{"list":"other","total":58,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"id":"1904.01355","title":"FCOS: Fully Convolutional One-Stage Object Detection","created":"2019-04-02","cited_by_count":1577},{"id":"1907.01341","title":"Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer","created":"2019-07-02","cited_by_count":1495},{"id":"1911.11763","title":"SuperGlue: Learning Feature Matching with Graph Neural Networks","created":"2019-11-26","cited_by_count":1443},{"id":"1712.07629","title":"SuperPoint: Self-Supervised Interest Point Detection and Description","created":"2017-12-20","cited_by_count":1320},{"id":"1406.2283","title":"Depth Map Prediction from a Single Image using a Multi-Scale Deep Network","created":"2014-06-09","cited_by_count":1274},{"id":"2203.17270","title":"BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers","created":"2022-03-31","cited_by_count":1218},{"id":"1904.07850","title":"Objects as Points","created":"2019-04-16","cited_by_count":1175},{"id":"1502.00956","title":"ORB-SLAM: a Versatile and Accurate Monocular SLAM System","created":"2015-02-03","cited_by_count":988},{"id":"1703.07402","title":"Simple Online and Realtime Tracking with a Deep Association Metric","created":"2017-03-21","cited_by_count":910},{"id":"1912.13192","title":"PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection","created":"2019-12-31","cited_by_count":891},{"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":"1704.07813","title":"Unsupervised Learning of Depth and Ego-Motion from Video","created":"2017-04-25","cited_by_count":782},{"id":"2112.11790","title":"BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View","created":"2021-12-22","cited_by_count":713},{"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":"2110.06922","title":"DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries","created":"2021-10-13","cited_by_count":658},{"id":"1812.03506","title":"From Coarse to Fine: Robust Hierarchical Localization at Large Scale","created":"2018-12-09","cited_by_count":559},{"id":"2009.07736","title":"HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking","created":"2020-09-16","cited_by_count":552},{"id":"2101.02702","title":"TrackFormer: Multi-Object Tracking with Transformers","created":"2021-01-07","cited_by_count":518},{"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":"2104.10956","title":"FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection","created":"2021-04-22","cited_by_count":447},{"id":"1707.06484","title":"Deep Layer Aggregation","created":"2017-07-20","cited_by_count":436},{"id":"1903.05625","title":"Tracking without bells and whistles","created":"2019-03-13","cited_by_count":382},{"id":"2105.03247","title":"MOTR: End-to-End Multiple-Object Tracking with Transformer","created":"2021-05-07","cited_by_count":381},{"id":"2203.14360","title":"Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking","created":"2022-03-27","cited_by_count":346},{"id":"2108.06417","title":"Is Pseudo-Lidar needed for Monocular 3D Object detection?","created":"2021-08-13","cited_by_count":249},{"id":"2004.15021","title":"Consistent Video Depth Estimation","created":"2020-04-30","cited_by_count":220},{"id":"1912.07515","title":"Learning a Neural Solver for Multiple Object Tracking","created":"2019-12-16","cited_by_count":198},{"id":"2104.02323","title":"Objects are Different: Flexible Monocular 3D Object Detection","created":"2021-04-06","cited_by_count":185},{"id":"2103.14258","title":"Learning to Track with Object Permanence","created":"2021-03-26","cited_by_count":119},{"id":"2203.13250","title":"Global Tracking Transformers","created":"2022-03-24","cited_by_count":110},{"id":"2205.00613","title":"MUTR3D: A Multi-camera Tracking Framework via 3D-to-2D Queries","created":"2022-05-02","cited_by_count":91},{"id":"2209.10248","title":"BEVStereo: Enhancing Depth Estimation in Multi-view 3D Object Detection with Dynamic Temporal Stereo","created":"2022-09-21","cited_by_count":90},{"id":"2207.10035","title":"Fully Sparse 3D Object Detection","created":"2022-07-20","cited_by_count":84},{"id":"2103.07351","title":"Monocular Quasi-Dense 3D Object Tracking","created":"2021-03-12","cited_by_count":81},{"id":"1811.10742","title":"Joint Monocular 3D Vehicle Detection and Tracking","created":"2018-11-26","cited_by_count":77},{"id":"1906.06618","title":"How To Train Your Deep Multi-Object Tracker","created":"2019-06-15","cited_by_count":71},{"id":"2003.13870","title":"RetinaTrack: Online Single Stage Joint Detection and Tracking","created":"2020-03-30","cited_by_count":67},{"id":"2008.08063","title":"AB3DMOT: A Baseline for 3D Multi-Object Tracking and New Evaluation Metrics","created":"2020-08-18","cited_by_count":63},{"id":"2210.06984","title":"QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Tracking","created":"2022-10-12","cited_by_count":61},{"id":"2102.02267","title":"DEFT: Detection Embeddings for Tracking","created":"2021-02-03","cited_by_count":56},{"id":"2108.01166","title":"Consistent Depth of Moving Objects in Video","created":"2021-08-02","cited_by_count":56},{"id":"2302.03802","title":"Standing Between Past and Future: Spatio-Temporal Modeling for Multi-Camera 3D Multi-Object Tracking","created":"2023-02-07","cited_by_count":54},{"id":"2103.16178","title":"Learnable Graph Matching: Incorporating Graph Partitioning with Deep Feature Learning for Multiple Object Tracking","created":"2021-03-30","cited_by_count":47},{"id":"2111.13672","title":"Immortal Tracker: Tracklet Never Dies","created":"2021-11-26","cited_by_count":42},{"id":"2207.12988","title":"Monocular 3D Object Detection with Depth from Motion","created":"2022-07-26","cited_by_count":38},{"id":"2012.02337","title":"Probabilistic Tracklet Scoring and Inpainting for Multiple Object Tracking","created":"2020-12-03","cited_by_count":36},{"id":"2012.08419","title":"Detecting Invisible People","created":"2020-12-15","cited_by_count":31},{"id":"2210.07681","title":"Quo Vadis: Is Trajectory Forecasting the Key Towards Long-Term Multi-Object Tracking?","created":"2022-10-14","cited_by_count":29},{"id":"2108.06029","title":"Track without Appearance: Learn Box and Tracklet Embedding with Local and Global Motion Patterns for Vehicle Tracking","created":"2021-08-13","cited_by_count":26},{"id":"2101.04206","title":"TrackMPNN: A Message Passing Graph Neural Architecture for Multi-Object Tracking","created":"2021-01-11","cited_by_count":21},{"id":"2204.01784","title":"Object Permanence Emerges in a Random Walk along Memory","created":"2022-04-04","cited_by_count":18},{"id":"2303.15416","title":"3D Video Object Detection with Learnable Object-Centric Global Optimization","created":"2023-03-27","cited_by_count":7}],"next_cursor":null}