{"list":"other","total":75,"rows":[{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"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":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"id":"1603.05027","title":"Identity Mappings in Deep Residual Networks","created":"2016-03-16","cited_by_count":1965},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"1602.07261","title":"Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning","created":"2016-02-23","cited_by_count":1512},{"id":"1801.07455","title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2018-01-23","cited_by_count":1209},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"1807.05520","title":"Deep Clustering for Unsupervised Learning of Visual Features","created":"2018-07-15","cited_by_count":1028},{"id":"1604.02808","title":"NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis","created":"2016-04-11","cited_by_count":686},{"id":"1705.02101","title":"TALL: Temporal Activity Localization via Language Query","created":"2017-05-05","cited_by_count":584},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"1905.04757","title":"NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding","created":"2019-05-12","cited_by_count":533},{"id":"1611.05267","title":"Temporal Convolutional Networks for Action Segmentation and Detection","created":"2016-11-16","cited_by_count":508},{"id":"1705.08421","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","created":"2017-05-23","cited_by_count":449},{"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":"1812.02849","title":"A Survey of Unsupervised Deep Domain Adaptation","created":"2018-12-06","cited_by_count":361},{"id":"2202.07925","title":"ActionFormer: Localizing Moments of Actions with Transformers","created":"2022-02-16","cited_by_count":311},{"id":"1911.12667","title":"Self-Supervised Learning by Cross-Modal Audio-Video Clustering","created":"2019-11-28","cited_by_count":267},{"id":"2007.04687","title":"Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision","created":"2020-07-09","cited_by_count":238},{"id":"2111.15668","title":"AdaViT: Adaptive Vision Transformers for Efficient Image Recognition","created":"2021-11-30","cited_by_count":228},{"id":"1801.03150","title":"Moments in Time Dataset: one million videos for event understanding","created":"2018-01-09","cited_by_count":215},{"id":"2208.03550","title":"Frozen CLIP Models are Efficient Video Learners","created":"2022-08-06","cited_by_count":182},{"id":"2004.01398","title":"TEA: Temporal Excitation and Aggregation for Action Recognition","created":"2020-04-03","cited_by_count":165},{"id":"2012.11866","title":"Human Action Recognition from Various Data Modalities: A Review","created":"2020-12-22","cited_by_count":163},{"id":"2005.06803","title":"TAM: Temporal Adaptive Module for Video Recognition","created":"2020-05-14","cited_by_count":139},{"id":"2001.07416","title":"Deep Learning for Sensor-based Human Activity Recognition: Overview, Challenges and Opportunities","created":"2020-01-21","cited_by_count":126},{"id":"1804.09337","title":"Learning a Discriminative Feature Network for Semantic Segmentation","created":"2018-04-25","cited_by_count":114},{"id":"1907.12743","title":"Temporal Attentive Alignment for Large-Scale Video Domain Adaptation","created":"2019-07-30","cited_by_count":100},{"id":"2107.12309","title":"Spatial-Temporal Transformer for Dynamic Scene Graph Generation","created":"2021-07-26","cited_by_count":96},{"id":"1507.05738","title":"Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos","created":"2015-07-21","cited_by_count":93},{"id":"2105.07404","title":"MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actions","created":"2021-05-16","cited_by_count":84},{"id":"2108.11539","title":"TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios","created":"2021-08-26","cited_by_count":83},{"id":"1811.07391","title":"Temporal Recurrent Networks for Online Action Detection","created":"2018-11-18","cited_by_count":80},{"id":"2006.15418","title":"Counting Out Time: Class Agnostic Video Repetition Counting in the Wild","created":"2020-06-27","cited_by_count":68},{"id":"2303.03729","title":"Learning Discriminative Representations for Skeleton Based Action Recognition","created":"2023-03-07","cited_by_count":62},{"id":"1902.10322","title":"Spatio-Temporal Dynamics and Semantic Attribute Enriched Visual Encoding for Video Captioning","created":"2019-02-27","cited_by_count":60},{"id":"1605.04988","title":"Going Deeper into Action Recognition: A Survey","created":"2016-05-16","cited_by_count":55},{"id":"2105.04489","title":"Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptions","created":"2021-05-10","cited_by_count":53},{"id":"2105.05226","title":"Home Action Genome: Cooperative Compositional Action Understanding","created":"2021-05-11","cited_by_count":53},{"id":"2004.11246","title":"SensitiveLoss: Improving Accuracy and Fairness of Face Representations with Discrimination-Aware Deep Learning","created":"2020-04-22","cited_by_count":50},{"id":"2102.02751","title":"Semi-Supervised Action Recognition with Temporal Contrastive Learning","created":"2021-02-04","cited_by_count":50},{"id":"2108.09322","title":"MM-ViT: Multi-Modal Video Transformer for Compressed Video Action Recognition","created":"2021-08-20","cited_by_count":46},{"id":"1801.03149","title":"An overview of deep learning based methods for unsupervised and semi-supervised anomaly detection in videos","created":"2018-01-09","cited_by_count":45},{"id":"1911.00232","title":"Multi-Moments in Time: Learning and Interpreting Models for Multi-Action Video Understanding","created":"2019-11-01","cited_by_count":37},{"id":"2108.11244","title":"Multiscale Spatio-Temporal Graph Neural Networks for 3D Skeleton-Based Motion Prediction","created":"2021-08-25","cited_by_count":37},{"id":"2203.10233","title":"DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition","created":"2022-03-19","cited_by_count":31},{"id":"2207.12100","title":"IGFormer: Interaction Graph Transformer for Skeleton-based Human Interaction Recognition","created":"2022-07-25","cited_by_count":31},{"id":"2107.04932","title":"Aligning Correlation Information for Domain Adaptation in Action Recognition","created":"2021-07-11","cited_by_count":30},{"id":"2111.14834","title":"Self-supervised Autoregressive Domain Adaptation for Time Series Data","created":"2021-11-29","cited_by_count":29},{"id":"1604.05633","title":"Online Human Action Detection using Joint Classification-Regression Recurrent Neural Networks","created":"2016-04-19","cited_by_count":28},{"id":"2202.04075","title":"Joint-bone Fusion Graph Convolutional Network for Semi-supervised Skeleton Action Recognition","created":"2022-02-08","cited_by_count":24},{"id":"2012.11806","title":"Graph and Temporal Convolutional Networks for 3D Multi-person Pose Estimation in Monocular Videos","created":"2020-12-22","cited_by_count":23},{"id":"1502.01812","title":"Crowded Scene Analysis: A Survey","created":"2015-02-06","cited_by_count":21},{"id":"2001.03886","title":"Multi-source Domain Adaptation for Visual Sentiment Classification","created":"2020-01-12","cited_by_count":16},{"id":"2004.08058","title":"Generative Adversarial Networks for Video-to-Video Domain Adaptation","created":"2020-04-17","cited_by_count":11},{"id":"2208.05251","title":"Consistency-based Self-supervised Learning for Temporal Anomaly Localization","created":"2022-08-10","cited_by_count":10},{"id":"2105.01342","title":"An Empirical Review of Deep Learning Frameworks for Change Detection: Model Design, Experimental Frameworks, Challenges and Research Needs","created":"2021-05-04","cited_by_count":9},{"id":"1705.06709","title":"Learning Spatiotemporal Features for Infrared Action Recognition with 3D Convolutional Neural Networks","created":"2017-05-18","cited_by_count":8},{"id":"2006.08247","title":"Learn to cycle: Time-consistent feature discovery for action recognition","created":"2020-06-15","cited_by_count":8},{"id":"2001.04129","title":"Incremental Unsupervised Domain-Adversarial Training of Neural Networks","created":"2020-01-13","cited_by_count":7},{"id":"1711.04161","title":"End-to-end Video-level Representation Learning for Action Recognition","created":"2017-11-11","cited_by_count":4},{"id":"1812.07124","title":"Multi-Level Sequence GAN for Group Activity Recognition","created":"2018-12-18","cited_by_count":3},{"id":"2103.10023","title":"Discriminative and Semantic Feature Selection for Place Recognition towards Dynamic Environments","created":"2021-03-18","cited_by_count":1},{"id":"2108.07897","title":"Affect-Aware Deep Belief Network Representations for Multimodal Unsupervised Deception Detection","created":"2021-08-17","cited_by_count":1},{"id":"2110.09819","title":"LSTC: Boosting Atomic Action Detection with Long-Short-Term Context","created":"2021-10-19","cited_by_count":1},{"id":"2112.12409","title":"InstaIndoor and Multi-modal Deep Learning for Indoor Scene Recognition","created":"2021-12-23","cited_by_count":1}],"next_cursor":null}