{"list":"other","total":58,"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":"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":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1706.02413","title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","created":"2017-06-07","cited_by_count":4401},{"id":"1901.05103","title":"DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation","created":"2019-01-16","cited_by_count":2689},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"1711.06396","title":"VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection","created":"2017-11-17","cited_by_count":1323},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"1703.07402","title":"Simple Online and Realtime Tracking with a Deep Association Metric","created":"2017-03-21","cited_by_count":910},{"id":"1712.06584","title":"End-to-end Recovery of Human Shape and Pose","created":"2017-12-18","cited_by_count":885},{"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":"1911.02620","title":"Argoverse: 3D Tracking and Forecasting with Rich Maps","created":"2019-11-06","cited_by_count":732},{"id":"2203.16527","title":"Exploring Plain Vision Transformer Backbones for Object Detection","created":"2022-03-30","cited_by_count":724},{"id":"1811.07246","title":"PointConv: Deep Convolutional Networks on 3D Point Clouds","created":"2018-11-17","cited_by_count":657},{"id":"1912.05656","title":"VIBE: Video Inference for Human Body Pose and Shape Estimation","created":"2019-12-11","cited_by_count":620},{"id":"2012.07177","title":"Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation","created":"2020-12-13","cited_by_count":596},{"id":"1604.00449","title":"3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction","created":"2016-04-02","cited_by_count":588},{"id":"2009.07736","title":"HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking","created":"2020-09-16","cited_by_count":552},{"id":"1901.02970","title":"Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation","created":"2019-01-09","cited_by_count":495},{"id":"2003.09003","title":"MOT20: A benchmark for multi object tracking in crowded scenes","created":"2020-03-19","cited_by_count":357},{"id":"2305.20091","title":"Humans in 4D: Reconstructing and Tracking Humans with Transformers","created":"2023-05-31","cited_by_count":350},{"id":"1611.05009","title":"OctNet: Learning Deep 3D Representations at High Resolutions","created":"2016-11-15","cited_by_count":342},{"id":"2104.08527","title":"PARE: Part Attention Regressor for 3D Human Body Estimation","created":"2021-04-17","cited_by_count":337},{"id":"1803.07549","title":"Learning Category-Specific Mesh Reconstruction from Image Collections","created":"2018-03-20","cited_by_count":317},{"id":"1704.07809","title":"Hand Keypoint Detection in Single Images using Multiview Bootstrapping","created":"2017-04-25","cited_by_count":231},{"id":"1804.03142","title":"Markerless tracking of user-defined features with deep learning","created":"2018-04-09","cited_by_count":206},{"id":"2207.10660","title":"Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild","created":"2022-07-21","cited_by_count":160},{"id":"2112.08274","title":"Putting People in their Place: Monocular Regression of 3D People in Depth","created":"2021-12-15","cited_by_count":142},{"id":"2103.12340","title":"Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers","created":"2021-03-23","cited_by_count":104},{"id":"1509.01329","title":"Semantic Amodal Segmentation","created":"2015-09-04","cited_by_count":103},{"id":"1803.08319","title":"Learning to Detect and Track Visible and Occluded Body Joints in a Virtual World","created":"2018-03-22","cited_by_count":82},{"id":"2004.00614","title":"Articulation-aware Canonical Surface Mapping","created":"2020-04-01","cited_by_count":81},{"id":"2112.01988","title":"ROCA: Robust CAD Model Retrieval and Alignment from a Single Image","created":"2021-12-03","cited_by_count":67},{"id":"1909.06043","title":"End-to-End Learnable Geometric Vision by Backpropagating PnP Optimization","created":"2019-09-13","cited_by_count":65},{"id":"1804.08864","title":"Learning to See the Invisible: End-to-End Trainable Amodal Instance Segmentation","created":"2018-04-24","cited_by_count":62},{"id":"1703.10239","title":"SeGAN: Segmenting and Generating the Invisible","created":"2017-03-29","cited_by_count":60},{"id":"1811.12222","title":"ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Driving","created":"2018-11-29","cited_by_count":59},{"id":"2208.01166","title":"Ithaca365: Dataset and Driving Perception under Repeated and Challenging Weather Conditions","created":"2022-08-01","cited_by_count":48},{"id":"2111.14341","title":"OOD-CV: A Benchmark for Robustness to Out-of-Distribution Shifts of Individual Nuisances in Natural Images","created":"2021-11-29","cited_by_count":46},{"id":"2101.12378","title":"NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose Estimation","created":"2021-01-29","cited_by_count":41},{"id":"1803.10870","title":"Learning to Look around Objects for Top-View Representations of Outdoor Scenes","created":"2018-03-28","cited_by_count":37},{"id":"1508.04546","title":"Learning Analysis-by-Synthesis for 6D Pose Estimation in RGB-D Images","created":"2015-08-19","cited_by_count":29},{"id":"2007.13124","title":"GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware Supervision","created":"2020-07-26","cited_by_count":28},{"id":"2012.02107","title":"Robust Instance Segmentation through Reasoning about Multi-Object Occlusion","created":"2020-12-03","cited_by_count":23},{"id":"2204.10380","title":"The 6th AI City Challenge","created":"2022-04-21","cited_by_count":23},{"id":"2209.05624","title":"Robust Category-Level 6D Pose Estimation with Coarse-to-Fine Rendering of Neural Features","created":"2022-09-12","cited_by_count":23},{"id":"1612.02699","title":"Deep Supervision with Shape Concepts for Occlusion-Aware 3D Object Parsing","created":"2016-12-08","cited_by_count":19},{"id":"2007.11965","title":"CAD-Deform: Deformable Fitting of CAD Models to 3D Scans","created":"2020-07-23","cited_by_count":17},{"id":"2009.13146","title":"Amodal 3D Reconstruction for Robotic Manipulation via Stability and Connectivity","created":"2020-09-28","cited_by_count":15},{"id":"1411.5935","title":"Towards Scene Understanding with Detailed 3D Object Representations","created":"2014-11-18","cited_by_count":9},{"id":"2311.04243","title":"Toward Planet-Wide Traffic Camera Calibration","created":"2023-11-06","cited_by_count":7}],"next_cursor":null}