{"list":"other","total":52,"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":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"1712.07629","title":"SuperPoint: Self-Supervised Interest Point Detection and Description","created":"2017-12-20","cited_by_count":1320},{"id":"1504.06852","title":"FlowNet: Learning Optical Flow with Convolutional Networks","created":"2015-04-26","cited_by_count":1059},{"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":"1704.00675","title":"The 2017 DAVIS Challenge on Video Object Segmentation","created":"2017-04-03","cited_by_count":957},{"id":"1512.02134","title":"A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation","created":"2015-12-07","cited_by_count":881},{"id":"1504.00702","title":"End-to-End Training of Deep Visuomotor Policies","created":"2015-04-02","cited_by_count":875},{"id":"1612.01925","title":"FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks","created":"2016-12-06","cited_by_count":784},{"id":"1804.00607","title":"MegaDepth: Learning Single-View Depth Prediction from Internet Photos","created":"2018-04-02","cited_by_count":737},{"id":"1802.00434","title":"DensePose: Dense Human Pose Estimation In The Wild","created":"2018-02-01","cited_by_count":575},{"id":"2009.07736","title":"HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking","created":"2020-09-16","cited_by_count":552},{"id":"1603.00831","title":"MOT16: A Benchmark for Multi-Object Tracking","created":"2016-03-02","cited_by_count":532},{"id":"1810.11981","title":"GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild","created":"2018-10-29","cited_by_count":475},{"id":"1611.00850","title":"Optical Flow Estimation using a Spatial Pyramid Network","created":"2016-11-03","cited_by_count":424},{"id":"1809.03327","title":"YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark","created":"2018-09-06","cited_by_count":383},{"id":"2203.03570","title":"Kubric: A scalable dataset generator","created":"2022-03-07","cited_by_count":381},{"id":"1612.07828","title":"Learning from Simulated and Unsupervised Images through Adversarial Training","created":"2016-12-22","cited_by_count":288},{"id":"1903.07593","title":"Learning Correspondence from the Cycle-Consistency of Time","created":"2019-03-18","cited_by_count":269},{"id":"1704.05939","title":"HPatches: A benchmark and evaluation of handcrafted and learned local descriptors","created":"2017-04-19","cited_by_count":264},{"id":"2006.14613","title":"Space-Time Correspondence as a Contrastive Random Walk","created":"2020-06-25","cited_by_count":239},{"id":"2103.14167","title":"COTR: Correspondence Transformer for Matching Across Images","created":"2021-03-25","cited_by_count":183},{"id":"2007.11858","title":"Whole-Body Human Pose Estimation in the Wild","created":"2020-07-23","cited_by_count":178},{"id":"1710.10000","title":"PoseTrack: A Benchmark for Human Pose Estimation and Tracking","created":"2017-10-27","cited_by_count":173},{"id":"1806.09594","title":"Tracking Emerges by Colorizing Videos","created":"2018-06-25","cited_by_count":166},{"id":"1406.4773","title":"Deep Learning Face Representation by Joint Identification-Verification","created":"2014-06-18","cited_by_count":162},{"id":"1903.06684","title":"kPAM: KeyPoint Affordances for Category-Level Robotic Manipulation","created":"2019-03-15","cited_by_count":153},{"id":"1510.05970","title":"Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches","created":"2015-10-20","cited_by_count":151},{"id":"1805.09662","title":"LF-Net: Learning Local Features from Images","created":"2018-05-24","cited_by_count":151},{"id":"2005.10356","title":"TAO: A Large-Scale Benchmark for Tracking Any Object","created":"2020-05-20","cited_by_count":147},{"id":"1806.08756","title":"Dense Object Nets: Learning Dense Visual Object Descriptors By and For Robotic Manipulation","created":"2018-06-22","cited_by_count":142},{"id":"2104.04691","title":"Unidentified Video Objects: A Benchmark for Dense, Open-World Segmentation","created":"2021-04-10","cited_by_count":133},{"id":"1803.09693","title":"Efficient Interactive Annotation of Segmentation Datasets with Polygon-RNN++","created":"2018-03-26","cited_by_count":120},{"id":"1904.11111","title":"Learning the Depths of Moving People by Watching Frozen People","created":"2019-04-25","cited_by_count":120},{"id":"1806.07823","title":"Unsupervised Learning of Object Landmarks through Conditional Image Generation","created":"2018-06-20","cited_by_count":114},{"id":"1702.00824","title":"YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Video","created":"2017-02-02","cited_by_count":109},{"id":"2002.07793","title":"MAST: A Memory-Augmented Self-supervised Tracker","created":"2020-02-18","cited_by_count":109},{"id":"1909.06933","title":"Self-Supervised Correspondence in Visuomotor Policy Learning","created":"2019-09-16","cited_by_count":107},{"id":"2104.14544","title":"AutoFlow: Learning a Better Training Set for Optical Flow","created":"2021-04-29","cited_by_count":102},{"id":"1704.07804","title":"SfM-Net: Learning of Structure and Motion from Video","created":"2017-04-25","cited_by_count":89},{"id":"1811.05804","title":"Creatures great and SMAL: Recovering the shape and motion of animals from video","created":"2018-11-14","cited_by_count":84},{"id":"2103.17263","title":"Rethinking Self-supervised Correspondence Learning: A Video Frame-level Similarity Perspective","created":"2021-03-31","cited_by_count":81},{"id":"1909.11895","title":"Joint-task Self-supervised Learning for Temporal Correspondence","created":"2019-09-26","cited_by_count":80},{"id":"1804.04412","title":"Unsupervised Discovery of Object Landmarks as Structural Representations","created":"2018-04-12","cited_by_count":73},{"id":"2110.06192","title":"Beyond Pick-and-Place: Tackling Robotic Stacking of Diverse Shapes","created":"2021-10-12","cited_by_count":71},{"id":"2009.05085","title":"Keypoints into the Future: Self-Supervised Correspondence in Model-Based Reinforcement Learning","created":"2020-09-10","cited_by_count":70},{"id":"1705.02193","title":"Unsupervised learning of object landmarks by factorized spatial embeddings","created":"2017-05-05","cited_by_count":64},{"id":"2110.06562","title":"Unsupervised Object Learning via Common Fate","created":"2021-10-13","cited_by_count":29},{"id":"2009.14711","title":"S3K: Self-Supervised Semantic Keypoints for Robotic Manipulation via Multi-View Consistency","created":"2020-09-30","cited_by_count":28},{"id":"2109.13227","title":"TSM: Temporal Shift Module for Efficient and Scalable Video Understanding on Edge Device","created":"2021-09-27","cited_by_count":17},{"id":"2012.12554","title":"Efficient video annotation with visual interpolation and frame selection guidance","created":"2020-12-23","cited_by_count":10}],"next_cursor":null}