{"list":"other","total":52,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"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":"1801.00868","title":"Panoptic Segmentation","created":"2018-01-03","cited_by_count":802},{"id":"2101.02702","title":"TrackFormer: Multi-Object Tracking with Transformers","created":"2021-01-07","cited_by_count":518},{"id":"2004.01888","title":"FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking","created":"2020-04-04","cited_by_count":490},{"id":"2004.01177","title":"Tracking Objects as Points","created":"2020-04-02","cited_by_count":483},{"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":"1809.03327","title":"YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark","created":"2018-09-06","cited_by_count":383},{"id":"2003.09003","title":"MOT20: A benchmark for multi object tracking in crowded scenes","created":"2020-03-19","cited_by_count":357},{"id":"2101.11939","title":"Exploring Cross-Image Pixel Contrast for Semantic Segmentation","created":"2021-01-28","cited_by_count":242},{"id":"1902.03604","title":"MOTS: Multi-Object Tracking and Segmentation","created":"2019-02-10","cited_by_count":223},{"id":"2112.10764","title":"Mask2Former for Video Instance Segmentation","created":"2021-12-20","cited_by_count":171},{"id":"2102.01558","title":"Occluded Video Instance Segmentation: A Benchmark","created":"2021-02-02","cited_by_count":154},{"id":"2006.11339","title":"Video Panoptic Segmentation","created":"2020-06-19","cited_by_count":142},{"id":"2001.06810","title":"See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks","created":"2020-01-19","cited_by_count":138},{"id":"2107.01153","title":"A Survey on Deep Learning Technique for Video Segmentation","created":"2021-07-02","cited_by_count":132},{"id":"1912.04573","title":"Classifying, Segmenting, and Tracking Object Instances in Video with Mask Propagation","created":"2019-12-10","cited_by_count":125},{"id":"2008.08115","title":"TIDE: A General Toolbox for Identifying Object Detection Errors","created":"2020-08-18","cited_by_count":114},{"id":"2007.14772","title":"SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation","created":"2020-07-29","cited_by_count":108},{"id":"2106.03299","title":"Video Instance Segmentation using Inter-Frame Communication Transformers","created":"2021-06-07","cited_by_count":105},{"id":"2112.08275","title":"SeqFormer: Sequential Transformer for Video Instance Segmentation","created":"2021-12-15","cited_by_count":98},{"id":"1905.00737","title":"The 2019 DAVIS Challenge on VOS: Unsupervised Multi-Object Segmentation","created":"2019-05-02","cited_by_count":97},{"id":"2207.10661","title":"In Defense of Online Models for Video Instance Segmentation","created":"2022-07-21","cited_by_count":97},{"id":"2103.10284","title":"SG-Net: Spatial Granularity Network for One-Stage Video Instance Segmentation","created":"2021-03-18","cited_by_count":87},{"id":"2001.06807","title":"Zero-Shot Video Object Segmentation via Attentive Graph Neural Networks","created":"2020-01-19","cited_by_count":84},{"id":"2205.13775","title":"A Survey on Long-Tailed Visual Recognition","created":"2022-05-27","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":"1807.10706","title":"Diagnosing Error in Temporal Action Detectors","created":"2018-07-27","cited_by_count":71},{"id":"2204.08412","title":"Temporally Efficient Vision Transformer for Video Instance Segmentation","created":"2022-04-18","cited_by_count":55},{"id":"1811.12596","title":"Parsing R-CNN for Instance-Level Human Analysis","created":"2018-11-30","cited_by_count":53},{"id":"1702.00871","title":"Video Salient Object Detection via Fully Convolutional Networks","created":"2017-02-02","cited_by_count":46},{"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":"1811.12026","title":"Attacks on State-of-the-Art Face Recognition using Attentional Adversarial Attack Generative Network","created":"2018-11-29","cited_by_count":38},{"id":"2003.04845","title":"Hierarchical Human Parsing with Typed Part-Relation Reasoning","created":"2020-03-10","cited_by_count":38},{"id":"2009.09447","title":"Renovating Parsing R-CNN for Accurate Multiple Human Parsing","created":"2020-09-20","cited_by_count":37},{"id":"1808.00661","title":"Adaptive Temporal Encoding Network for Video Instance-level Human Parsing","created":"2018-08-02","cited_by_count":36},{"id":"2112.04177","title":"VISOLO: Grid-Based Space-Time Aggregation for Efficient Online Video Instance Segmentation","created":"2021-12-08","cited_by_count":29},{"id":"2203.14333","title":"Locality-Aware Inter-and Intra-Video Reconstruction for Self-Supervised Correspondence Learning","created":"2022-03-27","cited_by_count":26},{"id":"1611.00135","title":"A Benchmark Dataset and Saliency-guided Stacked Autoencoders for Video-based Salient Object Detection","created":"2016-11-01","cited_by_count":19},{"id":"1911.12451","title":"Empirical Upper Bound in Object Detection and More","created":"2019-11-27","cited_by_count":12},{"id":"1911.07959","title":"TracKlinic: Diagnosis of Challenge Factors in Visual Tracking","created":"2019-11-18","cited_by_count":6},{"id":"2003.03570","title":"CPM R-CNN: Calibrating Point-guided Misalignment in Object Detection","created":"2020-03-07","cited_by_count":4},{"id":"2110.13110","title":"Diagnosing Errors in Video Relation Detectors","created":"2021-10-25","cited_by_count":4},{"id":"2110.14773","title":"SiamPolar: Semi-supervised Realtime Video Object Segmentation with Polar Representation","created":"2021-10-27","cited_by_count":1}],"next_cursor":null}