{"list":"other","total":73,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"1811.12231","title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","created":"2018-11-29","cited_by_count":1432},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"1904.08405","title":"Event-based Vision: A Survey","created":"2019-04-17","cited_by_count":1016},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"1709.02371","title":"PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume","created":"2017-09-07","cited_by_count":968},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"1811.08383","title":"TSM: Temporal Shift Module for Efficient Video Understanding","created":"2018-11-20","cited_by_count":856},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"2004.04730","title":"X3D: Expanding Architectures for Efficient Video Recognition","created":"2020-04-09","cited_by_count":637},{"id":"2106.04803","title":"CoAtNet: Marrying Convolution and Attention for All Data Sizes","created":"2021-06-09","cited_by_count":569},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"1712.04851","title":"Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification","created":"2017-12-13","cited_by_count":521},{"id":"1411.4389","title":"Long-term Recurrent Convolutional Networks for Visual Recognition and Description","created":"2014-11-17","cited_by_count":484},{"id":"1711.10305","title":"Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks","created":"2017-11-28","cited_by_count":387},{"id":"2003.10580","title":"Meta Pseudo Labels","created":"2020-03-23","cited_by_count":374},{"id":"1712.00080","title":"Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation","created":"2017-11-30","cited_by_count":326},{"id":"1711.08496","title":"Temporal Relational Reasoning in Videos","created":"2017-11-22","cited_by_count":324},{"id":"1812.08156","title":"Unsupervised Event-based Learning of Optical Flow, Depth, and Egomotion","created":"2018-12-19","cited_by_count":307},{"id":"2103.06011","title":"DSEC: A Stereo Event Camera Dataset for Driving Scenarios","created":"2021-03-10","cited_by_count":303},{"id":"1904.02811","title":"Video Classification with Channel-Separated Convolutional Networks","created":"2019-04-04","cited_by_count":290},{"id":"1705.02953","title":"Temporal Segment Networks for Action Recognition in Videos","created":"2017-05-08","cited_by_count":279},{"id":"1704.02463","title":"First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations","created":"2017-04-08","cited_by_count":230},{"id":"1908.08498","title":"EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition","created":"2019-08-22","cited_by_count":226},{"id":"1803.07913","title":"HATS: Histograms of Averaged Time Surfaces for Robust Event-based Object Classification","created":"2018-03-21","cited_by_count":218},{"id":"1904.08245","title":"End-to-End Learning of Representations for Asynchronous Event-Based Data","created":"2019-04-17","cited_by_count":217},{"id":"2106.02036","title":"Anticipative Video Transformer","created":"2021-06-03","cited_by_count":200},{"id":"2009.13436","title":"Learning to Detect Objects with a 1 Megapixel Event Camera","created":"2020-09-28","cited_by_count":186},{"id":"1912.03095","title":"Video to Events: Recycling Video Datasets for Event Cameras","created":"2019-12-06","cited_by_count":165},{"id":"2108.10552","title":"E-RAFT: Dense Optical Flow from Event Cameras","created":"2021-08-24","cited_by_count":152},{"id":"1904.03375","title":"Modeling Point Clouds with Self-Attention and Gumbel Subset Sampling","created":"2019-04-06","cited_by_count":151},{"id":"2106.07286","title":"TimeLens: Event-based Video Frame Interpolation","created":"2021-06-14","cited_by_count":151},{"id":"2005.02190","title":"Rolling-Unrolling LSTMs for Action Anticipation from First-Person Video","created":"2020-05-04","cited_by_count":120},{"id":"2001.09691","title":"Multi-Modal Domain Adaptation for Fine-Grained Action Recognition","created":"2020-01-27","cited_by_count":115},{"id":"2001.08499","title":"A Large Scale Event-based Detection Dataset for Automotive","created":"2020-01-23","cited_by_count":109},{"id":"1804.00892","title":"When will you do what? - Anticipating Temporal Occurrences of Activities","created":"2018-04-03","cited_by_count":107},{"id":"2003.09148","title":"Event-based Asynchronous Sparse Convolutional Networks","created":"2020-03-20","cited_by_count":104},{"id":"1904.03597","title":"Self-supervised Spatio-temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics","created":"2019-04-07","cited_by_count":92},{"id":"2112.01041","title":"N-ImageNet: Towards Robust, Fine-Grained Object Recognition with Event Cameras","created":"2021-12-02","cited_by_count":92},{"id":"2102.09320","title":"Combining Events and Frames using Recurrent Asynchronous Multimodal Networks for Monocular Depth Prediction","created":"2021-02-18","cited_by_count":90},{"id":"2010.08350","title":"Learning Monocular Dense Depth from Events","created":"2020-10-16","cited_by_count":85},{"id":"1711.11152","title":"Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognition","created":"2017-11-29","cited_by_count":82},{"id":"1904.01293","title":"Event-Based Motion Segmentation by Motion Compensation","created":"2019-04-02","cited_by_count":78},{"id":"2006.00626","title":"In the Eye of the Beholder: Gaze and Actions in First Person Video","created":"2020-05-31","cited_by_count":69},{"id":"1607.01794","title":"VideoLSTM Convolves, Attends and Flows for Action Recognition","created":"2016-07-06","cited_by_count":60},{"id":"1812.07045","title":"EventNet: Asynchronous Recursive Event Processing","created":"2018-12-07","cited_by_count":58},{"id":"1805.07931","title":"Asynchronous Convolutional Networks for Object Detection in Neuromorphic Cameras","created":"2018-05-21","cited_by_count":57},{"id":"1811.10698","title":"LSTA: Long Short-Term Attention for Egocentric Action Recognition","created":"2018-11-26","cited_by_count":57},{"id":"2005.08605","title":"DDD20 End-to-End Event Camera Driving Dataset: Fusing Frames and Events with Deep Learning for Improved Steering Prediction","created":"2020-05-18","cited_by_count":56},{"id":"1711.01467","title":"Attentional Pooling for Action Recognition","created":"2017-11-04","cited_by_count":54},{"id":"2010.08946","title":"Temporal Binary Representation for Event-Based Action Recognition","created":"2020-10-18","cited_by_count":51},{"id":"2012.08730","title":"Event-based Motion Segmentation with Spatio-Temporal Graph Cuts","created":"2020-12-16","cited_by_count":50},{"id":"2110.15128","title":"Contrast and Mix: Temporal Contrastive Video Domain Adaptation with Background Mixing","created":"2021-10-28","cited_by_count":49},{"id":"2108.11974","title":"Learning Cross-modal Contrastive Features for Video Domain Adaptation","created":"2021-08-26","cited_by_count":47},{"id":"2011.03920","title":"Integrating Human Gaze into Attention for Egocentric Activity Recognition","created":"2020-11-08","cited_by_count":42},{"id":"2111.01024","title":"With a Little Help from my Temporal Context: Multimodal Egocentric Action Recognition","created":"2021-11-01","cited_by_count":41},{"id":"1510.00562","title":"Human Action Recognition using Factorized Spatio-Temporal Convolutional Networks","created":"2015-10-02","cited_by_count":40},{"id":"2107.13411","title":"Predicting the Future from First Person (Egocentric) Vision: A Survey","created":"2021-07-28","cited_by_count":36},{"id":"2110.10101","title":"Domain Generalization through Audio-Visual Relative Norm Alignment in First Person Action Recognition","created":"2021-10-19","cited_by_count":35},{"id":"1807.10037","title":"Motion Feature Network: Fixed Motion Filter for Action Recognition","created":"2018-07-26","cited_by_count":34},{"id":"1904.00696","title":"Dance with Flow: Two-in-One Stream Action Detection","created":"2019-04-01","cited_by_count":30},{"id":"2110.12211","title":"ES-ImageNet: A Million Event-Stream Classification Dataset for Spiking Neural Networks","created":"2021-10-23","cited_by_count":24},{"id":"1505.04803","title":"Predicting Important Objects for Egocentric Video Summarization","created":"2015-05-18","cited_by_count":21},{"id":"2103.12768","title":"DA4Event: towards bridging the Sim-to-Real Gap for Event Cameras using Domain Adaptation","created":"2021-03-23","cited_by_count":14},{"id":"1910.06693","title":"Seeing and Hearing Egocentric Actions: How Much Can We Learn?","created":"2019-10-15","cited_by_count":8},{"id":"1908.00867","title":"An Evaluation of Action Recognition Models on EPIC-Kitchens","created":"2019-08-02","cited_by_count":5},{"id":"2109.14657","title":"Understanding Egocentric Hand-Object Interactions from Hand Pose Estimation","created":"2021-09-29","cited_by_count":5}],"next_cursor":null}