{"list":"other","total":66,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"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":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2006.11275","title":"Center-based 3D Object Detection and Tracking","created":"2020-06-19","cited_by_count":1144},{"id":"2104.13921","title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","created":"2021-04-28","cited_by_count":906},{"id":"2110.11334","title":"Generalized Out-of-Distribution Detection: A Survey","created":"2021-10-21","cited_by_count":802},{"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":"2301.00493","title":"Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting","created":"2023-01-02","cited_by_count":707},{"id":"2302.12288","title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","created":"2023-02-23","cited_by_count":657},{"id":"2201.02605","title":"Detecting Twenty-thousand Classes using Image-level Supervision","created":"2022-01-07","cited_by_count":614},{"id":"2401.17270","title":"YOLO-World: Real-Time Open-Vocabulary Object Detection","created":"2024-01-30","cited_by_count":503},{"id":"2203.11496","title":"TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers","created":"2022-03-22","cited_by_count":466},{"id":"1911.11132","title":"Scaling Out-of-Distribution Detection for Real-World Settings","created":"2019-11-25","cited_by_count":465},{"id":"2011.10678","title":"Open-Vocabulary Object Detection Using Captions","created":"2020-11-20","cited_by_count":427},{"id":"2403.18913","title":"UniDepth: Universal Monocular Metric Depth Estimation","created":"2024-03-27","cited_by_count":382},{"id":"2306.09683","title":"Scaling Open-Vocabulary Object Detection","created":"2023-06-16","cited_by_count":343},{"id":"2203.17054","title":"BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detection","created":"2022-03-31","cited_by_count":341},{"id":"2205.13790","title":"BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework","created":"2022-05-27","cited_by_count":336},{"id":"2211.10439","title":"BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision","created":"2022-11-18","cited_by_count":302},{"id":"2211.12860","title":"DETRs with Collaborative Hybrid Assignments Training","created":"2022-11-22","cited_by_count":274},{"id":"2106.11037","title":"One Million Scenes for Autonomous Driving: ONCE Dataset","created":"2021-06-21","cited_by_count":218},{"id":"2303.08131","title":"A Simple Framework for Open-Vocabulary Segmentation and Detection","created":"2023-03-14","cited_by_count":198},{"id":"2104.14812","title":"SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation","created":"2021-04-30","cited_by_count":150},{"id":"2308.09244","title":"SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videos","created":"2023-08-18","cited_by_count":150},{"id":"1904.03215","title":"The Fishyscapes Benchmark: Measuring Blind Spots in Semantic Segmentation","created":"2019-04-05","cited_by_count":122},{"id":"2302.13996","title":"Aligning Bag of Regions for Open-Vocabulary Object Detection","created":"2023-02-27","cited_by_count":119},{"id":"1609.04653","title":"Lost and Found: Detecting Small Road Hazards for Self-Driving Vehicles","created":"2016-09-15","cited_by_count":117},{"id":"2203.07724","title":"CODA: A Real-World Road Corner Case Dataset for Object Detection in Autonomous Driving","created":"2022-03-15","cited_by_count":100},{"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":"2304.00788","title":"Open-Vocabulary Point-Cloud Object Detection without 3D Annotation","created":"2023-04-03","cited_by_count":81},{"id":"2303.11749","title":"Detecting Everything in the Open World: Towards Universal Object Detection","created":"2023-03-21","cited_by_count":62},{"id":"2306.05493","title":"Multi-Modal Classifiers for Open-Vocabulary Object Detection","created":"2023-06-08","cited_by_count":53},{"id":"2310.02960","title":"CoDA: Collaborative Novel Box Discovery and Cross-modal Alignment for Open-vocabulary 3D Object Detection","created":"2023-10-04","cited_by_count":52},{"id":"2404.09216","title":"DetCLIPv3: Towards Versatile Generative Open-vocabulary Object Detection","created":"2024-04-14","cited_by_count":48},{"id":"2305.18980","title":"Multi-modal Queried Object Detection in the Wild","created":"2023-05-30","cited_by_count":47},{"id":"2310.16667","title":"CoDet: Co-Occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detection","created":"2023-10-25","cited_by_count":46},{"id":"2011.11094","title":"Dense open-set recognition with synthetic outliers generated by Real NVP","created":"2020-11-22","cited_by_count":29},{"id":"2403.10191","title":"Generative Region-Language Pretraining for Open-Ended Object Detection","created":"2024-03-15","cited_by_count":29},{"id":"2203.01437","title":"MUAD: Multiple Uncertainties for Autonomous Driving, a benchmark for multiple uncertainty types and tasks","created":"2022-03-02","cited_by_count":24},{"id":"2312.11376","title":"CLIM: Contrastive Language-Image Mosaic for Region Representation","created":"2023-12-18","cited_by_count":21},{"id":"2403.13556","title":"Find n' Propagate: Open-Vocabulary 3D Object Detection in Urban Environments","created":"2024-03-20","cited_by_count":21},{"id":"2210.02074","title":"Two Video Data Sets for Tracking and Retrieval of Out of Distribution Objects","created":"2022-10-05","cited_by_count":19},{"id":"2312.14465","title":"FM-OV3D: Foundation Model-based Cross-modal Knowledge Blending for Open-Vocabulary 3D Detection","created":"2023-12-22","cited_by_count":19},{"id":"2403.19580","title":"OV-Uni3DETR: Towards Unified Open-Vocabulary 3D Object Detection via Cycle-Modality Propagation","created":"2024-03-28","cited_by_count":19},{"id":"2410.24001","title":"ImOV3D: Learning Open-Vocabulary Point Clouds 3D Object Detection from Only 2D Images","created":"2024-10-31","cited_by_count":17},{"id":"2404.02517","title":"HENet: Hybrid Encoding for End-to-end Multi-task 3D Perception from Multi-view Cameras","created":"2024-04-03","cited_by_count":16},{"id":"2410.05963","title":"Training-Free Open-Ended Object Detection and Segmentation via Attention as Prompts","created":"2024-10-08","cited_by_count":16},{"id":"2405.07865","title":"AnoVox: A Benchmark for Multimodal Anomaly Detection in Autonomous Driving","created":"2024-05-13","cited_by_count":14},{"id":"2407.05256","title":"Unlocking Textual and Visual Wisdom: Open-Vocabulary 3D Object Detection Enhanced by Comprehensive Guidance from Text and Image","created":"2024-07-07","cited_by_count":14},{"id":"2111.07971","title":"Towards Optimal Strategies for Training Self-Driving Perception Models in Simulation","created":"2021-11-15","cited_by_count":12},{"id":"2401.08687","title":"DA-BEV: Unsupervised Domain Adaptation for Bird's Eye View Perception","created":"2024-01-13","cited_by_count":5}],"next_cursor":null}