{"total":1630,"rows":[{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139,"area":null},{"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,"area":null},{"id":"2207.05608","title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","created":"2022-07-12","cited_by_count":1081,"area":"wm"},{"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":"2301.07093","title":"GLIGEN: Open-Set Grounded Text-to-Image Generation","created":"2023-01-17","cited_by_count":781,"area":"diffusion"},{"id":"2201.02605","title":"Detecting Twenty-thousand Classes using Image-level Supervision","created":"2022-01-07","cited_by_count":614,"area":null},{"id":"2201.12329","title":"DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR","created":"2022-01-28","cited_by_count":573,"area":null},{"id":"2304.08069","title":"DETRs Beat YOLOs on Real-time Object Detection","created":"2023-04-17","cited_by_count":533,"area":null},{"id":"2405.14458","title":"YOLOv10: Real-Time End-to-End Object Detection","created":"2024-05-23","cited_by_count":515,"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":"2410.17725","title":"YOLOv11: An Overview of the Key Architectural Enhancements","created":"2024-10-23","cited_by_count":425,"area":null},{"id":"2108.06152","title":"Conditional DETR for Fast Training Convergence","created":"2021-08-13","cited_by_count":424,"area":null},{"id":"2206.14651","title":"BoT-SORT: Robust Associations Multi-Pedestrian Tracking","created":"2022-06-29","cited_by_count":320,"area":null},{"id":"2502.12524","title":"YOLOv12: Attention-Centric Real-Time Object Detectors","created":"2025-02-18","cited_by_count":305,"area":null},{"id":"2307.10816","title":"BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion","created":"2023-07-20","cited_by_count":282,"area":"diffusion"},{"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":"2303.17189","title":"LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generation","created":"2023-03-30","cited_by_count":259,"area":"diffusion"},{"id":"2210.07558","title":"DyLoRA: Parameter Efficient Tuning of Pre-trained Models using Dynamic Search-Free Low-Rank Adaptation","created":"2022-10-14","cited_by_count":233,"area":null},{"id":"2108.10831","title":"LLVIP: A Visible-infrared Paired Dataset for Low-light Vision","created":"2021-08-24","cited_by_count":231,"area":null},{"id":"2211.14461","title":"CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion","created":"2022-11-26","cited_by_count":223,"area":null},{"id":"2305.11147","title":"UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild","created":"2023-05-18","cited_by_count":200,"area":"diffusion"},{"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":"2303.11681","title":"DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models","created":"2023-03-21","cited_by_count":162,"area":"diffusion"},{"id":"2109.14545","title":"Activation Functions in Deep Learning: A Comprehensive Survey and Benchmark","created":"2021-09-29","cited_by_count":155,"area":null},{"id":"2303.06840","title":"DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion","created":"2023-03-13","cited_by_count":153,"area":"diffusion"},{"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":"2102.12145","title":"GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimator","created":"2021-02-24","cited_by_count":148,"area":null},{"id":"2103.07461","title":"Probabilistic two-stage detection","created":"2021-03-12","cited_by_count":130,"area":null},{"id":"2207.14096","title":"Towards Large-Scale Small Object Detection: Survey and Benchmarks","created":"2022-07-28","cited_by_count":122,"area":null},{"id":"2103.09460","title":"You Only Look One-level Feature","created":"2021-03-17","cited_by_count":116,"area":null},{"id":"2103.11402","title":"Instant-Teaching: An End-to-End Semi-Supervised Object Detection Framework","created":"2021-03-21","cited_by_count":113,"area":null},{"id":"2405.12971","title":"BiomedParse: a biomedical foundation model for image parsing of everything everywhere all at once","created":"2024-05-21","cited_by_count":111,"area":null},{"id":"2103.14962","title":"Panoptic-PolarNet: Proposal-free LiDAR Point Cloud Panoptic Segmentation","created":"2021-03-27","cited_by_count":107,"area":null},{"id":"2108.09017","title":"DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection","created":"2021-08-20","cited_by_count":106,"area":null},{"id":"2202.06934","title":"Slicing Aided Hyper Inference and Fine-tuning for Small Object Detection","created":"2022-02-14","cited_by_count":105,"area":null},{"id":"2305.11443","title":"Equivariant Multi-Modality Image Fusion","created":"2023-05-19","cited_by_count":99,"area":null},{"id":"2104.11892","title":"A Survey of Modern Deep Learning based Object Detection Models","created":"2021-04-24","cited_by_count":98,"area":null},{"id":"2205.01491","title":"A Comprehensive Survey of Image Augmentation Techniques for Deep Learning","created":"2022-05-03","cited_by_count":97,"area":null},{"id":"2106.05786","title":"CAT: Cross Attention in Vision Transformer","created":"2021-06-10","cited_by_count":92,"area":null},{"id":"2407.17140","title":"RT-DETRv2: Improved Baseline with Bag-of-Freebies for Real-Time Detection Transformer","created":"2024-07-24","cited_by_count":91,"area":null},{"id":"2303.09105","title":"Rethinking Model Ensemble in Transfer-based Adversarial Attacks","created":"2023-03-16","cited_by_count":89,"area":null},{"id":"2111.00273","title":"Cross-Modality Fusion Transformer for Multispectral Object Detection","created":"2021-10-30","cited_by_count":86,"area":null},{"id":"2112.08088","title":"Image-Adaptive YOLO for Object Detection in Adverse Weather Conditions","created":"2021-12-15","cited_by_count":85,"area":null},{"id":"2108.11539","title":"TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios","created":"2021-08-26","cited_by_count":83,"area":null},{"id":"2108.11250","title":"YOLOP: You Only Look Once for Panoptic Driving Perception","created":"2021-08-25","cited_by_count":82,"area":"wm"},{"id":"2301.00265","title":"Source-Free Unsupervised Domain Adaptation: A Survey","created":"2022-12-31","cited_by_count":80,"area":null},{"id":"2509.25164","title":"YOLO26: Key Architectural Enhancements and Performance Benchmarking for Real-Time Object Detection","created":"2025-09-29","cited_by_count":79,"area":null},{"id":"2307.11411","title":"Deep Directly-Trained Spiking Neural Networks for Object Detection","created":"2023-07-21","cited_by_count":77,"area":null},{"id":"2308.07504","title":"ICAFusion: Iterative Cross-Attention Guided Feature Fusion for Multispectral Object Detection","created":"2023-08-15","cited_by_count":76,"area":null},{"id":"2203.16250","title":"PP-YOLOE: An evolved version of YOLO","created":"2022-03-30","cited_by_count":75,"area":null},{"id":"2208.13753","title":"Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesis","created":"2022-08-29","cited_by_count":75,"area":"diffusion"},{"id":"2201.12558","title":"The KFIoU Loss for Rotated Object Detection","created":"2022-01-29","cited_by_count":73,"area":null},{"id":"2103.13027","title":"AutoMix: Unveiling the Power of Mixup for Stronger Classifiers","created":"2021-03-24","cited_by_count":69,"area":null},{"id":"2203.10593","title":"Open-Vocabulary One-Stage Detection with Hierarchical Visual-Language Knowledge Distillation","created":"2022-03-20","cited_by_count":68,"area":"distill"},{"id":"2204.06806","title":"YOLO-Pose: Enhancing YOLO for Multi Person Pose Estimation Using Object Keypoint Similarity Loss","created":"2022-04-14","cited_by_count":68,"area":null},{"id":"2412.04234","title":"DEIM: DETR with Improved Matching for Fast Convergence","created":"2024-12-05","cited_by_count":68,"area":null},{"id":"2403.07392","title":"ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictions","created":"2024-03-12","cited_by_count":66,"area":null},{"id":"2302.08908","title":"LayoutDiffuse: Adapting Foundational Diffusion Models for Layout-to-Image Generation","created":"2023-02-16","cited_by_count":65,"area":"diffusion"},{"id":"2202.11912","title":"A Rigorous Study of Integrated Gradients Method and Extensions to Internal Neuron Attributions","created":"2022-02-24","cited_by_count":64,"area":null},{"id":"2303.11749","title":"Detecting Everything in the Open World: Towards Universal Object Detection","created":"2023-03-21","cited_by_count":62,"area":null},{"id":"2106.15277","title":"EPMF: Efficient Perception-aware Multi-sensor Fusion for 3D Semantic Segmentation","created":"2021-06-21","cited_by_count":59,"area":null},{"id":"2211.09773","title":"T-SEA: Transfer-based Self-Ensemble Attack on Object Detection","created":"2022-11-16","cited_by_count":59,"area":null},{"id":"2301.05586","title":"YOLOv6 v3.0: A Full-Scale Reloading","created":"2023-01-13","cited_by_count":58,"area":null},{"id":"2304.10410","title":"Radar-Camera Fusion for Object Detection and Semantic Segmentation in Autonomous Driving: A Comprehensive Review","created":"2023-04-20","cited_by_count":58,"area":null},{"id":"2506.17733","title":"YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception","created":"2025-06-21","cited_by_count":58,"area":null},{"id":"2108.13342","title":"DNNFusion: Accelerating Deep Neural Networks Execution with Advanced Operator Fusion","created":"2021-08-30","cited_by_count":57,"area":null},{"id":"2102.12252","title":"Localization Distillation for Dense Object Detection","created":"2021-02-24","cited_by_count":55,"area":"distill"},{"id":"2203.13349","title":"Occluded Human Mesh Recovery","created":"2022-03-24","cited_by_count":54,"area":null},{"id":"2203.16421","title":"OPD: Single-view 3D Openable Part Detection","created":"2022-03-30","cited_by_count":54,"area":null},{"id":"2204.08817","title":"An Efficient Domain-Incremental Learning Approach to Drive in All Weather Conditions","created":"2022-04-19","cited_by_count":54,"area":null},{"id":"2305.04925","title":"PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point Clouds","created":"2023-05-08","cited_by_count":54,"area":null},{"id":"2105.00363","title":"RADDet: Range-Azimuth-Doppler based Radar Object Detection for Dynamic Road Users","created":"2021-05-02","cited_by_count":52,"area":null},{"id":"2306.11369","title":"CrossKD: Cross-Head Knowledge Distillation for Object Detection","created":"2023-06-20","cited_by_count":52,"area":"distill"},{"id":"2203.04708","title":"A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection","created":"2022-03-09","cited_by_count":51,"area":null},{"id":"2203.09831","title":"DTA: Physical Camouflage Attacks using Differentiable Transformation Network","created":"2022-03-18","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":"2309.11331","title":"Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanism","created":"2023-09-20","cited_by_count":51,"area":null},{"id":"2105.01294","title":"Hallucination Improves Few-Shot Object Detection","created":"2021-05-04","cited_by_count":50,"area":null},{"id":"2212.14474","title":"Learning 3D Human Pose Estimation from Dozens of Datasets using a Geometry-Aware Autoencoder to Bridge Between Skeleton Formats","created":"2022-12-29","cited_by_count":50,"area":null},{"id":"2303.14042","title":"Class-Incremental Exemplar Compression for Class-Incremental Learning","created":"2023-03-24","cited_by_count":50,"area":null},{"id":"2205.12740","title":"SIoU Loss: More Powerful Learning for Bounding Box Regression","created":"2022-05-25","cited_by_count":49,"area":null},{"id":"2207.10758","title":"DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection","created":"2022-07-21","cited_by_count":48,"area":null},{"id":"2306.05238","title":"SparseTrack: Multi-Object Tracking by Performing Scene Decomposition based on Pseudo-Depth","created":"2023-06-08","cited_by_count":48,"area":null},{"id":"2209.13351","title":"SuperYOLO: Super Resolution Assisted Object Detection in Multimodal Remote Sensing Imagery","created":"2022-09-27","cited_by_count":47,"area":null},{"id":"2202.11983","title":"GIAOTracker: A comprehensive framework for MCMOT with global information and optimizing strategies in VisDrone 2021","created":"2022-02-24","cited_by_count":46,"area":null},{"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,"area":null},{"id":"2408.15857","title":"What is YOLOv8: An In-Depth Exploration of the Internal Features of the Next-Generation Object Detector","created":"2024-08-28","cited_by_count":45,"area":null},{"id":"2105.12931","title":"YOLO5Face: Why Reinventing a Face Detector","created":"2021-05-27","cited_by_count":44,"area":null},{"id":"2206.04656","title":"Simple Cues Lead to a Strong Multi-Object Tracker","created":"2022-06-09","cited_by_count":44,"area":null},{"id":"2112.05749","title":"Label, Verify, Correct: A Simple Few Shot Object Detection Method","created":"2021-12-10","cited_by_count":43,"area":null},{"id":"2208.11036","title":"CitySim: A Drone-Based Vehicle Trajectory Dataset for Safety Oriented Research and Digital Twins","created":"2022-08-23","cited_by_count":43,"area":null},{"id":"2303.08348","title":"Active Teacher for Semi-Supervised Object Detection","created":"2023-03-15","cited_by_count":43,"area":"distill"},{"id":"2212.12995","title":"Simultaneously Optimizing Perturbations and Positions for Black-box Adversarial Patch Attacks","created":"2022-12-26","cited_by_count":42,"area":null},{"id":"2305.14298","title":"MOTRv3: Release-Fetch Supervision for End-to-End Multi-Object Tracking","created":"2023-05-23","cited_by_count":42,"area":null},{"id":"2303.14488","title":"Adaptive Sparse Convolutional Networks with Global Context Enhancement for Faster Object Detection on Drone Images","created":"2023-03-25","cited_by_count":41,"area":null},{"id":"2410.14324","title":"HiCo: Hierarchical Controllable Diffusion Model for Layout-to-image Generation","created":"2024-10-18","cited_by_count":41,"area":"diffusion"},{"id":"2305.11618","title":"DAP: A Dynamic Adversarial Patch for Evading Person Detectors","created":"2023-05-19","cited_by_count":40,"area":null},{"id":"2308.09905","title":"DiffusionTrack: Diffusion Model For Multi-Object Tracking","created":"2023-08-19","cited_by_count":40,"area":"diffusion"}],"next_cursor":"100"}