{"total":195,"rows":[{"id":"2108.06152","title":"Conditional DETR for Fast Training Convergence","created":"2021-08-13","cited_by_count":424,"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":"2108.06417","title":"Is Pseudo-Lidar needed for Monocular 3D Object detection?","created":"2021-08-13","cited_by_count":249,"area":null},{"id":"2103.14259","title":"OTA: Optimal Transport Assignment for Object Detection","created":"2021-03-26","cited_by_count":178,"area":null},{"id":"2104.06728","title":"Adversarial Sticker: A Stealthy Attack Method in the Physical World","created":"2021-04-14","cited_by_count":93,"area":null},{"id":"2104.14545","title":"LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search","created":"2021-04-29","cited_by_count":82,"area":null},{"id":"2203.10350","title":"CLRNet: Cross Layer Refinement Network for Lane Detection","created":"2022-03-19","cited_by_count":82,"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":"2201.12558","title":"The KFIoU Loss for Rotated Object Detection","created":"2022-01-29","cited_by_count":73,"area":null},{"id":"2303.10404","title":"MotionTrack: Learning Robust Short-term and Long-term Motions for Multi-Object Tracking","created":"2023-03-18","cited_by_count":64,"area":null},{"id":"2105.11595","title":"SiamMOT: Siamese Multi-Object Tracking","created":"2021-05-25","cited_by_count":62,"area":null},{"id":"2206.15436","title":"Category-Level 6D Object Pose Estimation in the Wild: A Semi-Supervised Learning Approach and A New Dataset","created":"2022-06-30","cited_by_count":59,"area":null},{"id":"2101.08158","title":"Focal and Efficient IOU Loss for Accurate Bounding Box Regression","created":"2021-01-20","cited_by_count":57,"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":"2110.13389","title":"A Normalized Gaussian Wasserstein Distance for Tiny Object Detection","created":"2021-10-26","cited_by_count":53,"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":"2108.11179","title":"Recall@k Surrogate Loss with Large Batches and Similarity Mixup","created":"2021-08-25","cited_by_count":49,"area":null},{"id":"2404.16622","title":"DAVE -- A Detect-and-Verify Paradigm for Low-Shot Counting","created":"2024-04-25","cited_by_count":49,"area":null},{"id":"2112.09686","title":"Efficient Visual Tracking with Exemplar Transformers","created":"2021-12-17","cited_by_count":48,"area":null},{"id":"2108.06685","title":"Vector-Decomposed Disentanglement for Domain-Invariant Object Detection","created":"2021-08-15","cited_by_count":47,"area":null},{"id":"2112.02838","title":"Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlook","created":"2021-12-06","cited_by_count":46,"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":"2303.15710","title":"Explicit Attention-Enhanced Fusion for RGB-Thermal Perception Tasks","created":"2023-03-28","cited_by_count":41,"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":"2205.03776","title":"SparseTT: Visual Tracking with Sparse Transformers","created":"2022-05-08","cited_by_count":36,"area":null},{"id":"2208.04094","title":"Towards Semantic Communications: Deep Learning-Based Image Semantic Coding","created":"2022-08-08","cited_by_count":36,"area":null},{"id":"2210.06742","title":"H2RBox: Horizontal Box Annotation is All You Need for Oriented Object Detection","created":"2022-10-13","cited_by_count":36,"area":null},{"id":"2104.01070","title":"MOST: A Multi-Oriented Scene Text Detector with Localization Refinement","created":"2021-04-02","cited_by_count":33,"area":null},{"id":"2106.15947","title":"SOLO: A Simple Framework for Instance Segmentation","created":"2021-06-30","cited_by_count":32,"area":null},{"id":"2403.18551","title":"Attention Calibration for Disentangled Text-to-Image Personalization","created":"2024-03-27","cited_by_count":31,"area":null},{"id":"2301.10051","title":"Wise-IoU: Bounding Box Regression Loss with Dynamic Focusing Mechanism","created":"2023-01-24","cited_by_count":30,"area":null},{"id":"2203.16897","title":"Multi-Granularity Alignment Domain Adaptation for Object Detection","created":"2022-03-31","cited_by_count":29,"area":null},{"id":"2304.04403","title":"H2RBox-v2: Incorporating Symmetry for Boosting Horizontal Box Supervised Oriented Object Detection","created":"2023-04-10","cited_by_count":28,"area":null},{"id":"2105.02184","title":"PolarMask++: Enhanced Polar Representation for Single-Shot Instance Segmentation and Beyond","created":"2021-05-05","cited_by_count":27,"area":null},{"id":"2308.09534","title":"Small Object Detection via Coarse-to-fine Proposal Generation and Imitation Learning","created":"2023-08-18","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":"2110.00249","title":"Synergizing between Self-Training and Adversarial Learning for Domain Adaptive Object Detection","created":"2021-10-01","cited_by_count":24,"area":null},{"id":"2303.08345","title":"Scanning Only Once: An End-to-end Framework for Fast Temporal Grounding in Long Videos","created":"2023-03-15","cited_by_count":23,"area":null},{"id":"2108.12711","title":"Learning to Track Objects from Unlabeled Videos","created":"2021-08-28","cited_by_count":21,"area":null},{"id":"2102.04700","title":"Loss Function Discovery for Object Detection via Convergence-Simulation Driven Search","created":"2021-02-09","cited_by_count":20,"area":null},{"id":"2202.05126","title":"Deep Learning for Computational Cytology: A Survey","created":"2022-02-10","cited_by_count":20,"area":null},{"id":"2205.11796","title":"G-Rep: Gaussian Representation for Arbitrary-Oriented Object Detection","created":"2022-05-24","cited_by_count":20,"area":null},{"id":"2103.14026","title":"AutoLoss-Zero: Searching Loss Functions from Scratch for Generic Tasks","created":"2021-03-25","cited_by_count":19,"area":null},{"id":"2106.06072","title":"Gaussian Bounding Boxes and Probabilistic Intersection-over-Union for Object Detection","created":"2021-06-10","cited_by_count":18,"area":null},{"id":"2110.13675","title":"Alpha-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression","created":"2021-10-26","cited_by_count":18,"area":null},{"id":"2206.06506","title":"Spiking Neural Networks for Frame-based and Event-based Single Object Localization","created":"2022-06-13","cited_by_count":18,"area":null},{"id":"2203.06410","title":"Kernel Proposal Network for Arbitrary Shape Text Detection","created":"2022-03-12","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":"2401.16741","title":"MESA: Matching Everything by Segmenting Anything","created":"2024-01-30","cited_by_count":16,"area":null},{"id":"2505.07375","title":"Boosting Global-Local Feature Matching via Anomaly Synthesis for Multi-Class Point Cloud Anomaly Detection","created":"2025-05-12","cited_by_count":16,"area":null},{"id":"2208.02019","title":"YOLO-FaceV2: A Scale and Occlusion Aware Face Detector","created":"2022-08-03","cited_by_count":15,"area":null},{"id":"2305.10061","title":"Rethinking Boundary Discontinuity Problem for Oriented Object Detection","created":"2023-05-17","cited_by_count":15,"area":null},{"id":"2207.06854","title":"AIParsing: Anchor-free Instance-level Human Parsing","created":"2022-07-14","cited_by_count":14,"area":null},{"id":"2405.09782","title":"Size-invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection","created":"2024-05-16","cited_by_count":14,"area":null},{"id":"2202.09745","title":"RDP-Net: Region Detail Preserving Network for Change Detection","created":"2022-02-20","cited_by_count":13,"area":null},{"id":"2104.05215","title":"SCPM-Net: An Anchor-free 3D Lung Nodule Detection Network using Sphere Representation and Center Points Matching","created":"2021-04-12","cited_by_count":12,"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":"2208.00946","title":"Motion-aware Memory Network for Fast Video Salient Object Detection","created":"2022-08-01","cited_by_count":12,"area":null},{"id":"2208.10895","title":"A Comprehensive Study of Real-Time Object Detection Networks Across Multiple Domains: A Survey","created":"2022-08-23","cited_by_count":12,"area":null},{"id":"2211.03850","title":"Polite Teacher: Semi-Supervised Instance Segmentation with Mutual Learning and Pseudo-Label Thresholding","created":"2022-11-07","cited_by_count":12,"area":null},{"id":"2108.10809","title":"Reconcile Prediction Consistency for Balanced Object Detection","created":"2021-08-24","cited_by_count":11,"area":null},{"id":"2205.04281","title":"Siamese Object Tracking for Unmanned Aerial Vehicle: A Review and Comprehensive Analysis","created":"2022-05-09","cited_by_count":11,"area":null},{"id":"2404.04799","title":"Few-Shot Object Detection: Research Advances and Challenges","created":"2024-04-07","cited_by_count":11,"area":null},{"id":"2103.14983","title":"Going Deeper Into Face Detection: A Survey","created":"2021-03-27","cited_by_count":10,"area":null},{"id":"2104.12389","title":"Variational Pedestrian Detection","created":"2021-04-26","cited_by_count":10,"area":null},{"id":"2204.02791","title":"Implicit Motion-Compensated Network for Unsupervised Video Object Segmentation","created":"2022-04-06","cited_by_count":10,"area":null},{"id":"2303.07582","title":"Calibrated Teacher for Sparsely Annotated Object Detection","created":"2023-03-14","cited_by_count":10,"area":null},{"id":"2307.07662","title":"MPDIoU: A Loss for Efficient and Accurate Bounding Box Regression","created":"2023-07-14","cited_by_count":10,"area":null},{"id":"2507.01182","title":"Rapid Salient Object Detection with Difference Convolutional Neural Networks","created":"2025-07-01","cited_by_count":10,"area":null},{"id":"2105.02480","title":"A Simple and Strong Baseline for Universal Targeted Attacks on Siamese Visual Tracking","created":"2021-05-06","cited_by_count":9,"area":null},{"id":"2105.11237","title":"SiamRCR: Reciprocal Classification and Regression for Visual Object Tracking","created":"2021-05-24","cited_by_count":9,"area":null},{"id":"2108.04644","title":"FoodLogoDet-1500: A Dataset for Large-Scale Food Logo Detection via Multi-Scale Feature Decoupling Network","created":"2021-08-10","cited_by_count":9,"area":null},{"id":"2201.02302","title":"Extending One-Stage Detection with Open-World Proposals","created":"2022-01-07","cited_by_count":9,"area":null},{"id":"2207.05200","title":"Real-Time And Robust 3D Object Detection with Roadside LiDARs","created":"2022-07-11","cited_by_count":9,"area":null},{"id":"2311.02877","title":"Inner-IoU: More Effective Intersection over Union Loss with Auxiliary Bounding Box","created":"2023-11-06","cited_by_count":9,"area":null},{"id":"2401.10525","title":"Focaler-IoU: More Focused Intersection over Union Loss","created":"2024-01-19","cited_by_count":9,"area":null},{"id":"2503.12840","title":"Dynamic Derivation and Elimination: Audio Visual Segmentation with Enhanced Audio Semantics","created":"2025-03-17","cited_by_count":9,"area":null},{"id":"2104.04899","title":"Location-Sensitive Visual Recognition with Cross-IOU Loss","created":"2021-04-11","cited_by_count":8,"area":null},{"id":"2112.06701","title":"Anchor Retouching via Model Interaction for Robust Object Detection in Aerial Images","created":"2021-12-13","cited_by_count":8,"area":null},{"id":"2503.12847","title":"Robust Audio-Visual Segmentation via Audio-Guided Visual Convergent Alignment","created":"2025-03-17","cited_by_count":8,"area":null},{"id":"2202.13372","title":"Weakly Supervised Learning for cell recognition in immunohistochemical cytoplasm staining images","created":"2022-02-27","cited_by_count":7,"area":null},{"id":"2206.02424","title":"Slim-neck by GSConv: A lightweight-design for real-time detector architectures","created":"2022-06-06","cited_by_count":7,"area":null},{"id":"2312.16023","title":"DocMSU: A Comprehensive Benchmark for Document-level Multimodal Sarcasm Understanding","created":"2023-12-26","cited_by_count":7,"area":null},{"id":"2406.08837","title":"Research on Deep Learning Model of Feature Extraction Based on Convolutional Neural Network","created":"2024-06-13","cited_by_count":7,"area":null},{"id":"2103.07017","title":"CRFace: Confidence Ranker for Model-Agnostic Face Detection Refinement","created":"2021-03-12","cited_by_count":6,"area":null},{"id":"2206.05708","title":"Narrowing the Gap: Improved Detector Training with Noisy Location Annotations","created":"2022-06-12","cited_by_count":6,"area":null},{"id":"2301.00371","title":"Robust Domain Adaptive Object Detection with Unified Multi-Granularity Alignment","created":"2023-01-01","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":"2311.04815","title":"Domain Adaptive Object Detection via Balancing Between Self-Training and Adversarial Learning","created":"2023-11-08","cited_by_count":6,"area":null},{"id":"2502.09471","title":"Wholly-WOOD: Wholly Leveraging Diversified-quality Labels for Weakly-supervised Oriented Object Detection","created":"2025-02-13","cited_by_count":6,"area":null},{"id":"2107.02827","title":"Plot2Spectra: an Automatic Spectra Extraction Tool","created":"2021-07-06","cited_by_count":5,"area":null},{"id":"2212.09408","title":"Universal Object Detection with Large Vision Model","created":"2022-12-19","cited_by_count":5,"area":null},{"id":"2305.20055","title":"Cross-Domain Car Detection Model with Integrated Convolutional Block Attention Mechanism","created":"2023-05-31","cited_by_count":5,"area":null},{"id":"2508.02660","title":"PMGS: Reconstruction of Projectile Motion Across Large Spatiotemporal Spans via 3D Gaussian Splatting","created":"2025-08-04","cited_by_count":5,"area":null},{"id":"2103.11017","title":"TDIOT: Target-driven Inference for Deep Video Object Tracking","created":"2021-03-19","cited_by_count":4,"area":null},{"id":"2104.00462","title":"SCALoss: Side and Corner Aligned Loss for Bounding Box Regression","created":"2021-04-01","cited_by_count":4,"area":null},{"id":"2109.06148","title":"DAFNe: A One-Stage Anchor-Free Approach for Oriented Object Detection","created":"2021-09-13","cited_by_count":4,"area":null},{"id":"2112.01793","title":"A Systematic IoU-Related Method: Beyond Simplified Regression for Better Localization","created":"2021-12-03","cited_by_count":4,"area":null},{"id":"2203.11432","title":"Gated Domain-Invariant Feature Disentanglement for Domain Generalizable Object Detection","created":"2022-03-22","cited_by_count":4,"area":null},{"id":"2309.08196","title":"ECEA: Extensible Co-Existing Attention for Few-Shot Object Detection","created":"2023-09-15","cited_by_count":4,"area":null}],"next_cursor":"100"}