{"list":"other","total":51,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"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":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1296},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744},{"id":"1906.02467","title":"ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering","created":"2019-06-06","cited_by_count":561},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"1910.01442","title":"CLEVRER: CoLlision Events for Video REpresentation and Reasoning","created":"2019-10-03","cited_by_count":484},{"id":"2102.06183","title":"Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling","created":"2021-02-11","cited_by_count":484},{"id":"1809.01696","title":"TVQA: Localized, Compositional Video Question Answering","created":"2018-09-05","cited_by_count":467},{"id":"1704.04497","title":"TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question Answering","created":"2017-04-14","cited_by_count":378},{"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":"2106.02636","title":"MERLOT: Multimodal Neural Script Knowledge Models","created":"2021-06-04","cited_by_count":311},{"id":"1512.02902","title":"MovieQA: Understanding Stories in Movies through Question-Answering","created":"2015-12-09","cited_by_count":304},{"id":"1810.02338","title":"Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding","created":"2018-10-04","cited_by_count":304},{"id":"2012.00451","title":"Just Ask: Learning to Answer Questions from Millions of Narrated Videos","created":"2020-12-01","cited_by_count":248},{"id":"2006.16934","title":"ERNIE-ViL: Knowledge Enhanced Vision-Language Representations Through Scene Graph","created":"2020-06-30","cited_by_count":211},{"id":"2207.02505","title":"Pure Transformers are Powerful Graph Learners","created":"2022-07-06","cited_by_count":188},{"id":"2201.02639","title":"MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound","created":"2022-01-07","cited_by_count":184},{"id":"1708.07632","title":"Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition","created":"2017-08-25","cited_by_count":178},{"id":"2002.10698","title":"Hierarchical Conditional Relation Networks for Video Question Answering","created":"2020-02-25","cited_by_count":163},{"id":"1904.04357","title":"Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answering","created":"2019-04-08","cited_by_count":146},{"id":"2012.11014","title":"KRISP: Integrating Implicit and Symbolic Knowledge for Open-Domain Knowledge-Based VQA","created":"2020-12-20","cited_by_count":125},{"id":"2104.01111","title":"A Comprehensive Survey of Scene Graphs: Generation and Application","created":"2021-03-17","cited_by_count":125},{"id":"2103.16002","title":"AGQA: A Benchmark for Compositional Spatio-Temporal Reasoning","created":"2021-03-30","cited_by_count":120},{"id":"1903.12314","title":"Relation-Aware Graph Attention Network for Visual Question Answering","created":"2019-03-29","cited_by_count":119},{"id":"1812.01855","title":"Explainable and Explicit Visual Reasoning over Scene Graphs","created":"2018-12-05","cited_by_count":103},{"id":"1803.10906","title":"Motion-Appearance Co-Memory Networks for Video Question Answering","created":"2018-03-29","cited_by_count":95},{"id":"2203.01225","title":"Video Question Answering: Datasets, Algorithms and Challenges","created":"2022-03-02","cited_by_count":84},{"id":"2201.00443","title":"Scene Graph Generation: A Comprehensive Survey","created":"2022-01-03","cited_by_count":73},{"id":"2112.06197","title":"Video as Conditional Graph Hierarchy for Multi-Granular Question Answering","created":"2021-12-12","cited_by_count":68},{"id":"1611.04021","title":"Leveraging Video Descriptions to Learn Video Question Answering","created":"2016-11-12","cited_by_count":55},{"id":"1905.04405","title":"Language-Conditioned Graph Networks for Relational Reasoning","created":"2019-05-10","cited_by_count":55},{"id":"2012.05710","title":"Look Before you Speak: Visually Contextualized Utterances","created":"2020-12-10","cited_by_count":53},{"id":"2007.12146","title":"Spatially Aware Multimodal Transformers for TextVQA","created":"2020-07-23","cited_by_count":44},{"id":"1611.07810","title":"A dataset and exploration of models for understanding video data through fill-in-the-blank question-answering","created":"2016-11-23","cited_by_count":41},{"id":"2010.14095","title":"MMFT-BERT: Multimodal Fusion Transformer with BERT Encodings for Visual Question Answering","created":"2020-10-27","cited_by_count":30},{"id":"2106.13432","title":"Hierarchical Object-oriented Spatio-Temporal Reasoning for Video Question Answering","created":"2021-06-25","cited_by_count":29},{"id":"2106.10446","title":"Attend What You Need: Motion-Appearance Synergistic Networks for Video Question Answering","created":"2021-06-19","cited_by_count":26},{"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":"2101.05479","title":"Understanding the Role of Scene Graphs in Visual Question Answering","created":"2021-01-14","cited_by_count":20},{"id":"2101.05954","title":"Recent Advances in Video Question Answering: A Review of Datasets and Methods","created":"2021-01-15","cited_by_count":12},{"id":"2204.06105","title":"AGQA 2.0: An Updated Benchmark for Compositional Spatio-Temporal Reasoning","created":"2022-04-12","cited_by_count":10}],"next_cursor":null}