{"list":"other","total":65,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"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":"1911.08287","title":"Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression","created":"2019-11-19","cited_by_count":459},{"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":"2109.10852","title":"Pix2seq: A Language Modeling Framework for Object Detection","created":"2021-09-22","cited_by_count":349},{"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":"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":"2001.06303","title":"Detection and Tracking Meet Drones Challenge","created":"2020-01-16","cited_by_count":263},{"id":"1611.09224","title":"ECO: Efficient Convolution Operators for Tracking","created":"2016-11-28","cited_by_count":239},{"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":"1510.07945","title":"Learning Multi-Domain Convolutional Neural Networks for Visual Tracking","created":"2015-10-27","cited_by_count":209},{"id":"1804.00518","title":"The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking","created":"2018-03-26","cited_by_count":208},{"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":"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":"1904.05979","title":"The Sound of Motions","created":"2019-04-11","cited_by_count":146},{"id":"2004.05508","title":"MetaIQA: Deep Meta-learning for No-Reference Image Quality Assessment","created":"2020-04-11","cited_by_count":144},{"id":"1703.05884","title":"Need for Speed: A Benchmark for Higher Frame Rate Object Tracking","created":"2017-03-17","cited_by_count":137},{"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":"2103.16746","title":"Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark","created":"2021-03-31","cited_by_count":126},{"id":"1511.04164","title":"Natural Language Object Retrieval","created":"2015-11-13","cited_by_count":124},{"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":"2104.00946","title":"UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehicles","created":"2021-04-02","cited_by_count":96},{"id":"1604.01802","title":"Learning to Track at 100 FPS with Deep Regression Networks","created":"2016-04-06","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":"1908.00855","title":"Learning the Model Update for Siamese Trackers","created":"2019-08-02","cited_by_count":76},{"id":"1904.01828","title":"Unsupervised Deep Tracking","created":"2019-04-03","cited_by_count":74},{"id":"2108.00202","title":"HiFT: Hierarchical Feature Transformer for Aerial Tracking","created":"2021-07-31","cited_by_count":72},{"id":"2011.11204","title":"Graph Attention Tracking","created":"2020-11-23","cited_by_count":70},{"id":"2108.00803","title":"Learn to Match: Automatic Matching Network Design for Visual Tracking","created":"2021-08-02","cited_by_count":67},{"id":"1608.03773","title":"Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking","created":"2016-08-12","cited_by_count":66},{"id":"2008.00217","title":"Efficient Adversarial Attacks for Visual Object Tracking","created":"2020-08-01","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":"1804.04273","title":"VITAL: VIsual Tracking via Adversarial Learning","created":"2018-04-12","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":"1910.11760","title":"Self-supervised Moving Vehicle Tracking with Stereo Sound","created":"2019-10-25","cited_by_count":63},{"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":"1912.08531","title":"GlobalTrack: A Simple and Strong Baseline for Long-term Tracking","created":"2019-12-18","cited_by_count":57},{"id":"1803.09502","title":"Long-term Tracking in the Wild: A Benchmark","created":"2018-03-26","cited_by_count":55},{"id":"1908.02231","title":"Learning Aberrance Repressed Correlation Filters for Real-Time UAV Tracking","created":"2019-08-06","cited_by_count":47},{"id":"1706.03038","title":"Okutama-Action: An Aerial View Video Dataset for Concurrent Human Action Detection","created":"2017-06-09","cited_by_count":46},{"id":"1801.03049","title":"Meta-Tracker: Fast and Robust Online Adaptation for Visual Object Trackers","created":"2018-01-09","cited_by_count":34},{"id":"2101.08466","title":"Anti-UAV: A Large Multi-Modal Benchmark for UAV Tracking","created":"2021-01-21","cited_by_count":31},{"id":"2007.09919","title":"Robust Tracking against Adversarial Attacks","created":"2020-07-20","cited_by_count":28},{"id":"2101.08446","title":"All-Day Object Tracking for Unmanned Aerial Vehicle","created":"2021-01-21","cited_by_count":28},{"id":"2008.03467","title":"RPT: Learning Point Set Representation for Siamese Visual Tracking","created":"2020-08-08","cited_by_count":26},{"id":"1807.11348","title":"Learning Adaptive Discriminative Correlation Filters via Temporal Consistency Preserving Spatial Feature Selection for Robust Visual Tracking","created":"2018-07-30","cited_by_count":25},{"id":"2103.14938","title":"IoU Attack: Towards Temporally Coherent Black-Box Adversarial Attack for Visual Object Tracking","created":"2021-03-27","cited_by_count":25},{"id":"1603.09725","title":"Audio-Visual Speaker Diarization Based on Spatiotemporal Bayesian Fusion","created":"2016-03-31","cited_by_count":23},{"id":"2108.03821","title":"Video Annotation for Visual Tracking via Selection and Refinement","created":"2021-08-09","cited_by_count":5}],"next_cursor":null}