{"list":"other","total":53,"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":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"1612.08242","title":"YOLO9000: Better, Faster, Stronger","created":"2016-12-25","cited_by_count":1431},{"id":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"id":"1712.00726","title":"Cascade R-CNN: Delving into High Quality Object Detection","created":"2017-12-03","cited_by_count":1276},{"id":"2107.08430","title":"YOLOX: Exceeding YOLO Series in 2021","created":"2021-07-18","cited_by_count":1071},{"id":"1504.06852","title":"FlowNet: Learning Optical Flow with Convolutional Networks","created":"2015-04-26","cited_by_count":1059},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"2011.12450","title":"Sparse R-CNN: End-to-End Object Detection with Learnable Proposals","created":"2020-11-25","cited_by_count":495},{"id":"1901.07518","title":"Hybrid Task Cascade for Instance Segmentation","created":"2019-01-22","cited_by_count":481},{"id":"1506.02106","title":"What's the Point: Semantic Segmentation with Point Supervision","created":"2015-06-06","cited_by_count":298},{"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":"1611.07715","title":"Deep Feature Flow for Video Recognition","created":"2016-11-23","cited_by_count":186},{"id":"1703.10025","title":"Flow-Guided Feature Aggregation for Video Object Detection","created":"2017-03-29","cited_by_count":177},{"id":"1807.11590","title":"Acquisition of Localization Confidence for Accurate Object Detection","created":"2018-07-30","cited_by_count":176},{"id":"2012.02310","title":"BoxInst: High-Performance Instance Segmentation with Box Annotations","created":"2020-12-03","cited_by_count":151},{"id":"1710.03958","title":"Detect to Track and Track to Detect","created":"2017-10-11","cited_by_count":131},{"id":"2003.12063","title":"Memory Enhanced Global-Local Aggregation for Video Object Detection","created":"2020-03-26","cited_by_count":128},{"id":"2103.09460","title":"You Only Look One-level Feature","created":"2021-03-17","cited_by_count":116},{"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":"1904.06493","title":"Rethinking Classification and Localization for Object Detection","created":"2019-04-13","cited_by_count":98},{"id":"1907.06390","title":"Sequence Level Semantics Aggregation for Video Object Detection","created":"2019-07-15","cited_by_count":87},{"id":"2003.07540","title":"Revisiting the Sibling Head in Object Detector","created":"2020-03-17","cited_by_count":82},{"id":"2201.05047","title":"TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformers","created":"2022-01-13","cited_by_count":78},{"id":"1908.09511","title":"Relation Distillation Networks for Video Object Detection","created":"2019-08-26","cited_by_count":77},{"id":"1602.08465","title":"Seq-NMS for Video Object Detection","created":"2016-02-26","cited_by_count":68},{"id":"1604.02532","title":"T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos","created":"2016-04-09","cited_by_count":67},{"id":"1711.11577","title":"Towards High Performance Video Object Detection","created":"2017-11-30","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":"1803.05549","title":"Object Detection in Video with Spatiotemporal Sampling Networks","created":"2018-03-15","cited_by_count":57},{"id":"1912.05384","title":"AugFPN: Improving Multi-scale Feature Learning for Object Detection","created":"2019-12-11","cited_by_count":55},{"id":"2109.03495","title":"Temporal RoI Align for Video Object Recognition","created":"2021-09-08","cited_by_count":44},{"id":"1712.06317","title":"Video Object Detection with an Aligned Spatial-Temporal Memory","created":"2017-12-18","cited_by_count":42},{"id":"1604.04053","title":"Object Detection from Video Tubelets with Convolutional Neural Networks","created":"2016-04-14","cited_by_count":40},{"id":"2108.05821","title":"TF-Blender: Temporal Feature Blender for Video Object Detection","created":"2021-08-12","cited_by_count":37},{"id":"1903.09126","title":"Progressive Sparse Local Attention for Video object detection","created":"2019-03-21","cited_by_count":30},{"id":"1803.06799","title":"Revisiting RCNN: On Awakening the Classification Power of Faster RCNN","created":"2018-03-19","cited_by_count":28},{"id":"1804.05472","title":"Optimizing Video Object Detection via a Scale-Time Lattice","created":"2018-04-16","cited_by_count":25},{"id":"1905.05880","title":"Budget-aware Semi-Supervised Semantic and Instance Segmentation","created":"2019-05-14","cited_by_count":12},{"id":"1801.09823","title":"Object Detection in Videos by High Quality Object Linking","created":"2018-01-30","cited_by_count":11},{"id":"1807.08638","title":"Joint Anchor-Feature Refinement for Real-Time Accurate Object Detection in Images and Videos","created":"2018-07-23","cited_by_count":9}],"next_cursor":null}