{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"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":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1606.04797","title":"V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation","created":"2016-06-15","cited_by_count":2292},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"id":"1902.09630","title":"Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression","created":"2019-02-25","cited_by_count":1368},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"2110.06864","title":"ByteTrack: Multi-Object Tracking by Associating Every Detection Box","created":"2021-10-13","cited_by_count":823},{"id":"1703.07737","title":"In Defense of the Triplet Loss for Person Re-Identification","created":"2017-03-22","cited_by_count":786},{"id":"2201.12329","title":"DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR","created":"2022-01-28","cited_by_count":573},{"id":"1603.00831","title":"MOT16: A Benchmark for Multi-Object Tracking","created":"2016-03-02","cited_by_count":532},{"id":"2101.02702","title":"TrackFormer: Multi-Object Tracking with Transformers","created":"2021-01-07","cited_by_count":518},{"id":"2011.12450","title":"Sparse R-CNN: End-to-End Object Detection with Learnable Proposals","created":"2020-11-25","cited_by_count":495},{"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":"2108.06152","title":"Conditional DETR for Fast Training Convergence","created":"2021-08-13","cited_by_count":424},{"id":"1905.04804","title":"Video Instance Segmentation","created":"2019-05-12","cited_by_count":393},{"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":"2012.00759","title":"MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers","created":"2020-12-01","cited_by_count":355},{"id":"1605.09673","title":"Dynamic Filter Networks","created":"2016-05-31","cited_by_count":319},{"id":"2003.05664","title":"Conditional Convolutions for Instance Segmentation","created":"2020-03-12","cited_by_count":314},{"id":"2112.10764","title":"Mask2Former for Video Instance Segmentation","created":"2021-12-20","cited_by_count":171},{"id":"1409.7618","title":"Multiple Object Tracking: A Literature Review","created":"2014-09-26","cited_by_count":166},{"id":"2105.01928","title":"Instances as Queries","created":"2021-05-05","cited_by_count":158},{"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":"1710.03958","title":"Detect to Track and Track to Detect","created":"2017-10-11","cited_by_count":131},{"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":"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":"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":"2103.13746","title":"Video Instance Segmentation with a Propose-Reduce Paradigm","created":"2021-03-25","cited_by_count":74},{"id":"2012.03400","title":"CompFeat: Comprehensive Feature Aggregation for Video Instance Segmentation","created":"2020-12-07","cited_by_count":53},{"id":"1411.6031","title":"Finding Action Tubes","created":"2014-11-21","cited_by_count":50},{"id":"2106.11958","title":"Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation","created":"2021-06-22","cited_by_count":43},{"id":"1712.06317","title":"Video Object Detection with an Aligned Spatial-Temporal Memory","created":"2017-12-18","cited_by_count":42},{"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":"2203.01853","title":"Efficient Video Instance Segmentation via Tracklet Query and Proposal","created":"2022-03-03","cited_by_count":33},{"id":"2206.00468","title":"PanopticDepth: A Unified Framework for Depth-aware Panoptic Segmentation","created":"2022-06-01","cited_by_count":14},{"id":"2112.01695","title":"Hybrid Instance-aware Temporal Fusion for Online Video Instance Segmentation","created":"2021-12-03","cited_by_count":13},{"id":"2207.10959","title":"QueryProp: Object Query Propagation for High-Performance Video Object Detection","created":"2022-07-22","cited_by_count":12},{"id":"2208.03079","title":"Instance As Identity: A Generic Online Paradigm for Video Instance Segmentation","created":"2022-08-05","cited_by_count":8}],"next_cursor":null}