{"list":"other","total":61,"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":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1409.7495","title":"Unsupervised Domain Adaptation by Backpropagation","created":"2014-09-26","cited_by_count":1917},{"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":"1502.02791","title":"Learning Transferable Features with Deep Adaptation Networks","created":"2015-02-10","cited_by_count":1329},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"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":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"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":"1808.04560","title":"Deep Retinex Decomposition for Low-Light Enhancement","created":"2018-08-14","cited_by_count":723},{"id":"1712.02560","title":"Maximum Classifier Discrepancy for Unsupervised Domain Adaptation","created":"2017-12-07","cited_by_count":683},{"id":"2004.04730","title":"X3D: Expanding Architectures for Efficient Video Recognition","created":"2020-04-09","cited_by_count":637},{"id":"1711.06077","title":"The Perception-Distortion Tradeoff","created":"2017-11-16","cited_by_count":587},{"id":"1711.09577","title":"Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?","created":"2017-11-27","cited_by_count":551},{"id":"2001.06826","title":"Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement","created":"2020-01-19","cited_by_count":542},{"id":"1805.01934","title":"Learning to See in the Dark","created":"2018-05-04","cited_by_count":460},{"id":"1705.08421","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","created":"2017-05-23","cited_by_count":449},{"id":"1611.00850","title":"Optical Flow Estimation using a Spatial Pyramid Network","created":"2016-11-03","cited_by_count":424},{"id":"1711.10305","title":"Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks","created":"2017-11-28","cited_by_count":387},{"id":"1802.03494","title":"AMC: AutoML for Model Compression and Acceleration on Mobile Devices","created":"2018-02-10","cited_by_count":378},{"id":"2008.03800","title":"Spatiotemporal Contrastive Video Representation Learning","created":"2020-08-09","cited_by_count":372},{"id":"1905.04161","title":"Kindling the Darkness: A Practical Low-light Image Enhancer","created":"2019-05-04","cited_by_count":355},{"id":"1808.01340","title":"A Short Note about Kinetics-600","created":"2018-08-03","cited_by_count":333},{"id":"2111.13680","title":"GMFlow: Learning Optical Flow via Global Matching","created":"2021-11-26","cited_by_count":327},{"id":"1907.06987","title":"A Short Note on the Kinetics-700 Human Action Dataset","created":"2019-07-15","cited_by_count":310},{"id":"1904.02811","title":"Video Classification with Channel-Separated Convolutional Networks","created":"2019-04-04","cited_by_count":290},{"id":"1806.11230","title":"Human Action Recognition and Prediction: A Survey","created":"2018-06-28","cited_by_count":227},{"id":"1801.03150","title":"Moments in Time Dataset: one million videos for event understanding","created":"2018-01-09","cited_by_count":215},{"id":"2103.00860","title":"Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation","created":"2021-03-01","cited_by_count":192},{"id":"2004.01398","title":"TEA: Temporal Excitation and Aggregation for Action Recognition","created":"2020-04-03","cited_by_count":165},{"id":"1805.11227","title":"Getting to Know Low-light Images with The Exclusively Dark Dataset","created":"2018-05-29","cited_by_count":157},{"id":"2103.05905","title":"VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples","created":"2021-03-10","cited_by_count":154},{"id":"1612.05890","title":"Learning a No-Reference Quality Metric for Single-Image Super-Resolution","created":"2016-12-18","cited_by_count":144},{"id":"2008.05861","title":"Self-supervised Video Representation Learning by Pace Prediction","created":"2020-08-13","cited_by_count":139},{"id":"1905.00561","title":"Large-scale weakly-supervised pre-training for video action recognition","created":"2019-05-02","cited_by_count":130},{"id":"1907.01361","title":"FastDVDnet: Towards Real-Time Deep Video Denoising Without Flow Estimation","created":"2019-07-01","cited_by_count":128},{"id":"2006.11476","title":"Video Playback Rate Perception for Self-supervisedSpatio-Temporal Representation Learning","created":"2020-06-20","cited_by_count":103},{"id":"1809.05571","title":"Models Matter, So Does Training: An Empirical Study of CNNs for Optical Flow Estimation","created":"2018-09-14","cited_by_count":94},{"id":"2012.10671","title":"SMART Frame Selection for Action Recognition","created":"2020-12-19","cited_by_count":73},{"id":"1908.00682","title":"Attention Guided Low-light Image Enhancement with a Large Scale Low-light Simulation Dataset","created":"2019-08-02","cited_by_count":65},{"id":"1912.10405","title":"Adversarial Cross-Domain Action Recognition with Co-Attention","created":"2019-12-22","cited_by_count":51},{"id":"2102.02751","title":"Semi-Supervised Action Recognition with Temporal Contrastive Learning","created":"2021-02-04","cited_by_count":50},{"id":"2011.15045","title":"Unsupervised Deep Video Denoising","created":"2020-11-30","cited_by_count":44},{"id":"2006.03876","title":"ARID: A New Dataset for Recognizing Action in the Dark","created":"2020-06-06","cited_by_count":43},{"id":"1909.07945","title":"ProtoGAN: Towards Few Shot Learning for Action Recognition","created":"2019-09-17","cited_by_count":41},{"id":"1801.09086","title":"A Generative Approach to Zero-Shot and Few-Shot Action Recognition","created":"2018-01-27","cited_by_count":39},{"id":"1409.8230","title":"RENOIR - A Dataset for Real Low-Light Image Noise Reduction","created":"2014-09-29","cited_by_count":36},{"id":"1811.03879","title":"Cross and Learn: Cross-Modal Self-Supervision","created":"2018-11-09","cited_by_count":34},{"id":"1811.07503","title":"Compressing Recurrent Neural Networks with Tensor Ring for Action Recognition","created":"2018-11-19","cited_by_count":34},{"id":"1511.04458","title":"Transductive Zero-Shot Action Recognition by Word-Vector Embedding","created":"2015-11-13","cited_by_count":31},{"id":"1907.12865","title":"Open Set Domain Adaptation for Image and Action Recognition","created":"2019-07-30","cited_by_count":31},{"id":"2107.04941","title":"Partial Video Domain Adaptation with Partial Adversarial Temporal Attentive Network","created":"2021-07-11","cited_by_count":17},{"id":"2107.05202","title":"Delta Sampling R-BERT for limited data and low-light action recognition","created":"2021-07-12","cited_by_count":7},{"id":"1710.07455","title":"Generalized Zero-Shot Learning for Action Recognition with Web-Scale Video Data","created":"2017-10-20","cited_by_count":4},{"id":"1908.05674","title":"Bypass Enhancement RGB Stream Model for Pedestrian Action Recognition of Autonomous Vehicles","created":"2019-08-15","cited_by_count":1},{"id":"2109.12493","title":"Self-Supervised Video Representation Learning by Video Incoherence Detection","created":"2021-09-26","cited_by_count":1}],"next_cursor":null}