1511.03416","title":"Visual7W: Grounded Question Answering in Images","created":"2015-11-11","cited_by_count":318},{"id":"2004.00849","title":"Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Transformers","created":"2020-04-02","cited_by_count":288},{"id":"1606.00061","title":"Hierarchical Question-Image Co-Attention for Visual Question Answering","created":"2016-05-31","cited_by_count":278},{"id":"1912.02315","title":"12-in-1: Multi-Task Vision and Language Representation Learning","created":"2019-12-05","cited_by_count":278},{"id":"1511.02274","title":"Stacked Attention Networks for Image Question Answering","created":"2015-11-07","cited_by_count":273},{"id":"2006.04315","title":"Counterfactual VQA: A Cause-Effect Look at Language Bias","created":"2020-06-08","cited_by_count":266},{"id":"1909.11740","title":"UNITER: UNiversal Image-TExt Representation Learning","created":"2019-09-25","cited_by_count":228},{"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":"1803.03067","title":"Compositional Attention Networks for Machine Reasoning","created":"2018-03-08","cited_by_count":183},{"id":"1902.03751","title":"Taking a HINT: Leveraging Explanations to Make Vision and Language Models More Grounded","created":"2019-02-11","cited_by_count":128},{"id":"2102.12627","title":"How to represent part-whole hierarchies in a neural network","created":"2021-02-25","cited_by_count":123},{"id":"1606.03556","title":"Human Attention in Visual Question Answering: Do Humans and Deep Networks Look at the Same Regions?","created":"2016-06-11","cited_by_count":111},{"id":"1810.03649","title":"Overcoming Language Priors in Visual Question Answering with Adversarial Regularization","created":"2018-10-08","cited_by_count":105},{"id":"2103.16553","title":"Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers","created":"2021-03-30","cited_by_count":93},{"id":"2109.06082","title":"xGQA: Cross-Lingual Visual Question Answering","created":"2021-09-13","cited_by_count":72},{"id":"1906.02549","title":"Weakly-Supervised Spatio-Temporally Grounding Natural Sentence in Video","created":"2019-06-06","cited_by_count":60},{"id":"1903.11649","title":"Align2Ground: Weakly Supervised Phrase Grounding Guided by Image-Caption Alignment","created":"2019-03-27","cited_by_count":51},{"id":"2007.01951","title":"Improving Weakly Supervised Visual Grounding by Contrastive Knowledge Distillation","created":"2020-07-03","cited_by_count":51},{"id":"2101.12491","title":"Efficient-CapsNet: Capsule Network with Self-Attention Routing","created":"2021-01-29","cited_by_count":41},{"id":"1705.01371","title":"Weakly-supervised Visual Grounding of Phrases with Linguistic Structures","created":"2017-05-03","cited_by_count":40},{"id":"1709.06308","title":"Exploring Human-like Attention Supervision in Visual Question Answering","created":"2017-09-19","cited_by_count":36},{"id":"2103.12989","title":"Relation-aware Instance Refinement for Weakly Supervised Visual Grounding","created":"2021-03-24","cited_by_count":35},{"id":"1803.03879","title":"Knowledge Aided Consistency for Weakly Supervised Phrase Grounding","created":"2018-03-11","cited_by_count":32},{"id":"1804.04241","title":"Capsules for Object Segmentation","created":"2018-04-11","cited_by_count":30},{"id":"1805.08162","title":"VideoCapsuleNet: A Simplified Network for Action Detection","created":"2018-05-21","cited_by_count":30},{"id":"1910.00132","title":"CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule Routing","created":"2019-09-30","cited_by_count":29},{"id":"1808.00265","title":"Interpretable Visual Question Answering by Visual Grounding from Attention Supervision Mining","created":"2018-08-01","cited_by_count":28},{"id":"2107.09106","title":"Separating Skills and Concepts for Novel Visual Question Answering","created":"2021-07-19","cited_by_count":24},{"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":"2102.08606","title":"Centroid Transformers: Learning to Abstract with Attention","created":"2021-02-17","cited_by_count":20},{"id":"1612.06530","title":"Automatic Generation of Grounded Visual Questions","created":"2016-12-20","cited_by_count":19},{"id":"2010.03160","title":"Vision Skills Needed to Answer Visual Questions","created":"2020-10-07","cited_by_count":17},{"id":"2104.09829","title":"Detector-Free Weakly Supervised Grounding by Separation","created":"2021-04-20","cited_by_count":16},{"id":"2206.02664","title":"Learning with Capsules: A Survey","created":"2022-06-06","cited_by_count":10},{"id":"1909.00188","title":"Improving Multi-Head Attention with Capsule Networks","created":"2019-08-31","cited_by_count":6},{"id":"2004.14649","title":"Capsule-Transformer for Neural Machine Translation","created":"2020-04-30","cited_by_count":2}],"next_cursor":null}