{"total":75,"rows":[{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228,"area":null},{"id":"2207.02696","title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","created":"2022-07-06","cited_by_count":982,"area":null},{"id":"2203.16527","title":"Exploring Plain Vision Transformer Backbones for Object Detection","created":"2022-03-30","cited_by_count":724,"area":null},{"id":"2205.08534","title":"Vision Transformer Adapter for Dense Predictions","created":"2022-05-17","cited_by_count":565,"area":null},{"id":"2211.05778","title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","created":"2022-11-10","cited_by_count":482,"area":null},{"id":"2402.13616","title":"YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information","created":"2024-02-21","cited_by_count":425,"area":null},{"id":"2303.11331","title":"EVA-02: A Visual Representation for Neon Genesis","created":"2023-03-20","cited_by_count":381,"area":null},{"id":"2205.13790","title":"BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework","created":"2022-05-27","cited_by_count":336,"area":null},{"id":"2302.00402","title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","created":"2023-02-01","cited_by_count":154,"area":null},{"id":"2207.13080","title":"DETRs with Hybrid Matching","created":"2022-07-26","cited_by_count":150,"area":null},{"id":"2304.14340","title":"SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detection","created":"2023-04-27","cited_by_count":83,"area":null},{"id":"2303.13496","title":"The effectiveness of MAE pre-pretraining for billion-scale pretraining","created":"2023-03-23","cited_by_count":68,"area":null},{"id":"2205.14951","title":"Benchmarking the Robustness of LiDAR-Camera Fusion for 3D Object Detection","created":"2022-05-30","cited_by_count":50,"area":null},{"id":"2203.13249","title":"BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-training","created":"2022-03-24","cited_by_count":33,"area":null},{"id":"2211.09807","title":"Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information","created":"2022-11-17","cited_by_count":31,"area":null},{"id":"2303.17099","title":"BEVFusion4D: Learning LiDAR-Camera Fusion Under Bird's-Eye-View via Cross-Modality Guidance and Temporal Aggregation","created":"2023-03-30","cited_by_count":31,"area":null},{"id":"2309.14516","title":"UniBEV: Multi-modal 3D Object Detection with Uniform BEV Encoders for Robustness against Missing Sensor Modalities","created":"2023-09-25","cited_by_count":29,"area":null},{"id":"2306.07890","title":"VISION Datasets: A Benchmark for Vision-based InduStrial InspectiON","created":"2023-06-13","cited_by_count":25,"area":null},{"id":"2203.12976","title":"Focus-and-Detect: A Small Object Detection Framework for Aerial Images","created":"2022-03-24","cited_by_count":19,"area":null},{"id":"2311.05613","title":"Window Attention is Bugged: How not to Interpolate Position Embeddings","created":"2023-11-09","cited_by_count":18,"area":null},{"id":"2211.13508","title":"1st Workshop on Maritime Computer Vision (MaCVi) 2023: Challenge Results","created":"2022-11-24","cited_by_count":15,"area":null},{"id":"2304.05552","title":"DynamicDet: A Unified Dynamic Architecture for Object Detection","created":"2023-04-12","cited_by_count":15,"area":null},{"id":"2309.04902","title":"Transformers in Small Object Detection: A Benchmark and Survey of State-of-the-Art","created":"2023-09-10","cited_by_count":15,"area":null},{"id":"2111.09162","title":"It's About Time: Analog Clock Reading in the Wild","created":"2021-11-17","cited_by_count":14,"area":null},{"id":"2307.11077","title":"AlignDet: Aligning Pre-training and Fine-tuning in Object Detection","created":"2023-07-20","cited_by_count":14,"area":null},{"id":"2210.17424","title":"Tree Detection and Diameter Estimation Based on Deep Learning","created":"2022-10-31","cited_by_count":12,"area":null},{"id":"2312.05019","title":"Vision-based Learning for Drones: A Survey","created":"2023-12-08","cited_by_count":11,"area":null},{"id":"2407.10125","title":"When Pedestrian Detection Meets Multi-Modal Learning: Generalist Model and Benchmark Dataset","created":"2024-07-14","cited_by_count":10,"area":null},{"id":"2408.06832","title":"FlatFusion: Delving into Details of Sparse Transformer-based Camera-LiDAR Fusion for Autonomous Driving","created":"2024-08-13","cited_by_count":9,"area":null},{"id":"2201.08625","title":"VIPriors 2: Visual Inductive Priors for Data-Efficient Deep Learning Challenges","created":"2022-01-21","cited_by_count":8,"area":null},{"id":"2312.14919","title":"Lift-Attend-Splat: Bird's-eye-view camera-lidar fusion using transformers","created":"2023-12-22","cited_by_count":8,"area":null},{"id":"2406.04330","title":"Parameter-Inverted Image Pyramid Networks","created":"2024-06-06","cited_by_count":8,"area":null},{"id":"2501.07783","title":"Parameter-Inverted Image Pyramid Networks for Visual Perception and Multimodal Understanding","created":"2025-01-14","cited_by_count":8,"area":null},{"id":"2111.04204","title":"Natural Adversarial Objects","created":"2021-11-07","cited_by_count":7,"area":null},{"id":"2203.09416","title":"Bi-directional Object-context Prioritization Learning for Saliency Ranking","created":"2022-03-17","cited_by_count":7,"area":null},{"id":"2311.14762","title":"The 2nd Workshop on Maritime Computer Vision (MaCVi) 2024","created":"2023-11-23","cited_by_count":7,"area":null},{"id":"2306.03492","title":"Industrial Anomaly Detection and Localization Using Weakly-Supervised Residual Transformers","created":"2023-06-06","cited_by_count":6,"area":null},{"id":"2502.14063","title":"PedDet: Adaptive Spectral Optimization for Multimodal Pedestrian Detection","created":"2025-02-19","cited_by_count":6,"area":null},{"id":"2111.02668","title":"LVIS Challenge Track Technical Report 1st Place Solution: Distribution Balanced and Boundary Refinement for Large Vocabulary Instance Segmentation","created":"2021-11-04","cited_by_count":5,"area":null},{"id":"2211.11282","title":"Task-Specific Data Augmentation and Inference Processing for VIPriors Instance Segmentation Challenge","created":"2022-11-21","cited_by_count":5,"area":null},{"id":"2305.19688","title":"VIPriors 3: Visual Inductive Priors for Data-Efficient Deep Learning Challenges","created":"2023-05-31","cited_by_count":4,"area":null},{"id":"2206.12912","title":"Woodscape Fisheye Object Detection for Autonomous Driving -- CVPR 2022 OmniCV Workshop Challenge","created":"2022-06-26","cited_by_count":3,"area":null},{"id":"2310.18920","title":"Improving Multi-Person Pose Tracking with A Confidence Network","created":"2023-10-29","cited_by_count":3,"area":null},{"id":"2506.12105","title":"Multiple Object Tracking in Video SAR: A Benchmark and Tracking Baseline","created":"2025-06-13","cited_by_count":3,"area":null},{"id":"2108.10103","title":"Deep neural networks approach to microbial colony detection -- a comparative analysis","created":"2021-08-23","cited_by_count":2,"area":null},{"id":"2301.07583","title":"A Survey of Advanced Computer Vision Techniques for Sports","created":"2023-01-18","cited_by_count":2,"area":null},{"id":"2304.09694","title":"CrossFusion: Interleaving Cross-modal Complementation for Noise-resistant 3D Object Detection","created":"2023-04-19","cited_by_count":2,"area":null},{"id":"2504.01128","title":"RipVIS: Rip Currents Video Instance Segmentation Benchmark for Beach Monitoring and Safety","created":"2025-04-01","cited_by_count":2,"area":null},{"id":"2206.10845","title":"Parallel Pre-trained Transformers (PPT) for Synthetic Data-based Instance Segmentation","created":"2022-06-22","cited_by_count":1,"area":null},{"id":"2208.06063","title":"ICIP 2022 Challenge on Parasitic Egg Detection and Classification in Microscopic Images: Dataset, Methods and Results","created":"2022-08-11","cited_by_count":1,"area":null},{"id":"2209.13899","title":"Strong Instance Segmentation Pipeline for MMSports Challenge","created":"2022-09-28","cited_by_count":1,"area":null},{"id":"2302.00837","title":"SHINE: Deep Learning-Based Accessible Parking Management System","created":"2023-02-02","cited_by_count":1,"area":null},{"id":"2305.04332","title":"Segmentation of the veterinary cytological images for fast neoplastic tumors diagnosis","created":"2023-05-07","cited_by_count":1,"area":null},{"id":"2308.01622","title":"ReIDTrack: Multi-Object Track and Segmentation Without Motion","created":"2023-08-03","cited_by_count":1,"area":null},{"id":"2309.03110","title":"Do We Still Need Non-Maximum Suppression? Accurate Confidence Estimates and Implicit Duplication Modeling with IoU-Aware Calibration","created":"2023-09-06","cited_by_count":1,"area":null},{"id":"2402.04064","title":"Multi-class Road Defect Detection and Segmentation using Spatial and Channel-wise Attention for Autonomous Road Repairing","created":"2024-02-06","cited_by_count":1,"area":null},{"id":"2410.21822","title":"PK-YOLO: Pretrained Knowledge Guided YOLO for Brain Tumor Detection in Multiplanar MRI Slices","created":"2024-10-29","cited_by_count":1,"area":null},{"id":"2512.20217","title":"LiteFusion: Taming 3D Object Detectors from Vision-Based to Multi-Modal with Minimal Adaptation","created":"2025-12-23","cited_by_count":1,"area":null},{"id":"2110.00242","title":"3rd Place Scheme on Instance Segmentation Track of ICCV 2021 VIPriors Challenges","created":"2021-10-01","cited_by_count":0,"area":null},{"id":"2206.13718","title":"The Third Place Solution for CVPR2022 AVA Accessibility Vision and Autonomy Challenge","created":"2022-06-28","cited_by_count":0,"area":null},{"id":"2207.00997","title":"Dynamic boxes fusion strategy in object detection","created":"2022-07-03","cited_by_count":0,"area":null},{"id":"2304.13390","title":"Group Equivariant BEV for 3D Object Detection","created":"2023-04-26","cited_by_count":0,"area":null},{"id":"2306.14116","title":"The Second-place Solution for CVPR VISION 23 Challenge Track 1 -- Data Effificient Defect Detection","created":"2023-06-25","cited_by_count":0,"area":null},{"id":"2308.04598","title":"1st Place Solution for CVPR2023 BURST Long Tail and Open World Challenges","created":"2023-08-08","cited_by_count":0,"area":null},{"id":"2308.05358","title":"Fine-grained building roof instance segmentation based on domain adapted pretraining and composite dual-backbone","created":"2023-08-10","cited_by_count":0,"area":null},{"id":"2310.17949","title":"Instance Segmentation under Occlusions via Location-aware Copy-Paste Data Augmentation","created":"2023-10-27","cited_by_count":0,"area":null},{"id":"2311.07616","title":"ReIDTracker Sea: the technical report of BoaTrack and SeaDronesSee-MOT challenge at MaCVi of WACV24","created":"2023-11-12","cited_by_count":0,"area":null},{"id":"2402.16570","title":"Searching a Lightweight Network Architecture for Thermal Infrared Pedestrian Tracking","created":"2024-02-26","cited_by_count":0,"area":null},{"id":"2403.11572","title":"Augment Before Copy-Paste: Data and Memory Efficiency-Oriented Instance Segmentation Framework for Sport-scenes","created":"2024-03-18","cited_by_count":0,"area":null},{"id":"2403.11576","title":"MISS: Memory-efficient Instance Segmentation Framework By Visual Inductive Priors Flow Propagation","created":"2024-03-18","cited_by_count":0,"area":null},{"id":"2406.18176","title":"VIPriors 4: Visual Inductive Priors for Data-Efficient Deep Learning Challenges","created":"2024-06-26","cited_by_count":0,"area":null},{"id":"2502.07076","title":"On the use of neural networks for the structural characterization of polymeric porous materials","created":"2025-01-25","cited_by_count":0,"area":null},{"id":"2506.08612","title":"Data-Efficient Challenges in Visual Inductive Priors: A Retrospective","created":"2025-06-10","cited_by_count":0,"area":null},{"id":"2512.09700","title":"LiM-YOLO: Less is More with Pyramid Level Shift for Ship Detection in Optical Remote Sensing","created":"2025-12-10","cited_by_count":0,"area":null},{"id":"2605.28261","title":"MORI-Seg: Learning Morphological Geometry for Instance Segmentation without Instance Annotations","created":"2026-05-27","cited_by_count":0,"area":null}],"next_cursor":null}