{"list":"other","total":53,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"1906.07155","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","created":"2019-06-17","cited_by_count":1385},{"id":"1902.09630","title":"Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression","created":"2019-02-25","cited_by_count":1368},{"id":"2203.03605","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","created":"2022-03-07","cited_by_count":1319},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2107.08430","title":"YOLOX: Exceeding YOLO Series in 2021","created":"2021-07-18","cited_by_count":1071},{"id":"2011.12450","title":"Sparse R-CNN: End-to-End Object Detection with Learnable Proposals","created":"2020-11-25","cited_by_count":495},{"id":"2211.05778","title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","created":"2022-11-10","cited_by_count":482},{"id":"2006.04388","title":"Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection","created":"2020-06-08","cited_by_count":409},{"id":"2310.01852","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","created":"2023-10-03","cited_by_count":370},{"id":"2203.16220","title":"Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detection","created":"2022-03-30","cited_by_count":317},{"id":"2103.06011","title":"DSEC: A Stereo Event Camera Dataset for Driving Scenarios","created":"2021-03-10","cited_by_count":303},{"id":"1805.00123","title":"CrowdHuman: A Benchmark for Detecting Human in a Crowd","created":"2018-04-30","cited_by_count":284},{"id":"2211.12860","title":"DETRs with Collaborative Hybrid Assignments Training","created":"2022-11-22","cited_by_count":274},{"id":"2108.10831","title":"LLVIP: A Visible-infrared Paired Dataset for Low-light Vision","created":"2021-08-24","cited_by_count":231},{"id":"2203.04838","title":"CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers","created":"2022-03-09","cited_by_count":231},{"id":"2009.13436","title":"Learning to Detect Objects with a 1 Megapixel Event Camera","created":"2020-09-28","cited_by_count":186},{"id":"2007.11858","title":"Whole-Body Human Pose Estimation in the Wild","created":"2020-07-23","cited_by_count":178},{"id":"1702.05693","title":"CityPersons: A Diverse Dataset for Pedestrian Detection","created":"2017-02-19","cited_by_count":172},{"id":"2307.10802","title":"Meta-Transformer: A Unified Framework for Multimodal Learning","created":"2023-07-20","cited_by_count":136},{"id":"2303.01480","title":"Delivering Arbitrary-Modal Semantic Segmentation","created":"2023-03-02","cited_by_count":117},{"id":"2001.08499","title":"A Large Scale Event-based Detection Dataset for Automotive","created":"2020-01-23","cited_by_count":109},{"id":"2204.08680","title":"Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer","created":"2022-04-19","cited_by_count":101},{"id":"2111.00273","title":"Cross-Modality Fusion Transformer for Multispectral Object Detection","created":"2021-10-30","cited_by_count":86},{"id":"2009.12664","title":"Multispectral Fusion for Object Detection with Cyclic Fuse-and-Refine Blocks","created":"2020-09-26","cited_by_count":85},{"id":"1611.02644","title":"Multispectral Deep Neural Networks for Pedestrian Detection","created":"2016-11-08","cited_by_count":82},{"id":"2107.00420","title":"CBNet: A Composite Backbone Network Architecture for Object Detection","created":"2021-07-01","cited_by_count":77},{"id":"2104.02904","title":"Multimodal Object Detection via Probabilistic Ensembling","created":"2021-04-07","cited_by_count":68},{"id":"2003.09163","title":"Detection in Crowded Scenes: One Proposal, Multiple Predictions","created":"2020-03-20","cited_by_count":59},{"id":"2303.02936","title":"UniHCP: A Unified Model for Human-Centric Perceptions","created":"2023-03-06","cited_by_count":59},{"id":"1808.04818","title":"Multispectral Pedestrian Detection via Simultaneous Detection and Segmentation","created":"2018-08-14","cited_by_count":49},{"id":"2112.02991","title":"Cross-Modality Attentive Feature Fusion for Object Detection in Multispectral Remote Sensing Imagery","created":"2021-12-06","cited_by_count":45},{"id":"2303.05675","title":"HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining","created":"2023-03-10","cited_by_count":38},{"id":"2204.01026","title":"STCrowd: A Multimodal Dataset for Pedestrian Perception in Crowded Scenes","created":"2022-04-03","cited_by_count":35},{"id":"1707.05733","title":"Choosing Smartly: Adaptive Multimodal Fusion for Object Detection in Changing Environments","created":"2017-07-18","cited_by_count":34},{"id":"2203.07669","title":"Progressive End-to-End Object Detection in Crowded Scenes","created":"2022-03-15","cited_by_count":31},{"id":"2206.15157","title":"HRFuser: A Multi-resolution Sensor Fusion Architecture for 2D Object Detection","created":"2022-06-30","cited_by_count":31},{"id":"2207.04976","title":"Dual Vision Transformer","created":"2022-07-11","cited_by_count":29},{"id":"1708.00674","title":"Deep Detection of People and their Mobility Aids for a Hospital Robot","created":"2017-08-02","cited_by_count":9},{"id":"2312.05525","title":"You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-Person Multi-Task Human-Centric Perception","created":"2023-12-09","cited_by_count":9},{"id":"2404.19401","title":"UniFS: Universal Few-shot Instance Perception with Point Representations","created":"2024-04-30","cited_by_count":2}],"next_cursor":null}