{"list":"other","total":107,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"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":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1503.03832","title":"FaceNet: A Unified Embedding for Face Recognition and Clustering","created":"2015-03-12","cited_by_count":2849},{"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":"1808.01244","title":"CornerNet: Detecting Objects as Paired Keypoints","created":"2018-08-03","cited_by_count":763},{"id":"1606.09549","title":"Fully-Convolutional Siamese Networks for Object Tracking","created":"2016-06-30","cited_by_count":568},{"id":"1810.11981","title":"GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild","created":"2018-10-29","cited_by_count":475},{"id":"1812.11703","title":"SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks","created":"2018-12-31","cited_by_count":446},{"id":"1809.07845","title":"LaSOT: A High-quality Benchmark for Large-scale Single Object Tracking","created":"2018-09-20","cited_by_count":429},{"id":"2103.15436","title":"Transformer Tracking","created":"2021-03-29","cited_by_count":412},{"id":"2103.17154","title":"Learning Spatio-Temporal Transformer for Visual Tracking","created":"2021-03-31","cited_by_count":350},{"id":"1904.07220","title":"Learning Discriminative Model Prediction for Tracking","created":"2019-04-15","cited_by_count":344},{"id":"1803.10794","title":"TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild","created":"2018-03-28","cited_by_count":343},{"id":"1403.6382","title":"CNN Features off-the-shelf: an Astounding Baseline for Recognition","created":"2014-03-23","cited_by_count":316},{"id":"1811.07628","title":"ATOM: Accurate Tracking by Overlap Maximization","created":"2018-11-19","cited_by_count":285},{"id":"1812.05050","title":"Fast Online Object Tracking and Segmentation: A Unifying Approach","created":"2018-12-12","cited_by_count":272},{"id":"1611.09224","title":"ECO: Efficient Convolution Operators for Tracking","created":"2016-11-28","cited_by_count":239},{"id":"1809.00461","title":"YouTube-VOS: Sequence-to-Sequence Video Object Segmentation","created":"2018-09-03","cited_by_count":232},{"id":"2003.12565","title":"Probabilistic Regression for Visual Tracking","created":"2020-03-27","cited_by_count":231},{"id":"2103.11681","title":"Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking","created":"2021-03-22","cited_by_count":220},{"id":"2006.10721","title":"Ocean: Object-aware Anchor-free Tracking","created":"2020-06-18","cited_by_count":212},{"id":"1608.01471","title":"UnitBox: An Advanced Object Detection Network","created":"2016-08-04","cited_by_count":205},{"id":"1611.10012","title":"Speed/accuracy trade-offs for modern convolutional object detectors","created":"2016-11-30","cited_by_count":198},{"id":"2003.06761","title":"Siamese Box Adaptive Network for Visual Tracking","created":"2020-03-15","cited_by_count":189},{"id":"1808.06048","title":"Distractor-aware Siamese Networks for Visual Object Tracking","created":"2018-08-18","cited_by_count":187},{"id":"1911.06188","title":"SiamFC++: Towards Robust and Accurate Visual Tracking with Target Estimation Guidelines","created":"2019-11-14","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":"1911.12836","title":"Siam R-CNN: Visual Tracking by Re-Detection","created":"2019-11-28","cited_by_count":174},{"id":"1901.01660","title":"Deeper and Wider Siamese Networks for Real-Time Visual Tracking","created":"2019-01-07","cited_by_count":156},{"id":"1911.07241","title":"SiamCAR: Siamese Fully Convolutional Classification and Regression for Visual Tracking","created":"2019-11-17","cited_by_count":148},{"id":"1903.00621","title":"Feature Selective Anchor-Free Module for Single-Shot Object Detection","created":"2019-03-02","cited_by_count":139},{"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":"2103.16556","title":"Learning Target Candidate Association to Keep Track of What Not to Track","created":"2021-03-30","cited_by_count":131},{"id":"1405.3531","title":"Return of the Devil in the Details: Delving Deep into Convolutional Nets","created":"2014-05-14","cited_by_count":122},{"id":"2003.11014","title":"Know Your Surroundings: Exploiting Scene Information for Object Tracking","created":"2020-03-24","cited_by_count":119},{"id":"1503.01313","title":"A Novel Performance Evaluation Methodology for Single-Target Trackers","created":"2015-03-04","cited_by_count":113},{"id":"1702.00824","title":"YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Video","created":"2017-02-02","cited_by_count":109},{"id":"2004.06711","title":"Deformable Siamese Attention Networks for Visual Object Tracking","created":"2020-04-14","cited_by_count":97},{"id":"2104.00324","title":"STMTrack: Template-free Visual Tracking with Space-time Memory Networks","created":"2021-04-01","cited_by_count":91},{"id":"1704.06036","title":"End-to-end representation learning for Correlation Filter based tracking","created":"2017-04-20","cited_by_count":90},{"id":"1604.01802","title":"Learning to Track at 100 FPS with Deep Regression Networks","created":"2016-04-06","cited_by_count":89},{"id":"2003.11540","title":"Learning What to Learn for Video Object Segmentation","created":"2020-03-25","cited_by_count":89},{"id":"2104.14545","title":"LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search","created":"2021-04-29","cited_by_count":82},{"id":"2007.02024","title":"Alpha-Refine: Boosting Tracking Performance by Precise Bounding Box Estimation","created":"2020-07-04","cited_by_count":81},{"id":"1604.07866","title":"Learning by tracking: Siamese CNN for robust target association","created":"2016-04-26","cited_by_count":79},{"id":"1902.00749","title":"Online Multi-Object Tracking with Dual Matching Attention Networks","created":"2019-02-02","cited_by_count":77},{"id":"1908.00855","title":"Learning the Model Update for Siamese Trackers","created":"2019-08-02","cited_by_count":76},{"id":"2003.00908","title":"Learning Fast and Robust Target Models for Video Object Segmentation","created":"2020-02-27","cited_by_count":76},{"id":"1409.4326","title":"Computing the Stereo Matching Cost with a Convolutional Neural Network","created":"2014-09-15","cited_by_count":74},{"id":"1904.01828","title":"Unsupervised Deep Tracking","created":"2019-04-03","cited_by_count":74},{"id":"1906.06618","title":"How To Train Your Deep Multi-Object Tracker","created":"2019-06-15","cited_by_count":71},{"id":"1911.08862","title":"D3S -- A Discriminative Single Shot Segmentation Tracker","created":"2019-11-20","cited_by_count":69},{"id":"1608.03773","title":"Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking","created":"2016-08-12","cited_by_count":66},{"id":"1608.05571","title":"Learning Spatially Regularized Correlation Filters for Visual Tracking","created":"2016-08-19","cited_by_count":66},{"id":"1703.04590","title":"Learning Background-Aware Correlation Filters for Visual Tracking","created":"2017-03-14","cited_by_count":65},{"id":"1812.06148","title":"Siamese Cascaded Region Proposal Networks for Real-Time Visual Tracking","created":"2018-12-14","cited_by_count":65},{"id":"1803.08679","title":"Learning Spatial-Temporal Regularized Correlation Filters for Visual Tracking","created":"2018-03-23","cited_by_count":63},{"id":"1805.05563","title":"Facial Landmark Detection: a Literature Survey","created":"2018-05-15","cited_by_count":63},{"id":"1802.08817","title":"A Twofold Siamese Network for Real-Time Object Tracking","created":"2018-02-24","cited_by_count":62},{"id":"2003.12949","title":"AutoTrack: Towards High-Performance Visual Tracking for UAV with Automatic Spatio-Temporal Regularization","created":"2020-03-29","cited_by_count":62},{"id":"2105.11595","title":"SiamMOT: Siamese Multi-Object Tracking","created":"2021-05-25","cited_by_count":62},{"id":"1512.01355","title":"Staple: Complementary Learners for Real-Time Tracking","created":"2015-12-04","cited_by_count":60},{"id":"1803.07268","title":"Learning Dynamic Memory Networks for Object Tracking","created":"2018-03-20","cited_by_count":59},{"id":"2104.11221","title":"Opening up Open-World Tracking","created":"2021-04-22","cited_by_count":50},{"id":"1908.02231","title":"Learning Aberrance Repressed Correlation Filters for Real-Time UAV Tracking","created":"2019-08-06","cited_by_count":47},{"id":"1609.06141","title":"Discriminative Scale Space Tracking","created":"2016-09-20","cited_by_count":46},{"id":"1611.08461","title":"Discriminative Correlation Filter with Channel and Spatial Reliability","created":"2016-11-25","cited_by_count":45},{"id":"1904.01772","title":"Target-Aware Deep Tracking","created":"2019-04-03","cited_by_count":43},{"id":"1804.06833","title":"Unveiling the Power of Deep Tracking","created":"2018-04-18","cited_by_count":41},{"id":"1909.06800","title":"GradNet: Gradient-Guided Network for Visual Object Tracking","created":"2019-09-15","cited_by_count":41},{"id":"1801.03049","title":"Meta-Tracker: Fast and Robust Online Adaptation for Visual Object Trackers","created":"2018-01-09","cited_by_count":34},{"id":"1909.01840","title":"'Skimming-Perusal' Tracking: A Framework for Real-Time and Robust Long-term Tracking","created":"2019-09-04","cited_by_count":34},{"id":"1811.10863","title":"Object Tracking by Reconstruction with View-Specific Discriminative Correlation Filters","created":"2018-11-27","cited_by_count":33},{"id":"2003.11291","title":"A Unified Object Motion and Affinity Model for Online Multi-Object Tracking","created":"2020-03-25","cited_by_count":33},{"id":"2003.09595","title":"Cooling-Shrinking Attack: Blinding the Tracker with Imperceptible Noises","created":"2020-03-21","cited_by_count":32},{"id":"1708.00225","title":"CREST: Convolutional Residual Learning for Visual Tracking","created":"2017-08-01","cited_by_count":29},{"id":"1904.04452","title":"SPM-Tracker: Series-Parallel Matching for Real-Time Visual Object Tracking","created":"2019-04-09","cited_by_count":29},{"id":"2007.11984","title":"Unsupervised Deep Representation Learning for Real-Time Tracking","created":"2020-07-22","cited_by_count":29},{"id":"1907.12006","title":"ROAM: Recurrently Optimizing Tracking Model","created":"2019-07-28","cited_by_count":28},{"id":"1303.4803","title":"A Survey of Appearance Models in Visual Object Tracking","created":"2013-03-20","cited_by_count":21},{"id":"1711.01124","title":"End-to-end Flow Correlation Tracking with Spatial-temporal Attention","created":"2017-11-03","cited_by_count":21},{"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":"1708.02973","title":"Learning Policies for Adaptive Tracking with Deep Feature Cascades","created":"2017-08-09","cited_by_count":19},{"id":"1902.08231","title":"Online Multi-Object Tracking with Instance-Aware Tracker and Dynamic Model Refreshment","created":"2019-02-21","cited_by_count":18},{"id":"1907.13242","title":"Joint Group Feature Selection and Discriminative Filter Learning for Robust Visual Object Tracking","created":"2019-07-30","cited_by_count":17},{"id":"1704.04057","title":"DCFNet: Discriminant Correlation Filters Network for Visual Tracking","created":"2017-04-13","cited_by_count":11},{"id":"1907.07613","title":"Visual Tracking via Dynamic Memory Networks","created":"2019-07-12","cited_by_count":11},{"id":"1703.05020","title":"Large Margin Object Tracking with Circulant Feature Maps","created":"2017-03-15","cited_by_count":9},{"id":"1707.02309","title":"Adaptive Correlation Filters with Long-Term and Short-Term Memory for Object Tracking","created":"2017-07-07","cited_by_count":8},{"id":"1803.10537","title":"Context-aware Deep Feature Compression for High-speed Visual Tracking","created":"2018-03-28","cited_by_count":8},{"id":"1804.08965","title":"Correlation Tracking via Joint Discrimination and Reliability Learning","created":"2018-04-24","cited_by_count":7}],"next_cursor":"100"}