{"list":"other","total":51,"rows":[{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"2203.03605","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","created":"2022-03-07","cited_by_count":1319},{"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":"1612.01925","title":"FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks","created":"2016-12-06","cited_by_count":784},{"id":"2308.09713","title":"Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis","created":"2023-08-18","cited_by_count":737},{"id":"2201.12329","title":"DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR","created":"2022-01-28","cited_by_count":573},{"id":"2307.07635","title":"CoTracker: It is Better to Track Together","created":"2023-07-14","cited_by_count":522},{"id":"2101.02702","title":"TrackFormer: Multi-Object Tracking with Transformers","created":"2021-01-07","cited_by_count":518},{"id":"2203.01305","title":"DN-DETR: Accelerate DETR Training by Introducing Query DeNoising","created":"2022-03-02","cited_by_count":488},{"id":"1904.00607","title":"Video Object Segmentation using Space-Time Memory Networks","created":"2019-04-01","cited_by_count":438},{"id":"2108.06152","title":"Conditional DETR for Fast Training Convergence","created":"2021-08-13","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":"2105.03247","title":"MOTR: End-to-End Multiple-Object Tracking with Transformer","created":"2021-05-07","cited_by_count":381},{"id":"2012.15460","title":"TransTrack: Multiple Object Tracking with Transformer","created":"2020-12-31","cited_by_count":371},{"id":"2306.08637","title":"TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement","created":"2023-06-14","cited_by_count":287},{"id":"2307.15055","title":"PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking","created":"2023-07-27","cited_by_count":276},{"id":"2211.03726","title":"TAP-Vid: A Benchmark for Tracking Any Point in a Video","created":"2022-11-07","cited_by_count":263},{"id":"1611.05198","title":"One-Shot Video Object Segmentation","created":"2016-11-16","cited_by_count":235},{"id":"2106.02638","title":"Associating Objects with Transformers for Video Object Segmentation","created":"2021-06-04","cited_by_count":226},{"id":"2204.04153","title":"Particle Video Revisited: Tracking Through Occlusions Using Point Trajectories","created":"2022-04-08","cited_by_count":217},{"id":"2306.05422","title":"Tracking Everything Everywhere All at Once","created":"2023-06-08","cited_by_count":193},{"id":"2404.04319","title":"SpatialTracker: Tracking Any 2D Pixels in 3D Space","created":"2024-04-05","cited_by_count":181},{"id":"1902.09513","title":"FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation","created":"2019-02-25","cited_by_count":178},{"id":"2312.00112","title":"DynMF: Neural Motion Factorization for Real-time Dynamic View Synthesis with 3D Gaussian Splatting","created":"2023-11-30","cited_by_count":124},{"id":"2402.00847","title":"BootsTAP: Bootstrapped Training for Tracking-Any-Point","created":"2024-02-01","cited_by_count":120},{"id":"2312.17225","title":"4DGen: Grounded 4D Content Generation with Spatial-temporal Consistency","created":"2023-12-28","cited_by_count":117},{"id":"2303.01237","title":"FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation","created":"2023-03-02","cited_by_count":114},{"id":"2403.14610","title":"T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy","created":"2024-03-21","cited_by_count":94},{"id":"2308.15975","title":"RoboTAP: Tracking Arbitrary Points for Few-Shot Visual Imitation","created":"2023-08-30","cited_by_count":90},{"id":"2407.15420","title":"Local All-Pair Correspondence for Point Tracking","created":"2024-07-22","cited_by_count":80},{"id":"2312.02087","title":"VideoSwap: Customized Video Subject Swapping with Interactive Semantic Point Correspondence","created":"2023-12-04","cited_by_count":69},{"id":"1704.07325","title":"Accurate Optical Flow via Direct Cost Volume Processing","created":"2017-04-24","cited_by_count":66},{"id":"2203.11335","title":"Global Matching with Overlapping Attention for Optical Flow Estimation","created":"2022-03-21","cited_by_count":64},{"id":"2305.12998","title":"MFT: Long-Term Tracking of Every Pixel","created":"2023-05-22","cited_by_count":62},{"id":"2312.00786","title":"Dense Optical Tracking: Connecting the Dots","created":"2023-12-01","cited_by_count":61},{"id":"2104.13918","title":"High-Resolution Optical Flow from 1D Attention and Correlation","created":"2021-04-28","cited_by_count":54},{"id":"2104.02166","title":"Learning Optical Flow from a Few Matches","created":"2021-04-05","cited_by_count":53},{"id":"2311.13601","title":"Visual In-Context Prompting","created":"2023-11-22","cited_by_count":52},{"id":"2010.14851","title":"Displacement-Invariant Matching Cost Learning for Accurate Optical Flow Estimation","created":"2020-10-28","cited_by_count":49},{"id":"2202.00089","title":"Understanding AdamW through Proximal Methods and Scale-Freeness","created":"2022-01-31","cited_by_count":46},{"id":"2403.13042","title":"TAPTR: Tracking Any Point with Transformers as Detection","created":"2024-03-19","cited_by_count":45},{"id":"2103.15145","title":"TransCenter: Transformers with Dense Representations for Multiple-Object Tracking","created":"2021-03-28","cited_by_count":42},{"id":"2312.00583","title":"DeformGS: Scene Flow in Highly Deformable Scenes for Deformable Object Manipulation","created":"2023-11-30","cited_by_count":42},{"id":"2303.07335","title":"Lite DETR : An Interleaved Multi-Scale Encoder for Efficient DETR","created":"2023-03-13","cited_by_count":36},{"id":"2403.17931","title":"Track Everything Everywhere Fast and Robustly","created":"2024-03-26","cited_by_count":14},{"id":"2306.02000","title":"Context-PIPs: Persistent Independent Particles Demands Spatial Context Features","created":"2023-06-03","cited_by_count":9}],"next_cursor":null}