{"list":"other","total":63,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1704.01212","title":"Neural Message Passing for Quantum Chemistry","created":"2017-04-04","cited_by_count":3487},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"1902.09630","title":"Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression","created":"2019-02-25","cited_by_count":1368},{"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":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"1911.09070","title":"EfficientDet: Scalable and Efficient Object Detection","created":"2019-11-20","cited_by_count":1020},{"id":"1511.05493","title":"Gated Graph Sequence Neural Networks","created":"2015-11-17","cited_by_count":796},{"id":"1802.05751","title":"Image Transformer","created":"2018-02-15","cited_by_count":772},{"id":"1612.00563","title":"Self-critical Sequence Training for Image Captioning","created":"2016-12-02","cited_by_count":547},{"id":"1701.02426","title":"Scene Graph Generation by Iterative Message Passing","created":"2017-01-10","cited_by_count":462},{"id":"1711.06640","title":"Neural Motifs: Scene Graph Parsing with Global Context","created":"2017-11-17","cited_by_count":414},{"id":"1912.08226","title":"Meshed-Memory Transformer for Image Captioning","created":"2019-12-17","cited_by_count":343},{"id":"1808.00191","title":"Graph R-CNN for Scene Graph Generation","created":"2018-08-01","cited_by_count":298},{"id":"1904.04745","title":"Cross-Modal Self-Attention Network for Referring Image Segmentation","created":"2019-04-09","cited_by_count":263},{"id":"1603.03925","title":"Image Captioning with Semantic Attention","created":"2016-03-12","cited_by_count":260},{"id":"1612.06321","title":"Large-Scale Image Retrieval with Attentive Deep Local Features","created":"2016-12-19","cited_by_count":238},{"id":"1611.05594","title":"SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning","created":"2016-11-17","cited_by_count":219},{"id":"2106.08322","title":"Dynamic Head: Unifying Object Detection Heads with Attentions","created":"2021-06-15","cited_by_count":187},{"id":"2004.03548","title":"Temporal Pyramid Network for Action Recognition","created":"2020-04-07","cited_by_count":163},{"id":"1707.09700","title":"Scene Graph Generation from Objects, Phrases and Region Captions","created":"2017-07-31","cited_by_count":154},{"id":"2003.06576","title":"Counterfactual Samples Synthesizing for Robust Visual Question Answering","created":"2020-03-14","cited_by_count":153},{"id":"1912.12898","title":"PPDM: Parallel Point Detection and Matching for Real-time Human-Object Interaction Detection","created":"2019-12-30","cited_by_count":143},{"id":"2107.06912","title":"From Show to Tell: A Survey on Deep Learning-based Image Captioning","created":"2021-07-14","cited_by_count":138},{"id":"1903.12314","title":"Relation-Aware Graph Attention Network for Visual Question Answering","created":"2019-03-29","cited_by_count":119},{"id":"2106.08503","title":"Understanding and Evaluating Racial Biases in Image Captioning","created":"2021-06-16","cited_by_count":108},{"id":"2107.12309","title":"Spatial-Temporal Transformer for Dynamic Scene Graph Generation","created":"2021-07-26","cited_by_count":96},{"id":"2003.12058","title":"Grounded Situation Recognition","created":"2020-03-26","cited_by_count":78},{"id":"1804.08199","title":"Linguistically-Informed Self-Attention for Semantic Role Labeling","created":"2018-04-23","cited_by_count":71},{"id":"1902.09487","title":"MUREL: Multimodal Relational Reasoning for Visual Question Answering","created":"2019-02-25","cited_by_count":68},{"id":"2112.06197","title":"Video as Conditional Graph Hierarchy for Multi-Granular Question Answering","created":"2021-12-12","cited_by_count":68},{"id":"1712.06761","title":"MovieGraphs: Towards Understanding Human-Centric Situations from Videos","created":"2017-12-19","cited_by_count":67},{"id":"2108.02432","title":"Token Shift Transformer for Video Classification","created":"2021-08-05","cited_by_count":61},{"id":"2104.00990","title":"Visual Semantic Role Labeling for Video Understanding","created":"2021-04-02","cited_by_count":60},{"id":"1812.02347","title":"Counterfactual Critic Multi-Agent Training for Scene Graph Generation","created":"2018-12-06","cited_by_count":53},{"id":"2012.07061","title":"Improving Image Captioning by Leveraging Intra- and Inter-layer Global Representation in Transformer Network","created":"2020-12-13","cited_by_count":48},{"id":"2103.08784","title":"LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrieval","created":"2021-03-16","cited_by_count":44},{"id":"2103.13886","title":"Robust and Accurate Object Detection via Adversarial Learning","created":"2021-03-23","cited_by_count":42},{"id":"1708.04320","title":"Situation Recognition with Graph Neural Networks","created":"2017-08-14","cited_by_count":34},{"id":"1804.05287","title":"Video2Shop: Exact Matching Clothes in Videos to Online Shopping Images","created":"2018-04-14","cited_by_count":26},{"id":"2105.03236","title":"Towards Accurate Text-based Image Captioning with Content Diversity Exploration","created":"2021-04-23","cited_by_count":25},{"id":"1712.01586","title":"Deep Semantic Role Labeling with Self-Attention","created":"2017-12-05","cited_by_count":23},{"id":"2203.16518","title":"Collaborative Transformers for Grounded Situation Recognition","created":"2022-03-30","cited_by_count":19},{"id":"2203.09694","title":"Group Contextualization for Video Recognition","created":"2022-03-18","cited_by_count":18},{"id":"1804.06964","title":"GNAS: A Greedy Neural Architecture Search Method for Multi-Attribute Learning","created":"2018-04-19","cited_by_count":17},{"id":"2112.05375","title":"Rethinking the Two-Stage Framework for Grounded Situation Recognition","created":"2021-12-10","cited_by_count":16},{"id":"1612.04520","title":"Single Image Action Recognition using Semantic Body Part Actions","created":"2016-12-14","cited_by_count":14},{"id":"2111.10135","title":"Grounded Situation Recognition with Transformers","created":"2021-11-19","cited_by_count":14},{"id":"1612.00901","title":"Commonly Uncommon: Semantic Sparsity in Situation Recognition","created":"2016-12-03","cited_by_count":13},{"id":"1703.06233","title":"Recurrent Models for Situation Recognition","created":"2017-03-18","cited_by_count":13},{"id":"1804.05286","title":"On the Selection of Anchors and Targets for Video Hyperlinking","created":"2018-04-14","cited_by_count":9},{"id":"2008.05156","title":"HOSE-Net: Higher Order Structure Embedded Network for Scene Graph Generation","created":"2020-08-12","cited_by_count":9}],"next_cursor":null}