{"list":"other","total":63,"rows":[{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1904.02689","title":"YOLACT: Real-time Instance Segmentation","created":"2019-04-04","cited_by_count":443},{"id":"2011.14503","title":"End-to-End Video Instance Segmentation with Transformers","created":"2020-11-30","cited_by_count":443},{"id":"1905.04804","title":"Video Instance Segmentation","created":"2019-05-12","cited_by_count":393},{"id":"1803.07549","title":"Learning Category-Specific Mesh Reconstruction from Image Collections","created":"2018-03-20","cited_by_count":317},{"id":"1812.01601","title":"Learning 3D Human Dynamics from Video","created":"2018-12-04","cited_by_count":316},{"id":"2003.05664","title":"Conditional Convolutions for Instance Segmentation","created":"2020-03-12","cited_by_count":314},{"id":"1506.02106","title":"What's the Point: Semantic Segmentation with Point Supervision","created":"2015-06-06","cited_by_count":298},{"id":"1912.04488","title":"SOLO: Segmenting Objects by Locations","created":"2019-12-10","cited_by_count":289},{"id":"1904.05044","title":"Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations","created":"2019-04-10","cited_by_count":247},{"id":"1911.06667","title":"CenterMask : Real-Time Anchor-Free Instance Segmentation","created":"2019-11-15","cited_by_count":201},{"id":"1909.13226","title":"PolarMask: Single Shot Instance Segmentation with Polar Representation","created":"2019-09-29","cited_by_count":188},{"id":"2112.10764","title":"Mask2Former for Video Instance Segmentation","created":"2021-12-20","cited_by_count":171},{"id":"2103.08808","title":"Track to Detect and Segment: An Online Multi-Object Tracker","created":"2021-03-16","cited_by_count":156},{"id":"2102.01558","title":"Occluded Video Instance Segmentation: A Benchmark","created":"2021-02-02","cited_by_count":154},{"id":"2012.02310","title":"BoxInst: High-Performance Instance Segmentation with Box Annotations","created":"2020-12-03","cited_by_count":151},{"id":"2103.07941","title":"Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion","created":"2021-03-14","cited_by_count":129},{"id":"1912.04573","title":"Classifying, Segmenting, and Tracking Object Instances in Video with Mask Propagation","created":"2019-12-10","cited_by_count":125},{"id":"1611.07709","title":"Fully Convolutional Instance-aware Semantic Segmentation","created":"2016-11-23","cited_by_count":123},{"id":"2003.08429","title":"STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos","created":"2020-03-18","cited_by_count":121},{"id":"2007.14772","title":"SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation","created":"2020-07-29","cited_by_count":108},{"id":"1908.07201","title":"Three-D Safari: Learning to Estimate Zebra Pose, Shape, and Texture from Images \"In the Wild\"","created":"2019-08-20","cited_by_count":106},{"id":"2106.03299","title":"Video Instance Segmentation using Inter-Frame Communication Transformers","created":"2021-06-07","cited_by_count":105},{"id":"2202.12181","title":"FreeSOLO: Learning to Segment Objects without Annotations","created":"2022-02-24","cited_by_count":102},{"id":"2204.02574","title":"FocalClick: Towards Practical Interactive Image Segmentation","created":"2022-04-06","cited_by_count":102},{"id":"2207.10661","title":"In Defense of Online Models for Video Instance Segmentation","created":"2022-07-21","cited_by_count":97},{"id":"2208.02245","title":"MinVIS: A Minimal Video Instance Segmentation Framework without Video-based Training","created":"2022-08-03","cited_by_count":94},{"id":"2007.10982","title":"Shape and Viewpoint without Keypoints","created":"2020-07-21","cited_by_count":92},{"id":"2103.10284","title":"SG-Net: Spatial Granularity Network for One-Stage Video Instance Segmentation","created":"2021-03-18","cited_by_count":87},{"id":"2104.05970","title":"Crossover Learning for Fast Online Video Instance Segmentation","created":"2021-04-13","cited_by_count":83},{"id":"2104.06404","title":"Pointly-Supervised Instance Segmentation","created":"2021-04-13","cited_by_count":83},{"id":"1506.06204","title":"Learning to Segment Object Candidates","created":"2015-06-20","cited_by_count":79},{"id":"1804.00880","title":"Weakly Supervised Instance Segmentation using Class Peak Response","created":"2018-04-03","cited_by_count":75},{"id":"2103.13746","title":"Video Instance Segmentation with a Propose-Reduce Paradigm","created":"2021-03-25","cited_by_count":74},{"id":"1603.08695","title":"Learning to Refine Object Segments","created":"2016-03-29","cited_by_count":67},{"id":"2104.07434","title":"Points as Queries: Weakly Semi-supervised Object Detection by Points","created":"2021-04-15","cited_by_count":60},{"id":"2105.06464","title":"DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision","created":"2021-05-13","cited_by_count":59},{"id":"2204.08412","title":"Temporally Efficient Vision Transformer for Video Instance Segmentation","created":"2022-04-18","cited_by_count":55},{"id":"2012.03400","title":"CompFeat: Comprehensive Feature Aggregation for Video Instance Segmentation","created":"2020-12-07","cited_by_count":53},{"id":"1803.00557","title":"The 2018 DAVIS Challenge on Video Object Segmentation","created":"2018-03-01","cited_by_count":47},{"id":"2003.11712","title":"Mask Encoding for Single Shot Instance Segmentation","created":"2020-03-26","cited_by_count":47},{"id":"1909.03444","title":"Dynamic Context Correspondence Network for Semantic Alignment","created":"2019-09-08","cited_by_count":43},{"id":"2104.05606","title":"Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation","created":"2021-04-06","cited_by_count":42},{"id":"2207.05282","title":"PseudoClick: Interactive Image Segmentation with Click Imitation","created":"2022-07-12","cited_by_count":42},{"id":"2303.14124","title":"Towards Scalable Neural Representation for Diverse Videos","created":"2023-03-24","cited_by_count":37},{"id":"2007.09397","title":"Weakly Supervised Instance Segmentation by Learning Annotation Consistent Instances","created":"2020-07-18","cited_by_count":32},{"id":"2108.07682","title":"Fully Convolutional Networks for Panoptic Segmentation with Point-based Supervision","created":"2021-08-17","cited_by_count":31},{"id":"2208.06974","title":"Learning Semantic Correspondence with Sparse Annotations","created":"2022-08-15","cited_by_count":31},{"id":"2203.16089","title":"Omni-DETR: Omni-Supervised Object Detection with Transformers","created":"2022-03-30","cited_by_count":29},{"id":"2104.04782","title":"Target-Aware Object Discovery and Association for Unsupervised Video Multi-Object Segmentation","created":"2021-04-10","cited_by_count":21},{"id":"2104.10386","title":"Guided Interactive Video Object Segmentation Using Reliability-Based Attention Maps","created":"2021-04-21","cited_by_count":21},{"id":"2210.13950","title":"Pointly-Supervised Panoptic Segmentation","created":"2022-10-25","cited_by_count":21},{"id":"2103.12886","title":"Weakly Supervised Instance Segmentation for Videos with Temporal Mask Consistency","created":"2021-03-23","cited_by_count":19},{"id":"2203.09338","title":"Object Localization under Single Coarse Point Supervision","created":"2022-03-17","cited_by_count":19},{"id":"2104.00287","title":"Learning to Track Instances without Video Annotations","created":"2021-04-01","cited_by_count":18},{"id":"1801.00269","title":"Interactive Video Object Segmentation in the Wild","created":"2017-12-31","cited_by_count":16},{"id":"2012.07504","title":"Improving Video Instance Segmentation by Light-weight Temporal Uncertainty Estimates","created":"2020-12-14","cited_by_count":14},{"id":"1612.08843","title":"FastMask: Segment Multi-scale Object Candidates in One Shot","created":"2016-12-28","cited_by_count":10},{"id":"2106.11963","title":"Tracking Instances as Queries","created":"2021-06-22","cited_by_count":7}],"next_cursor":null}