{"list":"other","total":53,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"1409.1259","title":"On the Properties of Neural Machine Translation: Encoder-Decoder Approaches","created":"2014-09-03","cited_by_count":1304},{"id":"1812.08008","title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2018-12-18","cited_by_count":1162},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"1602.07360","title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size","created":"2016-02-24","cited_by_count":1060},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"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":"1906.08172","title":"MediaPipe: A Framework for Building Perception Pipelines","created":"2019-06-14","cited_by_count":583},{"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":"1912.08193","title":"PointRend: Image Segmentation as Rendering","created":"2019-12-17","cited_by_count":440},{"id":"1612.00137","title":"RMPE: Regional Multi-person Pose Estimation","created":"2016-12-01","cited_by_count":340},{"id":"1808.01340","title":"A Short Note about Kinetics-600","created":"2018-08-03","cited_by_count":333},{"id":"2104.13586","title":"Revisiting Skeleton-based Action Recognition","created":"2021-04-28","cited_by_count":257},{"id":"2211.03375","title":"AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time","created":"2022-11-07","cited_by_count":200},{"id":"1505.04474","title":"Visual Semantic Role Labeling","created":"2015-05-17","cited_by_count":190},{"id":"2004.03548","title":"Temporal Pyramid Network for Action Recognition","created":"2020-04-07","cited_by_count":163},{"id":"2005.06803","title":"TAM: Temporal Adaptive Module for Video Recognition","created":"2020-05-14","cited_by_count":139},{"id":"1405.2941","title":"Cross-view Action Modeling, Learning and Recognition","created":"2014-05-12","cited_by_count":134},{"id":"1803.08225","title":"PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model","created":"2018-03-22","cited_by_count":133},{"id":"1808.10437","title":"iCAN: Instance-Centric Attention Network for Human-Object Interaction Detection","created":"2018-08-30","cited_by_count":127},{"id":"1802.09232","title":"2D/3D Pose Estimation and Action Recognition using Multitask Deep Learning","created":"2018-02-26","cited_by_count":103},{"id":"1703.07475","title":"PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understanding","created":"2017-03-22","cited_by_count":101},{"id":"1605.03170","title":"DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model","created":"2016-05-10","cited_by_count":96},{"id":"1910.13796","title":"Deep Learning vs. Traditional Computer Vision","created":"2019-10-30","cited_by_count":94},{"id":"2010.10864","title":"A Short Note on the Kinetics-700-2020 Human Action Dataset","created":"2020-10-21","cited_by_count":92},{"id":"1911.11206","title":"Oops! Predicting Unintentional Action in Video","created":"2019-11-25","cited_by_count":82},{"id":"1802.00977","title":"Pose Flow: Efficient Online Pose Tracking","created":"2018-02-03","cited_by_count":80},{"id":"1404.3606","title":"PCANet: A Simple Deep Learning Baseline for Image Classification?","created":"2014-04-14","cited_by_count":70},{"id":"2004.07485","title":"Asynchronous Interaction Aggregation for Action Detection","created":"2020-04-16","cited_by_count":65},{"id":"1805.07631","title":"Learning to Detect","created":"2018-05-19","cited_by_count":63},{"id":"2010.14742","title":"ElderSim: A Synthetic Data Generation Platform for Human Action Recognition in Eldercare Applications","created":"2020-10-28","cited_by_count":29},{"id":"1409.6813","title":"Histogram of Oriented Principal Components for Cross-View Action Recognition","created":"2014-09-24","cited_by_count":27},{"id":"2003.01920","title":"ETRI-Activity3D: A Large-Scale RGB-D Dataset for Robots to Recognize Daily Activities of the Elderly","created":"2020-03-04","cited_by_count":26},{"id":"1908.05593","title":"FastPose: Towards Real-time Pose Estimation and Tracking via Scale-normalized Multi-task Networks","created":"2019-08-15","cited_by_count":15},{"id":"1704.04057","title":"DCFNet: Discriminant Correlation Filters Network for Visual Tracking","created":"2017-04-13","cited_by_count":11},{"id":"2007.07773","title":"Vision-Based Fall Event Detection in Complex Background Using Attention Guided Bi-directional LSTM","created":"2020-06-24","cited_by_count":9},{"id":"2206.12740","title":"Multi Visual Modality Fall Detection Dataset","created":"2022-06-25","cited_by_count":7},{"id":"2207.10952","title":"Vision-based Human Fall Detection Systems using Deep Learning: A Review","created":"2022-07-22","cited_by_count":7}],"next_cursor":null}