{"list":"other","total":53,"rows":[{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"1711.05101","title":"Decoupled Weight Decay Regularization","created":"2017-11-14","cited_by_count":1831},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"2004.04730","title":"X3D: Expanding Architectures for Efficient Video Recognition","created":"2020-04-09","cited_by_count":637},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"1705.08168","title":"Look, Listen and Learn","created":"2017-05-23","cited_by_count":458},{"id":"1604.06573","title":"Convolutional Two-Stream Network Fusion for Video Action Recognition","created":"2016-04-22","cited_by_count":384},{"id":"1807.00230","title":"Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization","created":"2018-06-30","cited_by_count":249},{"id":"1610.09001","title":"SoundNet: Learning Sound Representations from Unlabeled Video","created":"2016-10-27","cited_by_count":247},{"id":"1908.08498","title":"EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition","created":"2019-08-22","cited_by_count":226},{"id":"2106.05392","title":"Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers","created":"2021-06-09","cited_by_count":224},{"id":"2201.08377","title":"Omnivore: A Single Model for Many Visual Modalities","created":"2022-01-20","cited_by_count":215},{"id":"1507.00448","title":"Cross Modal Distillation for Supervision Transfer","created":"2015-07-02","cited_by_count":175},{"id":"1912.04487","title":"Listen to Look: Action Recognition by Previewing Audio","created":"2019-12-10","cited_by_count":163},{"id":"2106.04538","title":"What Makes Multi-modal Learning Better than Single (Provably)","created":"2021-06-08","cited_by_count":153},{"id":"2103.11511","title":"MoViNets: Mobile Video Networks for Efficient Video Recognition","created":"2021-03-21","cited_by_count":135},{"id":"1904.04289","title":"SCSampler: Sampling Salient Clips from Video for Efficient Action Recognition","created":"2019-04-08","cited_by_count":134},{"id":"1707.03502","title":"Deep Learning for Sensor-based Activity Recognition: A Survey","created":"2017-07-12","cited_by_count":133},{"id":"1804.09626","title":"Charades-Ego: A Large-Scale Dataset of Paired Third and First Person Videos","created":"2018-04-25","cited_by_count":128},{"id":"1804.09066","title":"ECO: Efficient Convolutional Network for Online Video Understanding","created":"2018-04-24","cited_by_count":115},{"id":"2204.01696","title":"Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videos","created":"2022-04-04","cited_by_count":111},{"id":"1512.02363","title":"On-Manifold Preintegration for Real-Time Visual-Inertial Odometry","created":"2015-12-08","cited_by_count":95},{"id":"2007.15796","title":"AR-Net: Adaptive Frame Resolution for Efficient Action Recognition","created":"2020-07-31","cited_by_count":88},{"id":"1806.07110","title":"Modality Distillation with Multiple Stream Networks for Action Recognition","created":"2018-06-19","cited_by_count":83},{"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":"2105.03245","title":"Adaptive Focus for Efficient Video Recognition","created":"2021-05-07","cited_by_count":77},{"id":"1905.12853","title":"RoNIN: Robust Neural Inertial Navigation in the Wild: Benchmark, Evaluations, and New Methods","created":"2019-05-30","cited_by_count":73},{"id":"1910.11760","title":"Self-supervised Moving Vehicle Tracking with Stereo Sound","created":"2019-10-25","cited_by_count":63},{"id":"2104.13400","title":"FrameExit: Conditional Early Exiting for Efficient Video Recognition","created":"2021-04-27","cited_by_count":59},{"id":"2111.11591","title":"Efficient Video Transformers with Spatial-Temporal Token Selection","created":"2021-11-23","cited_by_count":59},{"id":"2112.03596","title":"E$^2$(GO)MOTION: Motion Augmented Event Stream for Egocentric Action Recognition","created":"2021-12-07","cited_by_count":50},{"id":"2102.05775","title":"AdaFuse: Adaptive Temporal Fusion Network for Efficient Action Recognition","created":"2021-02-10","cited_by_count":48},{"id":"2104.02243","title":"3D-to-2D Distillation for Indoor Scene Parsing","created":"2021-04-06","cited_by_count":48},{"id":"1505.02206","title":"Learning image representations tied to ego-motion","created":"2015-05-08","cited_by_count":42},{"id":"1712.09004","title":"RIDI: Robust IMU Double Integration","created":"2017-12-25","cited_by_count":41},{"id":"2112.14238","title":"AdaFocus V2: End-to-End Training of Spatial Dynamic Networks for Video Recognition","created":"2021-12-28","cited_by_count":37},{"id":"2105.05165","title":"AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognition","created":"2021-05-11","cited_by_count":36},{"id":"2205.01652","title":"Episodic Memory Question Answering","created":"2022-05-03","cited_by_count":32},{"id":"2203.13116","title":"Egocentric Prediction of Action Target in 3D","created":"2022-03-24","cited_by_count":31},{"id":"2002.10718","title":"Denoising IMU Gyroscopes with Deep Learning for Open-Loop Attitude Estimation","created":"2020-02-25","cited_by_count":26},{"id":"1803.10827","title":"Who Let The Dogs Out? Modeling Dog Behavior From Visual Data","created":"2018-03-28","cited_by_count":20},{"id":"2205.06187","title":"Efficient Deep Visual and Inertial Odometry with Adaptive Visual Modality Selection","created":"2022-05-12","cited_by_count":18},{"id":"2111.11676","title":"RIO: Rotation-equivariance supervised learning of robust inertial odometry","created":"2021-11-23","cited_by_count":14},{"id":"2008.00380","title":"Vision and Inertial Sensing Fusion for Human Action Recognition : A Review","created":"2020-08-02","cited_by_count":10},{"id":"2110.01680","title":"How You Move Your Head Tells What You Do: Self-supervised Video Representation Learning with Egocentric Cameras and IMU Sensors","created":"2021-10-04","cited_by_count":3},{"id":"2112.11224","title":"Attention-Based Sensor Fusion for Human Activity Recognition Using IMU Signals","created":"2021-12-20","cited_by_count":3},{"id":"2010.08539","title":"What Can You Learn from Your Muscles? Learning Visual Representation from Human Interactions","created":"2020-10-16","cited_by_count":2}],"next_cursor":null}