{"total":2494,"rows":[{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556,"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":"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":"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":"2401.17270","title":"YOLO-World: Real-Time Open-Vocabulary Object Detection","created":"2024-01-30","cited_by_count":503,"area":null},{"id":"2203.01305","title":"DN-DETR: Accelerate DETR Training by Introducing Query DeNoising","created":"2022-03-02","cited_by_count":488,"area":null},{"id":"2204.12484","title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","created":"2022-04-26","cited_by_count":456,"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":"2105.03247","title":"MOTR: End-to-End Multiple-Object Tracking with Transformer","created":"2021-05-07","cited_by_count":381,"area":null},{"id":"2112.02244","title":"LAVT: Language-Aware Vision Transformer for Referring Image Segmentation","created":"2021-12-04","cited_by_count":348,"area":null},{"id":"2204.09817","title":"Making the Most of Text Semantics to Improve Biomedical Vision--Language Processing","created":"2022-04-21","cited_by_count":339,"area":null},{"id":"2206.14651","title":"BoT-SORT: Robust Associations Multi-Pedestrian Tracking","created":"2022-06-29","cited_by_count":320,"area":null},{"id":"2102.09480","title":"Unbiased Teacher for Semi-Supervised Object Detection","created":"2021-02-18","cited_by_count":306,"area":null},{"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":"2104.08541","title":"TransVG: End-to-End Visual Grounding with Transformers","created":"2021-04-17","cited_by_count":271,"area":null},{"id":"2208.00571","title":"CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation","created":"2022-08-01","cited_by_count":238,"area":null},{"id":"2306.16940","title":"BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion","created":"2023-06-29","cited_by_count":236,"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":"2303.06705","title":"Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement","created":"2023-03-12","cited_by_count":231,"area":null},{"id":"2202.13514","title":"StrongSORT: Make DeepSORT Great Again","created":"2022-02-28","cited_by_count":213,"area":null},{"id":"2211.03375","title":"AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time","created":"2022-11-07","cited_by_count":200,"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":"2103.14259","title":"OTA: Optimal Transport Assignment for Object Detection","created":"2021-03-26","cited_by_count":178,"area":null},{"id":"2303.07399","title":"RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose","created":"2023-03-13","cited_by_count":175,"area":null},{"id":"2103.12978","title":"RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentation","created":"2021-03-24","cited_by_count":173,"area":null},{"id":"2106.00666","title":"You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection","created":"2021-06-01","cited_by_count":170,"area":null},{"id":"2102.04530","title":"(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Network","created":"2021-02-08","cited_by_count":164,"area":null},{"id":"2202.05924","title":"Compute Trends Across Three Eras of Machine Learning","created":"2022-02-11","cited_by_count":163,"area":null},{"id":"2210.06044","title":"Multi-Granularity Cross-modal Alignment for Generalized Medical Visual Representation Learning","created":"2022-10-12","cited_by_count":159,"area":null},{"id":"2212.05598","title":"Recurrent Vision Transformers for Object Detection with Event Cameras","created":"2022-12-11","cited_by_count":159,"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":"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":"2302.07387","title":"PolyFormer: Referring Image Segmentation as Sequential Polygon Generation","created":"2023-02-14","cited_by_count":148,"area":null},{"id":"2403.09227","title":"BEHAVIOR-1K: A Human-Centered, Embodied AI Benchmark with 1,000 Everyday Activities and Realistic Simulation","created":"2024-03-14","cited_by_count":148,"area":null},{"id":"2206.08367","title":"SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation","created":"2022-06-16","cited_by_count":146,"area":null},{"id":"2103.05569","title":"FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagery","created":"2021-03-09","cited_by_count":143,"area":null},{"id":"2106.03089","title":"Referring Transformer: A One-step Approach to Multi-task Visual Grounding","created":"2021-06-06","cited_by_count":143,"area":null},{"id":"2203.16265","title":"SeqTR: A Simple yet Universal Network for Visual Grounding","created":"2022-03-30","cited_by_count":139,"area":null},{"id":"2106.00487","title":"Dense Nested Attention Network for Infrared Small Target Detection","created":"2021-06-01","cited_by_count":135,"area":null},{"id":"2112.00463","title":"The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalization","created":"2021-12-01","cited_by_count":131,"area":null},{"id":"2103.07461","title":"Probabilistic two-stage detection","created":"2021-03-12","cited_by_count":130,"area":null},{"id":"2104.01318","title":"Efficient DETR: Improving End-to-End Object Detector with Dense Prior","created":"2021-04-03","cited_by_count":128,"area":null},{"id":"2103.16746","title":"Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark","created":"2021-03-31","cited_by_count":126,"area":null},{"id":"2409.12259","title":"WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild","created":"2024-09-18","cited_by_count":124,"area":null},{"id":"2210.14457","title":"Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalization","created":"2022-10-26","cited_by_count":123,"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":"2103.07054","title":"FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanism","created":"2021-03-12","cited_by_count":121,"area":null},{"id":"2210.16774","title":"Dataset Distillation via Factorization","created":"2022-10-30","cited_by_count":115,"area":null},{"id":"2203.10981","title":"MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer","created":"2022-03-21","cited_by_count":109,"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":"2203.01923","title":"Recovering 3D Human Mesh from Monocular Images: A Survey","created":"2022-03-03","cited_by_count":103,"area":null},{"id":"2312.08782","title":"Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis","created":"2023-12-14","cited_by_count":103,"area":null},{"id":"2105.11111","title":"Oriented RepPoints for Aerial Object Detection","created":"2021-05-24","cited_by_count":102,"area":null},{"id":"2103.16284","title":"Locate then Segment: A Strong Pipeline for Referring Image Segmentation","created":"2021-03-30","cited_by_count":98,"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":"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":"2203.03373","title":"Adversarial Texture for Fooling Person Detectors in the Physical World","created":"2022-03-07","cited_by_count":96,"area":null},{"id":"2203.07918","title":"GPV-Pose: Category-level Object Pose Estimation via Geometry-guided Point-wise Voting","created":"2022-03-15","cited_by_count":94,"area":null},{"id":"2305.09972","title":"Real-Time Flying Object Detection with YOLOv8","created":"2023-05-17","cited_by_count":94,"area":null},{"id":"2111.08644","title":"UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detection","created":"2021-11-16","cited_by_count":93,"area":null},{"id":"2207.07078","title":"Towards Grand Unification of Object Tracking","created":"2022-07-14","cited_by_count":93,"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":"2110.15352","title":"MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning","created":"2021-10-28","cited_by_count":89,"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":"2108.08367","title":"SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimation","created":"2021-08-18","cited_by_count":88,"area":null},{"id":"2401.08399","title":"TACO: Benchmarking Generalizable Bimanual Tool-ACtion-Object Understanding","created":"2024-01-16","cited_by_count":88,"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":"2203.13310","title":"MonoDETR: Depth-guided Transformer for Monocular 3D Object Detection","created":"2022-03-24","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":"2103.08700","title":"Deep Learning for Chest X-ray Analysis: A Survey","created":"2021-03-15","cited_by_count":84,"area":null},{"id":"2103.16470","title":"Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection","created":"2021-03-30","cited_by_count":84,"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":"2107.02612","title":"Combining EfficientNet and Vision Transformers for Video Deepfake Detection","created":"2021-07-06","cited_by_count":82,"area":null},{"id":"2112.02889","title":"Joint Learning of Localized Representations from Medical Images and Reports","created":"2021-12-06","cited_by_count":81,"area":null},{"id":"2203.15533","title":"OSOP: A Multi-Stage One Shot Object Pose Estimation Framework","created":"2022-03-29","cited_by_count":81,"area":null},{"id":"2205.14871","title":"You Only Need 90K Parameters to Adapt Light: A Light Weight Transformer for Image Enhancement and Exposure Correction","created":"2022-05-30","cited_by_count":81,"area":null},{"id":"2201.08970","title":"Parallel Rectangle Flip Attack: A Query-based Black-box Attack against Object Detection","created":"2022-01-22","cited_by_count":79,"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":"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":"2107.00420","title":"CBNet: A Composite Backbone Network Architecture for Object Detection","created":"2021-07-01","cited_by_count":77,"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":"2203.16250","title":"PP-YOLOE: An evolved version of YOLO","created":"2022-03-30","cited_by_count":75,"area":null},{"id":"2402.15584","title":"State Space Models for Event Cameras","created":"2024-02-23","cited_by_count":75,"area":null},{"id":"2203.06398","title":"SIGMA: Semantic-complete Graph Matching for Domain Adaptive Object Detection","created":"2022-03-12","cited_by_count":74,"area":null},{"id":"2209.06192","title":"StoryDALL-E: Adapting Pretrained Text-to-Image Transformers for Story Continuation","created":"2022-09-13","cited_by_count":74,"area":null},{"id":"2201.00443","title":"Scene Graph Generation: A Comprehensive Survey","created":"2022-01-03","cited_by_count":73,"area":null},{"id":"2510.12798","title":"Detect Anything via Next Point Prediction","created":"2025-10-14","cited_by_count":73,"area":null},{"id":"2103.09136","title":"QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection","created":"2021-03-16","cited_by_count":70,"area":null},{"id":"2108.09518","title":"MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?","created":"2021-08-21","cited_by_count":69,"area":null},{"id":"2205.00272","title":"Improving Visual Grounding with Visual-Linguistic Verification and Iterative Reasoning","created":"2022-04-30","cited_by_count":69,"area":null},{"id":"2107.03332","title":"SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimation","created":"2021-07-07","cited_by_count":68,"area":null},{"id":"2308.13853","title":"Beyond One-to-One: Rethinking the Referring Image Segmentation","created":"2023-08-26","cited_by_count":68,"area":null},{"id":"2104.03541","title":"Multiple Object Tracking with Correlation Learning","created":"2021-04-08","cited_by_count":67,"area":null}],"next_cursor":"100"}