{"list":"other","total":61,"rows":[{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1306.0895","title":"Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances","created":"2013-06-04","cited_by_count":2316},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"1803.07728","title":"Unsupervised Representation Learning by Predicting Image Rotations","created":"2018-03-21","cited_by_count":1591},{"id":"1911.11763","title":"SuperGlue: Learning Feature Matching with Graph Neural Networks","created":"2019-11-26","cited_by_count":1443},{"id":"1705.07115","title":"Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics","created":"2017-05-19","cited_by_count":1358},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"1807.05520","title":"Deep Clustering for Unsupervised Learning of Visual Features","created":"2018-07-15","cited_by_count":1028},{"id":"1711.02257","title":"GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks","created":"2017-11-07","cited_by_count":834},{"id":"1704.06888","title":"Time-Contrastive Networks: Self-Supervised Learning from Video","created":"2017-04-23","cited_by_count":459},{"id":"1903.06864","title":"Domain Generalization by Solving Jigsaw Puzzles","created":"2019-03-16","cited_by_count":450},{"id":"1502.04681","title":"Unsupervised Learning of Video Representations using LSTMs","created":"2015-02-16","cited_by_count":435},{"id":"1609.02612","title":"Generating Videos with Scene Dynamics","created":"2016-09-08","cited_by_count":376},{"id":"2008.03800","title":"Spatiotemporal Contrastive Video Representation Learning","created":"2020-08-09","cited_by_count":372},{"id":"1703.01541","title":"Soft-DTW: a Differentiable Loss Function for Time-Series","created":"2017-03-05","cited_by_count":271},{"id":"1603.06668","title":"Learning Representations for Automatic Colorization","created":"2016-03-22","cited_by_count":251},{"id":"1708.01246","title":"Unsupervised Representation Learning by Sorting Sequences","created":"2017-08-03","cited_by_count":221},{"id":"2104.14558","title":"A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning","created":"2021-04-29","cited_by_count":214},{"id":"1703.04044","title":"Colorization as a Proxy Task for Visual Understanding","created":"2017-03-11","cited_by_count":175},{"id":"1805.09114","title":"Optimal Transport for structured data with application on graphs","created":"2018-05-23","cited_by_count":172},{"id":"2004.06130","title":"SpeedNet: Learning the Speediness in Videos","created":"2020-04-13","cited_by_count":171},{"id":"1904.07846","title":"Temporal Cycle-Consistency Learning","created":"2019-04-16","cited_by_count":154},{"id":"1811.09795","title":"Self-Supervised Video Representation Learning with Space-Time Cubic Puzzles","created":"2018-11-24","cited_by_count":149},{"id":"2008.05861","title":"Self-supervised Video Representation Learning by Pace Prediction","created":"2020-08-13","cited_by_count":139},{"id":"2101.07974","title":"TCLR: Temporal Contrastive Learning for Video Representation","created":"2021-01-20","cited_by_count":136},{"id":"1901.06003","title":"Gromov-Wasserstein Learning for Graph Matching and Node Embedding","created":"2019-01-17","cited_by_count":126},{"id":"1708.06734","title":"Representation Learning by Learning to Count","created":"2017-08-22","cited_by_count":120},{"id":"1506.09215","title":"Unsupervised Learning from Narrated Instruction Videos","created":"2015-06-30","cited_by_count":116},{"id":"2006.11476","title":"Video Playback Rate Perception for Self-supervisedSpatio-Temporal Representation Learning","created":"2020-06-20","cited_by_count":103},{"id":"2007.00394","title":"The IKEA ASM Dataset: Understanding People Assembling Furniture through Actions, Objects and Pose","created":"2020-07-01","cited_by_count":95},{"id":"1811.02834","title":"Fused Gromov-Wasserstein distance for structured objects: theoretical foundations and mathematical properties","created":"2018-11-07","cited_by_count":93},{"id":"2010.05599","title":"MS$^2$L: Multi-Task Self-Supervised Learning for Skeleton Based Action Recognition","created":"2020-10-12","cited_by_count":92},{"id":"1911.12409","title":"PREDICT & CLUSTER: Unsupervised Skeleton Based Action Recognition","created":"2019-11-27","cited_by_count":91},{"id":"2210.10352","title":"Temporal Action Segmentation: An Analysis of Modern Techniques","created":"2022-10-19","cited_by_count":85},{"id":"1904.04189","title":"Unsupervised learning of action classes with continuous temporal embedding","created":"2019-04-08","cited_by_count":76},{"id":"2103.11264","title":"Temporally-Weighted Hierarchical Clustering for Unsupervised Action Segmentation","created":"2021-03-20","cited_by_count":58},{"id":"1803.03095","title":"Leveraging Unlabeled Data for Crowd Counting by Learning to Rank","created":"2018-03-08","cited_by_count":57},{"id":"2105.13353","title":"Unsupervised Action Segmentation by Joint Representation Learning and Online Clustering","created":"2021-05-27","cited_by_count":49},{"id":"1904.11407","title":"DynamoNet: Dynamic Action and Motion Network","created":"2019-04-25","cited_by_count":48},{"id":"2103.17260","title":"Learning by Aligning Videos in Time","created":"2021-03-31","cited_by_count":48},{"id":"1412.6056","title":"Unsupervised Learning of Spatiotemporally Coherent Metrics","created":"2014-12-18","cited_by_count":46},{"id":"2001.11122","title":"Joint Visual-Temporal Embedding for Unsupervised Learning of Actions in Untrimmed Sequences","created":"2020-01-29","cited_by_count":45},{"id":"2111.00648","title":"Accurate Point Cloud Registration with Robust Optimal Transport","created":"2021-11-01","cited_by_count":38},{"id":"2404.01518","title":"Temporally Consistent Unbalanced Optimal Transport for Unsupervised Action Segmentation","created":"2024-04-01","cited_by_count":38},{"id":"2007.05934","title":"Adversarial Self-Supervised Learning for Semi-Supervised 3D Action Recognition","created":"2020-07-12","cited_by_count":34},{"id":"2104.02116","title":"Action Shuffle Alternating Learning for Unsupervised Action Segmentation","created":"2021-04-05","cited_by_count":33},{"id":"2305.05080","title":"Scalable Optimal Transport Methods in Machine Learning: A Contemporary Survey","created":"2023-05-08","cited_by_count":27},{"id":"2105.00067","title":"Unsupervised Discriminative Embedding for Sub-Action Learning in Complex Activities","created":"2021-04-30","cited_by_count":26},{"id":"2206.09398","title":"Aligning individual brains with Fused Unbalanced Gromov-Wasserstein","created":"2022-06-19","cited_by_count":23},{"id":"2111.09301","title":"Learning to Align Sequential Actions in the Wild","created":"2021-11-17","cited_by_count":20},{"id":"1612.02699","title":"Deep Supervision with Shape Concepts for Occlusion-Aware 3D Object Parsing","created":"2016-12-08","cited_by_count":19},{"id":"2004.02331","title":"Steering Self-Supervised Feature Learning Beyond Local Pixel Statistics","created":"2020-04-05","cited_by_count":19},{"id":"2412.17640","title":"Hierarchical Vector Quantization for Unsupervised Action Segmentation","created":"2024-12-23","cited_by_count":19},{"id":"2206.15031","title":"Timestamp-Supervised Action Segmentation with Graph Convolutional Networks","created":"2022-06-30","cited_by_count":18},{"id":"2305.19478","title":"Permutation-Aware Action Segmentation via Unsupervised Frame-to-Segment Alignment","created":"2023-05-31","cited_by_count":17},{"id":"2307.02402","title":"Unbalanced Optimal Transport: A Unified Framework for Object Detection","created":"2023-07-05","cited_by_count":15},{"id":"1801.07230","title":"DiscrimNet: Semi-Supervised Action Recognition from Videos using Generative Adversarial Networks","created":"2018-01-22","cited_by_count":14},{"id":"2204.12223","title":"Context-Aware Sequence Alignment using 4D Skeletal Augmentation","created":"2022-04-26","cited_by_count":11},{"id":"2309.06462","title":"Action Segmentation Using 2D Skeleton Heatmaps and Multi-Modality Fusion","created":"2023-09-12","cited_by_count":6},{"id":"2305.19480","title":"Learning by Aligning 2D Skeleton Sequences and Multi-Modality Fusion","created":"2023-05-31","cited_by_count":3}],"next_cursor":null}