{"list":"other","total":68,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"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":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"1805.01978","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","created":"2018-05-05","cited_by_count":1845},{"id":"1803.08494","title":"Group Normalization","created":"2018-03-22","cited_by_count":1524},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"id":"1906.05849","title":"Contrastive Multiview Coding","created":"2019-06-13","cited_by_count":1301},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"1904.07850","title":"Objects as Points","created":"2019-04-16","cited_by_count":1175},{"id":"2107.08430","title":"YOLOX: Exceeding YOLO Series in 2021","created":"2021-07-18","cited_by_count":1071},{"id":"1703.07402","title":"Simple Online and Realtime Tracking with a Deep Association Metric","created":"2017-03-21","cited_by_count":910},{"id":"1602.00763","title":"Simple Online and Realtime Tracking","created":"2016-02-02","cited_by_count":868},{"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":"1906.00910","title":"Learning Representations by Maximizing Mutual Information Across Views","created":"2019-06-03","cited_by_count":734},{"id":"1609.01775","title":"Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking","created":"2016-09-06","cited_by_count":692},{"id":"1905.09272","title":"Data-Efficient Image Recognition with Contrastive Predictive Coding","created":"2019-05-22","cited_by_count":673},{"id":"1606.09549","title":"Fully-Convolutional Siamese Networks for Object Tracking","created":"2016-06-30","cited_by_count":568},{"id":"2009.07736","title":"HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking","created":"2020-09-16","cited_by_count":552},{"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":"1804.06208","title":"Simple Baselines for Human Pose Estimation and Tracking","created":"2018-04-17","cited_by_count":502},{"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":"2002.10857","title":"Circle Loss: A Unified Perspective of Pair Similarity Optimization","created":"2020-02-25","cited_by_count":403},{"id":"1905.04804","title":"Video Instance Segmentation","created":"2019-05-12","cited_by_count":393},{"id":"1903.05625","title":"Tracking without bells and whistles","created":"2019-03-13","cited_by_count":382},{"id":"1911.11929","title":"CSPNet: A New Backbone that can Enhance Learning Capability of CNN","created":"2019-11-27","cited_by_count":381},{"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":"2003.09003","title":"MOT20: A benchmark for multi object tracking in crowded scenes","created":"2020-03-19","cited_by_count":357},{"id":"2203.14360","title":"Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking","created":"2022-03-27","cited_by_count":346},{"id":"1909.12605","title":"Towards Real-Time Multi-Object Tracking","created":"2019-09-27","cited_by_count":311},{"id":"1805.00123","title":"CrowdHuman: A Benchmark for Detecting Human in a Crowd","created":"2018-04-30","cited_by_count":284},{"id":"1904.02701","title":"Libra R-CNN: Towards Balanced Learning for Object Detection","created":"2019-04-04","cited_by_count":255},{"id":"2006.06664","title":"Quasi-Dense Similarity Learning for Multiple Object Tracking","created":"2020-06-11","cited_by_count":220},{"id":"2111.14690","title":"DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motion","created":"2021-11-29","cited_by_count":217},{"id":"2202.13514","title":"StrongSORT: Make DeepSORT Great Again","created":"2022-02-28","cited_by_count":213},{"id":"1702.05693","title":"CityPersons: A Diverse Dataset for Pedestrian Detection","created":"2017-02-19","cited_by_count":172},{"id":"2103.08808","title":"Track to Detect and Segment: An Online Multi-Object Tracker","created":"2021-03-16","cited_by_count":156},{"id":"2005.10356","title":"TAO: A Large-Scale Benchmark for Tracking Any Object","created":"2020-05-20","cited_by_count":147},{"id":"1710.03958","title":"Detect to Track and Track to Detect","created":"2017-10-11","cited_by_count":131},{"id":"2003.08429","title":"STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos","created":"2020-03-18","cited_by_count":121},{"id":"2007.14557","title":"Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Tracking","created":"2020-07-29","cited_by_count":115},{"id":"2203.13250","title":"Global Tracking Transformers","created":"2022-03-24","cited_by_count":110},{"id":"1604.01802","title":"Learning to Track at 100 FPS with Deep Regression Networks","created":"2016-04-06","cited_by_count":89},{"id":"2103.07351","title":"Monocular Quasi-Dense 3D Object Tracking","created":"2021-03-12","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":"1701.01909","title":"Tracking The Untrackable: Learning To Track Multiple Cues with Long-Term Dependencies","created":"2017-01-08","cited_by_count":76},{"id":"1610.06136","title":"POI: Multiple Object Tracking with High Performance Detection and Appearance Feature","created":"2016-10-19","cited_by_count":74},{"id":"2003.13870","title":"RetinaTrack: Online Single Stage Joint Detection and Tracking","created":"2020-03-30","cited_by_count":67},{"id":"1604.03635","title":"Online Multi-Target Tracking Using Recurrent Neural Networks","created":"2016-04-13","cited_by_count":59},{"id":"2003.09163","title":"Detection in Crowded Scenes: One Proposal, Multiple Predictions","created":"2020-03-20","cited_by_count":59},{"id":"1910.00130","title":"Track to Reconstruct and Reconstruct to Track","created":"2019-09-30","cited_by_count":49},{"id":"1504.02340","title":"Near-Online Multi-target Tracking with Aggregated Local Flow Descriptor","created":"2015-04-09","cited_by_count":46},{"id":"2207.12978","title":"Tracking Every Thing in the Wild","created":"2022-07-26","cited_by_count":44},{"id":"2106.11958","title":"Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation","created":"2021-06-22","cited_by_count":43},{"id":"1802.09298","title":"Beyond Pixels: Leveraging Geometry and Shape Cues for Online Multi-Object Tracking","created":"2018-02-26","cited_by_count":40},{"id":"1809.07357","title":"Combined Image- and World-Space Tracking in Traffic Scenes","created":"2018-09-19","cited_by_count":29},{"id":"2101.08040","title":"1st Place Solution to ECCV-TAO-2020: Detect and Represent Any Object for Tracking","created":"2021-01-20","cited_by_count":17},{"id":"2205.00968","title":"Detection Recovery in Online Multi-Object Tracking with Sparse Graph Tracker","created":"2022-05-02","cited_by_count":15}],"next_cursor":null}