{"list":"other","total":56,"rows":[{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"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":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1904.01355","title":"FCOS: Fully Convolutional One-Stage Object Detection","created":"2019-04-02","cited_by_count":1577},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"2101.02702","title":"TrackFormer: Multi-Object Tracking with Transformers","created":"2021-01-07","cited_by_count":518},{"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":"2003.05664","title":"Conditional Convolutions for Instance Segmentation","created":"2020-03-12","cited_by_count":314},{"id":"2111.12594","title":"Conditional Object-Centric Learning from Video","created":"2021-11-24","cited_by_count":248},{"id":"1503.01640","title":"BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation","created":"2015-03-05","cited_by_count":238},{"id":"1603.07485","title":"Simple Does It: Weakly Supervised Instance and Semantic Segmentation","created":"2016-03-24","cited_by_count":227},{"id":"1812.02898","title":"TDAN: Temporally Deformable Alignment Network for Video Super-Resolution","created":"2018-12-07","cited_by_count":226},{"id":"1902.03604","title":"MOTS: Multi-Object Tracking and Segmentation","created":"2019-02-10","cited_by_count":223},{"id":"2006.06664","title":"Quasi-Dense Similarity Learning for Multiple Object Tracking","created":"2020-06-11","cited_by_count":220},{"id":"1502.02734","title":"Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation","created":"2015-02-09","cited_by_count":189},{"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":"1912.04573","title":"Classifying, Segmenting, and Tracking Object Instances in Video with Mask Propagation","created":"2019-12-10","cited_by_count":125},{"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":"2103.08907","title":"BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentation","created":"2021-03-16","cited_by_count":105},{"id":"2106.03299","title":"Video Instance Segmentation using Inter-Frame Communication Transformers","created":"2021-06-07","cited_by_count":105},{"id":"2103.12340","title":"Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers","created":"2021-03-23","cited_by_count":104},{"id":"1904.11693","title":"Box-driven Class-wise Region Masking and Filling Rate Guided Loss for Weakly Supervised Semantic Segmentation","created":"2019-04-26","cited_by_count":98},{"id":"2207.10661","title":"In Defense of Online Models for Video Instance Segmentation","created":"2022-07-21","cited_by_count":97},{"id":"2206.04403","title":"VITA: Video Instance Segmentation via Object Token Association","created":"2022-06-09","cited_by_count":94},{"id":"2208.02245","title":"MinVIS: A Minimal Video Instance Segmentation Framework without Video-based Training","created":"2022-08-03","cited_by_count":94},{"id":"2207.07078","title":"Towards Grand Unification of Object Tracking","created":"2022-07-14","cited_by_count":93},{"id":"1503.00848","title":"Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation","created":"2015-03-03","cited_by_count":91},{"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":"1605.07866","title":"DeepCut: Object Segmentation from Bounding Box Annotations using Convolutional Neural Networks","created":"2016-05-25","cited_by_count":79},{"id":"2103.13746","title":"Video Instance Segmentation with a Propose-Reduce Paradigm","created":"2021-03-25","cited_by_count":74},{"id":"2111.13673","title":"Mask Transfiner for High-Quality Instance Segmentation","created":"2021-11-26","cited_by_count":64},{"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":"2106.11958","title":"Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation","created":"2021-06-22","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":"2207.09055","title":"Box-supervised Instance Segmentation with Level Set Evolution","created":"2022-07-19","cited_by_count":41},{"id":"2203.01853","title":"Efficient Video Instance Segmentation via Tracklet Query and Proposal","created":"2022-03-03","cited_by_count":33},{"id":"2207.14012","title":"Video Mask Transfiner for High-Quality Video Instance Segmentation","created":"2022-07-28","cited_by_count":28},{"id":"2103.12886","title":"Weakly Supervised Instance Segmentation for Videos with Temporal Mask Consistency","created":"2021-03-23","cited_by_count":19},{"id":"1908.04501","title":"Frame-to-Frame Aggregation of Active Regions in Web Videos for Weakly Supervised Semantic Segmentation","created":"2019-08-13","cited_by_count":18},{"id":"2104.00287","title":"Learning to Track Instances without Video Annotations","created":"2021-04-01","cited_by_count":18},{"id":"2301.01882","title":"InsPro: Propagating Instance Query and Proposal for Online Video Instance Segmentation","created":"2023-01-05","cited_by_count":13},{"id":"2203.13253","title":"Video Instance Segmentation via Multi-scale Spatio-temporal Split Attention Transformer","created":"2022-03-24","cited_by_count":9},{"id":"1708.04400","title":"Bringing Background into the Foreground: Making All Classes Equal in Weakly-supervised Video Semantic Segmentation","created":"2017-08-15","cited_by_count":7},{"id":"2007.07175","title":"Unsupervised Spatio-temporal Latent Feature Clustering for Multiple-object Tracking and Segmentation","created":"2020-07-14","cited_by_count":3}],"next_cursor":null}