{"total":178,"rows":[{"id":"2107.08430","title":"YOLOX: Exceeding YOLO Series in 2021","created":"2021-07-18","cited_by_count":1071,"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":"2110.06864","title":"ByteTrack: Multi-Object Tracking by Associating Every Detection Box","created":"2021-10-13","cited_by_count":823,"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":"2211.09788","title":"DiffusionDet: Diffusion Model for Object Detection","created":"2022-11-17","cited_by_count":354,"area":"diffusion"},{"id":"2502.12524","title":"YOLOv12: Attention-Centric Real-Time Object Detectors","created":"2025-02-18","cited_by_count":305,"area":null},{"id":"2209.02976","title":"YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications","created":"2022-09-07","cited_by_count":275,"area":null},{"id":"2108.07755","title":"TOOD: Task-aligned One-stage Object Detection","created":"2021-08-17","cited_by_count":218,"area":null},{"id":"2212.07784","title":"RTMDet: An Empirical Study of Designing Real-Time Object Detectors","created":"2022-12-14","cited_by_count":195,"area":null},{"id":"2304.00501","title":"A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS","created":"2023-04-02","cited_by_count":151,"area":null},{"id":"2105.11111","title":"Oriented RepPoints for Aerial Object Detection","created":"2021-05-24","cited_by_count":102,"area":null},{"id":"2207.13085","title":"Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment","created":"2022-07-26","cited_by_count":98,"area":null},{"id":"2112.00322","title":"FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection","created":"2021-12-01","cited_by_count":97,"area":null},{"id":"2207.10661","title":"In Defense of Online Models for Video Instance Segmentation","created":"2022-07-21","cited_by_count":97,"area":null},{"id":"2203.16507","title":"AdaMixer: A Fast-Converging Query-Based Object Detector","created":"2022-03-30","cited_by_count":79,"area":null},{"id":"2303.12776","title":"Dense Distinct Query for End-to-End Object Detection","created":"2023-03-22","cited_by_count":77,"area":null},{"id":"2305.00054","title":"LAVA: Data Valuation without Pre-Specified Learning Algorithms","created":"2023-04-28","cited_by_count":69,"area":null},{"id":"2205.13764","title":"Fully Convolutional One-Stage 3D Object Detection on LiDAR Range Images","created":"2022-05-27","cited_by_count":56,"area":null},{"id":"2206.13996","title":"Detecting tiny objects in aerial images: A normalized Wasserstein distance and a new benchmark","created":"2022-06-28","cited_by_count":56,"area":null},{"id":"2110.13389","title":"A Normalized Gaussian Wasserstein Distance for Tiny Object Detection","created":"2021-10-26","cited_by_count":53,"area":null},{"id":"2203.16317","title":"PseCo: Pseudo Labeling and Consistency Training for Semi-Supervised Object Detection","created":"2022-03-30","cited_by_count":51,"area":null},{"id":"2208.08738","title":"RFLA: Gaussian Receptive Field based Label Assignment for Tiny Object Detection","created":"2022-08-18","cited_by_count":51,"area":null},{"id":"2212.02773","title":"DiffusionInst: Diffusion Model for Instance Segmentation","created":"2022-12-06","cited_by_count":49,"area":"diffusion"},{"id":"2201.02593","title":"Equalized Focal Loss for Dense Long-Tailed Object Detection","created":"2022-01-07","cited_by_count":46,"area":null},{"id":"2405.18525","title":"REPARO: Compositional 3D Assets Generation with Differentiable 3D Layout Alignment","created":"2024-05-28","cited_by_count":45,"area":null},{"id":"2206.06608","title":"Label Matching Semi-Supervised Object Detection","created":"2022-06-14","cited_by_count":44,"area":null},{"id":"2209.01589","title":"Consistent-Teacher: Towards Reducing Inconsistent Pseudo-targets in Semi-supervised Object Detection","created":"2022-09-04","cited_by_count":43,"area":null},{"id":"2304.08876","title":"Dynamic Coarse-to-Fine Learning for Oriented Tiny Object Detection","created":"2023-04-18","cited_by_count":43,"area":null},{"id":"2107.12654","title":"Co-Transport for Class-Incremental Learning","created":"2021-07-27","cited_by_count":38,"area":null},{"id":"2211.15444","title":"DAMO-YOLO : A Report on Real-Time Object Detection Design","created":"2022-11-23","cited_by_count":38,"area":null},{"id":"2203.09507","title":"Towards Data-Efficient Detection Transformers","created":"2022-03-17","cited_by_count":34,"area":null},{"id":"2303.07700","title":"PATS: Patch Area Transportation with Subdivision for Local Feature Matching","created":"2023-03-14","cited_by_count":33,"area":null},{"id":"2203.06965","title":"UniVIP: A Unified Framework for Self-Supervised Visual Pre-training","created":"2022-03-14","cited_by_count":31,"area":null},{"id":"2209.10365","title":"SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learning","created":"2022-09-21","cited_by_count":31,"area":null},{"id":"2302.10363","title":"Transformed Distribution Matching for Missing Value Imputation","created":"2023-02-20","cited_by_count":31,"area":null},{"id":"2203.12338","title":"Real-time Object Detection for Streaming Perception","created":"2022-03-23","cited_by_count":30,"area":null},{"id":"2407.04603","title":"AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation","created":"2024-07-05","cited_by_count":28,"area":"mllm"},{"id":"2305.05080","title":"Scalable Optimal Transport Methods in Machine Learning: A Contemporary Survey","created":"2023-05-08","cited_by_count":27,"area":null},{"id":"2307.08095","title":"Semi-DETR: Semi-Supervised Object Detection with Detection Transformers","created":"2023-07-16","cited_by_count":27,"area":null},{"id":"2203.09730","title":"A Dual Weighting Label Assignment Scheme for Object Detection","created":"2022-03-18","cited_by_count":26,"area":null},{"id":"2309.13847","title":"Tuning Multi-mode Token-level Prompt Alignment across Modalities","created":"2023-09-25","cited_by_count":26,"area":"mllm"},{"id":"2308.01779","title":"Point2Mask: Point-supervised Panoptic Segmentation via Optimal Transport","created":"2023-08-03","cited_by_count":24,"area":null},{"id":"2111.13087","title":"BoxeR: Box-Attention for 2D and 3D Transformers","created":"2021-11-25","cited_by_count":23,"area":null},{"id":"2211.06108","title":"RaLiBEV: Radar and LiDAR BEV Fusion Learning for Anchor Box Free Object Detection Systems","created":"2022-11-11","cited_by_count":23,"area":null},{"id":"2312.15715","title":"UniRef++: Segment Every Reference Object in Spatial and Temporal Spaces","created":"2023-12-25","cited_by_count":22,"area":null},{"id":"2408.01946","title":"Masked Angle-Aware Autoencoder for Remote Sensing Images","created":"2024-08-04","cited_by_count":22,"area":null},{"id":"2212.07289","title":"ConQueR: Query Contrast Voxel-DETR for 3D Object Detection","created":"2022-12-14","cited_by_count":21,"area":null},{"id":"2111.09301","title":"Learning to Align Sequential Actions in the Wild","created":"2021-11-17","cited_by_count":20,"area":null},{"id":"2303.15334","title":"ByteTrackV2: 2D and 3D Multi-Object Tracking by Associating Every Detection Box","created":"2023-03-27","cited_by_count":20,"area":null},{"id":"2204.05957","title":"Localization Distillation for Object Detection","created":"2022-04-12","cited_by_count":19,"area":"distill"},{"id":"2303.12079","title":"OmniTracker: Unifying Object Tracking by Tracking-with-Detection","created":"2023-03-21","cited_by_count":19,"area":null},{"id":"2303.14863","title":"DiffTAD: Temporal Action Detection with Proposal Denoising Diffusion","created":"2023-03-27","cited_by_count":19,"area":"diffusion"},{"id":"2304.04515","title":"SOOD: Towards Semi-Supervised Oriented Object Detection","created":"2023-04-10","cited_by_count":19,"area":null},{"id":"2208.09686","title":"YOLOV: Making Still Image Object Detectors Great at Video Object Detection","created":"2022-08-20","cited_by_count":18,"area":null},{"id":"2108.10520","title":"Improving Object Detection by Label Assignment Distillation","created":"2021-08-24","cited_by_count":17,"area":null},{"id":"2202.04256","title":"GiraffeDet: A Heavy-Neck Paradigm for Object Detection","created":"2022-02-09","cited_by_count":17,"area":null},{"id":"2204.14195","title":"Improving Transferability for Domain Adaptive Detection Transformers","created":"2022-04-29","cited_by_count":17,"area":null},{"id":"2302.07577","title":"Efficient Teacher: Semi-Supervised Object Detection for YOLOv5","created":"2023-02-15","cited_by_count":17,"area":null},{"id":"2305.08366","title":"CLRerNet: Improving Confidence of Lane Detection with LaneIoU","created":"2023-05-15","cited_by_count":17,"area":null},{"id":"2204.11402","title":"PointInst3D: Segmenting 3D Instances by Points","created":"2022-04-25","cited_by_count":16,"area":null},{"id":"2307.02402","title":"Unbalanced Optimal Transport: A Unified Framework for Object Detection","created":"2023-07-05","cited_by_count":15,"area":null},{"id":"2203.05469","title":"Prediction-Guided Distillation for Dense Object Detection","created":"2022-03-10","cited_by_count":14,"area":"distill"},{"id":"2303.09061","title":"MixTeacher: Mining Promising Labels with Mixed Scale Teacher for Semi-Supervised Object Detection","created":"2023-03-16","cited_by_count":13,"area":null},{"id":"2303.12396","title":"Rigidity-Aware Detection for 6D Object Pose Estimation","created":"2023-03-22","cited_by_count":13,"area":null},{"id":"2303.17144","title":"DAMO-StreamNet: Optimizing Streaming Perception in Autonomous Driving","created":"2023-03-30","cited_by_count":13,"area":null},{"id":"2308.13077","title":"Preserving Modality Structure Improves Multi-Modal Learning","created":"2023-08-24","cited_by_count":13,"area":null},{"id":"2207.06985","title":"ObjectBox: From Centers to Boxes for Anchor-Free Object Detection","created":"2022-07-14","cited_by_count":12,"area":null},{"id":"2407.01016","title":"SOOD++: Leveraging Unlabeled Data to Boost Oriented Object Detection","created":"2024-07-01","cited_by_count":12,"area":null},{"id":"2203.14438","title":"Optimal Correction Cost for Object Detection Evaluation","created":"2022-03-28","cited_by_count":11,"area":null},{"id":"2205.02101","title":"Dynamic Sparse R-CNN","created":"2022-05-04","cited_by_count":11,"area":null},{"id":"2403.05105","title":"Learning to Rematch Mismatched Pairs for Robust Cross-Modal Retrieval","created":"2024-03-08","cited_by_count":11,"area":null},{"id":"2406.09008","title":"LLM Reading Tea Leaves: Automatically Evaluating Topic Models with Large Language Models","created":"2024-06-13","cited_by_count":11,"area":null},{"id":"2407.05909","title":"Multi-clue Consistency Learning to Bridge Gaps Between General and Oriented Object in Semi-supervised Detection","created":"2024-07-08","cited_by_count":11,"area":null},{"id":"2202.13096","title":"Continuous Human Action Recognition for Human-Machine Interaction: A Review","created":"2022-02-26","cited_by_count":10,"area":null},{"id":"2206.13728","title":"Boosting R-CNN: Reweighting R-CNN Samples by RPN's Error for Underwater Object Detection","created":"2022-06-28","cited_by_count":10,"area":null},{"id":"2402.03785","title":"Weakly Supervised Anomaly Detection via Knowledge-Data Alignment","created":"2024-02-06","cited_by_count":10,"area":null},{"id":"2403.17410","title":"On permutation-invariant neural networks","created":"2024-03-26","cited_by_count":10,"area":null},{"id":"2411.08534","title":"Neural Topic Modeling with Large Language Models in the Loop","created":"2024-11-13","cited_by_count":10,"area":null},{"id":"2206.06427","title":"A Multi-purpose Realistic Haze Benchmark with Quantifiable Haze Levels and Ground Truth","created":"2022-06-13","cited_by_count":9,"area":null},{"id":"2309.13242","title":"UniHead: Unifying Multi-Perception for Detection Heads","created":"2023-09-23","cited_by_count":9,"area":null},{"id":"2403.04309","title":"AO-DETR: Anti-Overlapping DETR for X-Ray Prohibited Items Detection","created":"2024-03-07","cited_by_count":9,"area":null},{"id":"2412.01537","title":"HandOS: 3D Hand Reconstruction in One Stage","created":"2024-12-02","cited_by_count":9,"area":null},{"id":"2110.10239","title":"1st Place Solution for the UVO Challenge on Image-based Open-World Segmentation 2021","created":"2021-10-19","cited_by_count":8,"area":null},{"id":"2303.11567","title":"One-to-Few Label Assignment for End-to-End Dense Detection","created":"2023-03-21","cited_by_count":8,"area":null},{"id":"2304.04978","title":"StageInteractor: Query-based Object Detector with Cross-stage Interaction","created":"2023-04-11","cited_by_count":8,"area":null},{"id":"2311.04041","title":"Hilbert's projective metric for functions of bounded growth and exponential convergence of Sinkhorn's algorithm","created":"2023-11-07","cited_by_count":8,"area":null},{"id":"2506.21364","title":"CA-I2P: Channel-Adaptive Registration Network with Global Optimal Selection","created":"2025-06-26","cited_by_count":8,"area":null},{"id":"2205.09956","title":"Structured Attention Composition for Temporal Action Localization","created":"2022-05-20","cited_by_count":7,"area":null},{"id":"2207.10433","title":"StreamYOLO: Real-time Object Detection for Streaming Perception","created":"2022-07-21","cited_by_count":7,"area":null},{"id":"2303.01503","title":"FeatAug-DETR: Enriching One-to-Many Matching for DETRs with Feature Augmentation","created":"2023-03-02","cited_by_count":7,"area":null},{"id":"2407.18487","title":"SMPISD-MTPNet: Scene Semantic Prior-Assisted Infrared Ship Detection Using Multi-Task Perception Networks","created":"2024-07-26","cited_by_count":7,"area":null},{"id":"2408.01089","title":"Prototypical Partial Optimal Transport for Universal Domain Adaptation","created":"2024-08-02","cited_by_count":7,"area":null},{"id":"2408.09332","title":"YOLOv1 to YOLOv10: The fastest and most accurate real-time object detection systems","created":"2024-08-18","cited_by_count":7,"area":null},{"id":"2108.04230","title":"Workshop on Autonomous Driving at CVPR 2021: Technical Report for Streaming Perception Challenge","created":"2021-07-27","cited_by_count":6,"area":null},{"id":"2305.19181","title":"Table Detection for Visually Rich Document Images","created":"2023-05-30","cited_by_count":6,"area":null},{"id":"2308.14286","title":"Bridging Cross-task Protocol Inconsistency for Distillation in Dense Object Detection","created":"2023-08-28","cited_by_count":6,"area":"distill"},{"id":"2207.04781","title":"MT-Net Submission to the Waymo 3D Detection Leaderboard","created":"2022-07-11","cited_by_count":5,"area":null},{"id":"2208.00817","title":"DSLA: Dynamic smooth label assignment for efficient anchor-free object detection","created":"2022-08-01","cited_by_count":5,"area":null},{"id":"2209.13933","title":"DPNet: Dual-Path Network for Real-time Object Detection with Lightweight Attention","created":"2022-09-28","cited_by_count":5,"area":null},{"id":"2304.07527","title":"Align-DETR: Enhancing End-to-end Object Detection with Aligned Loss","created":"2023-04-15","cited_by_count":5,"area":null}],"next_cursor":"100"}