{"list":"other","total":74,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"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":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"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":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"2004.11362","title":"Supervised Contrastive Learning","created":"2020-04-23","cited_by_count":2829},{"id":"1306.0895","title":"Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances","created":"2013-06-04","cited_by_count":2316},{"id":"2006.10739","title":"Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains","created":"2020-06-18","cited_by_count":2200},{"id":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"id":"1801.07455","title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2018-01-23","cited_by_count":1209},{"id":"1603.06937","title":"Stacked Hourglass Networks for Human Pose Estimation","created":"2016-03-22","cited_by_count":915},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"2103.00112","title":"Transformer in Transformer","created":"2021-02-27","cited_by_count":633},{"id":"1811.11742","title":"3D human pose estimation in video with temporal convolutions and semi-supervised training","created":"2018-11-28","cited_by_count":403},{"id":"1904.11490","title":"RepPoints: Point Set Representation for Object Detection","created":"2019-04-25","cited_by_count":264},{"id":"1912.06992","title":"Action Genome: Actions as Composition of Spatio-temporal Scene Graphs","created":"2019-12-15","cited_by_count":250},{"id":"2004.06704","title":"FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding","created":"2020-04-14","cited_by_count":234},{"id":"2106.05392","title":"Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers","created":"2021-06-09","cited_by_count":224},{"id":"1803.03067","title":"Compositional Attention Networks for Machine Reasoning","created":"2018-03-08","cited_by_count":183},{"id":"2106.08417","title":"Scene Transformer: A unified architecture for predicting multiple agent trajectories","created":"2021-06-15","cited_by_count":165},{"id":"2003.08802","title":"Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Prediction","created":"2020-03-17","cited_by_count":132},{"id":"2103.16002","title":"AGQA: A Benchmark for Compositional Spatio-Temporal Reasoning","created":"2021-03-30","cited_by_count":120},{"id":"1912.05534","title":"Why Can't I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognition","created":"2019-12-11","cited_by_count":117},{"id":"1912.09930","title":"Something-Else: Compositional Action Recognition with Spatial-Temporal Interaction Networks","created":"2019-12-20","cited_by_count":114},{"id":"1511.06361","title":"Order-Embeddings of Images and Language","created":"2015-11-19","cited_by_count":113},{"id":"1907.03950","title":"Learning by Abstraction: The Neural State Machine","created":"2019-07-09","cited_by_count":113},{"id":"2006.10204","title":"BlazePose: On-device Real-time Body Pose tracking","created":"2020-06-17","cited_by_count":113},{"id":"1906.11883","title":"Unsupervised Learning of Object Keypoints for Perception and Control","created":"2019-06-19","cited_by_count":109},{"id":"2006.13662","title":"Labelling unlabelled videos from scratch with multi-modal self-supervision","created":"2020-06-24","cited_by_count":100},{"id":"2010.05599","title":"MS$^2$L: Multi-Task Self-Supervised Learning for Skeleton Based Action Recognition","created":"2020-10-12","cited_by_count":92},{"id":"2001.03152","title":"Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias","created":"2020-01-09","cited_by_count":91},{"id":"1607.02643","title":"Hierarchical Deep Temporal Models for Group Activity Recognition","created":"2016-07-09","cited_by_count":89},{"id":"2003.12737","title":"Actor-Transformers for Group Activity Recognition","created":"2020-03-28","cited_by_count":84},{"id":"1904.10117","title":"Learning Actor Relation Graphs for Group Activity Recognition","created":"2019-04-23","cited_by_count":83},{"id":"1603.07772","title":"Co-occurrence Feature Learning for Skeleton based Action Recognition using Regularized Deep LSTM Networks","created":"2016-03-24","cited_by_count":63},{"id":"2104.12671","title":"Multimodal Clustering Networks for Self-supervised Learning from Unlabeled Videos","created":"2021-04-26","cited_by_count":62},{"id":"2108.05885","title":"The paradox of the compositionality of natural language: a neural machine translation case study","created":"2021-08-12","cited_by_count":59},{"id":"2108.12630","title":"GroupFormer: Group Activity Recognition with Clustered Spatial-Temporal Transformer","created":"2021-08-28","cited_by_count":54},{"id":"2105.05226","title":"Home Action Genome: Cooperative Compositional Action Understanding","created":"2021-05-11","cited_by_count":53},{"id":"2101.01600","title":"Learning the Predictability of the Future","created":"2021-01-01","cited_by_count":49},{"id":"1912.01001","title":"View-Invariant Probabilistic Embedding for Human Pose","created":"2019-12-02","cited_by_count":47},{"id":"2007.15781","title":"LEMMA: A Multi-view Dataset for Learning Multi-agent Multi-task Activities","created":"2020-07-31","cited_by_count":47},{"id":"2101.09387","title":"Online Adversarial Purification based on Self-Supervision","created":"2021-01-23","cited_by_count":46},{"id":"1611.09078","title":"Social Scene Understanding: End-to-End Multi-Person Action Localization and Collective Activity Recognition","created":"2016-11-28","cited_by_count":43},{"id":"2007.09470","title":"Social Adaptive Module for Weakly-supervised Group Activity Recognition","created":"2020-07-18","cited_by_count":42},{"id":"2108.11743","title":"Spatio-Temporal Dynamic Inference Network for Group Activity Recognition","created":"2021-08-26","cited_by_count":42},{"id":"2007.02632","title":"Joint Learning of Social Groups, Individuals Action and Sub-group Activities in Videos","created":"2020-07-06","cited_by_count":39},{"id":"1811.00270","title":"Hierarchical Long Short-Term Concurrent Memory for Human Interaction Recognition","created":"2018-11-01","cited_by_count":36},{"id":"1904.03308","title":"Convolutional Relational Machine for Group Activity Recognition","created":"2019-04-05","cited_by_count":34},{"id":"1908.02948","title":"Progressive Relation Learning for Group Activity Recognition","created":"2019-08-08","cited_by_count":28},{"id":"1511.04196","title":"Structure Inference Machines: Recurrent Neural Networks for Analyzing Relations in Group Activity Recognition","created":"2015-11-13","cited_by_count":27},{"id":"1910.04963","title":"Interaction Relational Network for Mutual Action Recognition","created":"2019-10-11","cited_by_count":27},{"id":"2111.13089","title":"GeomNet: A Neural Network Based on Riemannian Geometries of SPD Matrix Space and Cholesky Space for 3D Skeleton-Based Interaction Recognition","created":"2021-11-25","cited_by_count":27},{"id":"1511.02917","title":"Detecting events and key actors in multi-person videos","created":"2015-11-09","cited_by_count":26},{"id":"1609.02077","title":"Visual Saliency Detection Based on Multiscale Deep CNN Features","created":"2016-09-07","cited_by_count":26},{"id":"1704.03058","title":"CERN: Confidence-Energy Recurrent Network for Group Activity Recognition","created":"2017-04-10","cited_by_count":24},{"id":"1912.02323","title":"15 Keypoints Is All You Need","created":"2019-12-05","cited_by_count":23},{"id":"2012.01405","title":"Learning View-Disentangled Human Pose Representation by Contrastive Cross-View Mutual Information Maximization","created":"2020-12-02","cited_by_count":19},{"id":"2011.05653","title":"Skeleton-based Relational Reasoning for Group Activity Analysis","created":"2020-11-11","cited_by_count":18},{"id":"2104.10068","title":"Contrastive Learning for Sports Video: Unsupervised Player Classification","created":"2021-04-15","cited_by_count":17},{"id":"2108.04186","title":"Pose is all you need: The pose only group activity recognition system (POGARS)","created":"2021-08-09","cited_by_count":16},{"id":"2012.05689","title":"Interactive Fusion of Multi-level Features for Compositional Activity Recognition","created":"2020-12-10","cited_by_count":9},{"id":"1502.02063","title":"Visual Recognition by Counting Instances: A Multi-Instance Cardinality Potential Kernel","created":"2015-02-06","cited_by_count":7},{"id":"2012.02109","title":"SAFCAR: Structured Attention Fusion for Compositional Action Recognition","created":"2020-12-03","cited_by_count":4},{"id":"2105.06754","title":"Learning Group Activities from Skeletons without Individual Action Labels","created":"2021-05-14","cited_by_count":4}],"next_cursor":null}