{"list":"other","total":99,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1503.03832","title":"FaceNet: A Unified Embedding for Face Recognition and Clustering","created":"2015-03-12","cited_by_count":2849},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"2004.10934","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","created":"2020-04-23","cited_by_count":1630},{"id":"1511.00561","title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation","created":"2015-11-02","cited_by_count":1487},{"id":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"id":"1712.00726","title":"Cascade R-CNN: Delving into High Quality Object Detection","created":"2017-12-03","cited_by_count":1276},{"id":"1707.01083","title":"ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices","created":"2017-07-04","cited_by_count":1200},{"id":"1911.09070","title":"EfficientDet: Scalable and Efficient Object Detection","created":"2019-11-20","cited_by_count":1020},{"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},{"id":"1603.06937","title":"Stacked Hourglass Networks for Human Pose Estimation","created":"2016-03-22","cited_by_count":915},{"id":"1604.02878","title":"Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks","created":"2016-04-11","cited_by_count":903},{"id":"1710.09829","title":"Dynamic Routing Between Capsules","created":"2017-10-26","cited_by_count":689},{"id":"1904.08189","title":"CenterNet: Keypoint Triplets for Object Detection","created":"2019-04-17","cited_by_count":654},{"id":"2012.12556","title":"A Survey on Visual Transformer","created":"2020-12-23","cited_by_count":654},{"id":"2109.13410","title":"KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D","created":"2021-09-28","cited_by_count":575},{"id":"2405.14458","title":"YOLOv10: Real-Time End-to-End Object Detection","created":"2024-05-23","cited_by_count":515},{"id":"2401.17270","title":"YOLO-World: Real-Time Open-Vocabulary Object Detection","created":"2024-01-30","cited_by_count":503},{"id":"2205.15997","title":"TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving","created":"2022-05-31","cited_by_count":485},{"id":"2103.10697","title":"ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases","created":"2021-03-19","cited_by_count":484},{"id":"2402.13616","title":"YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information","created":"2024-02-21","cited_by_count":425},{"id":"2005.09007","title":"U$^2$-Net: Going Deeper with Nested U-Structure for Salient Object Detection","created":"2020-05-18","cited_by_count":412},{"id":"2204.00964","title":"AdaFace: Quality Adaptive Margin for Face Recognition","created":"2022-04-03","cited_by_count":391},{"id":"1911.11929","title":"CSPNet: A New Backbone that can Enhance Learning Capability of CNN","created":"2019-11-27","cited_by_count":381},{"id":"2103.06627","title":"MagFace: A Universal Representation for Face Recognition and Quality Assessment","created":"2021-03-11","cited_by_count":334},{"id":"1602.00134","title":"Convolutional Pose Machines","created":"2016-01-30","cited_by_count":325},{"id":"1511.06523","title":"WIDER FACE: A Face Detection Benchmark","created":"2015-11-20","cited_by_count":298},{"id":"2005.04757","title":"A Simple Semi-Supervised Learning Framework for Object Detection","created":"2020-05-10","cited_by_count":282},{"id":"1612.00496","title":"3D Bounding Box Estimation Using Deep Learning and Geometry","created":"2016-12-01","cited_by_count":278},{"id":"2209.02976","title":"YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications","created":"2022-09-07","cited_by_count":275},{"id":"2209.08575","title":"SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation","created":"2022-09-18","cited_by_count":252},{"id":"2011.08036","title":"Scaled-YOLOv4: Scaling Cross Stage Partial Network","created":"2020-11-16","cited_by_count":211},{"id":"1901.01892","title":"Scale-Aware Trident Networks for Object Detection","created":"2019-01-07","cited_by_count":159},{"id":"2109.09416","title":"ElasticFace: Elastic Margin Loss for Deep Face Recognition","created":"2021-09-20","cited_by_count":144},{"id":"2004.11757","title":"Ultra Fast Structure-aware Deep Lane Detection","created":"2020-04-24","cited_by_count":122},{"id":"2303.17472","title":"PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation","created":"2023-03-30","cited_by_count":92},{"id":"2111.12083","title":"VISTA 2.0: An Open, Data-driven Simulator for Multimodal Sensing and Policy Learning for Autonomous Vehicles","created":"2021-11-23","cited_by_count":81},{"id":"2007.12147","title":"CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point Blending","created":"2020-07-23","cited_by_count":80},{"id":"2003.09093","title":"Masked Face Recognition Dataset and Application","created":"2020-03-20","cited_by_count":66},{"id":"1603.01976","title":"Deep Contrast Learning for Salient Object Detection","created":"2016-03-07","cited_by_count":52},{"id":"2310.08854","title":"Rank-DETR for High Quality Object Detection","created":"2023-10-13","cited_by_count":50},{"id":"2007.12099","title":"PP-YOLO: An Effective and Efficient Implementation of Object Detector","created":"2020-07-23","cited_by_count":44},{"id":"2103.13886","title":"Robust and Accurate Object Detection via Adversarial Learning","created":"2021-03-23","cited_by_count":42},{"id":"2307.16687","title":"DiffPose: SpatioTemporal Diffusion Model for Video-Based Human Pose Estimation","created":"2023-07-31","cited_by_count":36},{"id":"2303.10610","title":"DiffMIC: Dual-Guidance Diffusion Network for Medical Image Classification","created":"2023-03-19","cited_by_count":32},{"id":"1711.07264","title":"Light-Head R-CNN: In Defense of Two-Stage Object Detector","created":"2017-11-20","cited_by_count":30},{"id":"2104.10419","title":"PP-YOLOv2: A Practical Object Detector","created":"2021-04-21","cited_by_count":30},{"id":"1812.06314","title":"PiCANet: Pixel-wise Contextual Attention Learning for Accurate Saliency Detection","created":"2018-12-15","cited_by_count":28},{"id":"1510.05484","title":"DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection","created":"2015-10-19","cited_by_count":24},{"id":"2109.05565","title":"SphereFace Revived: Unifying Hyperspherical Face Recognition","created":"2021-09-12","cited_by_count":23},{"id":"2011.13322","title":"Spatio-Temporal Inception Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2020-11-26","cited_by_count":18},{"id":"2402.02352","title":"Region-Based Representations Revisited","created":"2024-02-04","cited_by_count":18},{"id":"2202.04256","title":"GiraffeDet: A Heavy-Neck Paradigm for Object Detection","created":"2022-02-09","cited_by_count":17},{"id":"2102.04738","title":"End-to-End Deep Learning of Lane Detection and Path Prediction for Real-Time Autonomous Driving","created":"2021-02-09","cited_by_count":16},{"id":"2208.02019","title":"YOLO-FaceV2: A Scale and Occlusion Aware Face Detector","created":"2022-08-03","cited_by_count":15},{"id":"2407.09012","title":"TCAN: Animating Human Images with Temporally Consistent Pose Guidance using Diffusion Models","created":"2024-07-12","cited_by_count":15},{"id":"2503.07499","title":"AthletePose3D: A Benchmark Dataset for 3D Human Pose Estimation and Kinematic Validation in Athletic Movements","created":"2025-03-10","cited_by_count":14},{"id":"2204.02397","title":"SALISA: Saliency-based Input Sampling for Efficient Video Object Detection","created":"2022-04-05","cited_by_count":12},{"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},{"id":"2402.18844","title":"Deep learning for 3D human pose estimation and mesh recovery: A survey","created":"2024-02-29","cited_by_count":11},{"id":"2010.13321","title":"View-Invariant, Occlusion-Robust Probabilistic Embedding for Human Pose","created":"2020-10-23","cited_by_count":9},{"id":"2011.04244","title":"Real-time object detection method based on improved YOLOv4-tiny","created":"2020-11-09","cited_by_count":9},{"id":"1812.00469","title":"Anchor Box Optimization for Object Detection","created":"2018-12-02","cited_by_count":8},{"id":"2401.07801","title":"Pedestrian Detection in Low-Light Conditions: A Comprehensive Survey","created":"2024-01-15","cited_by_count":8},{"id":"1809.06972","title":"Mapless Online Detection of Dynamic Objects in 3D Lidar","created":"2018-09-19","cited_by_count":7},{"id":"2504.09666","title":"Uncertainty Guided Refinement for Fine-Grained Salient Object Detection","created":"2025-04-13","cited_by_count":4},{"id":"2407.07092","title":"V-VIPE: Variational View Invariant Pose Embedding","created":"2024-07-09","cited_by_count":3},{"id":"2410.04574","title":"Enhancing 3D Human Pose Estimation Amidst Severe Occlusion with Dual Transformer Fusion","created":"2024-10-06","cited_by_count":3},{"id":"2207.07742","title":"Human keypoint detection for close proximity human-robot interaction","created":"2022-07-15","cited_by_count":2},{"id":"2404.14996","title":"CA-Stream: Attention-based pooling for interpretable image recognition","created":"2024-04-23","cited_by_count":2},{"id":"2412.02479","title":"OODFace: Benchmarking Robustness of Face Recognition under Common Corruptions and Appearance Variations","created":"2024-12-03","cited_by_count":2},{"id":"2412.20768","title":"Sample Correlation for Fingerprinting Deep Face Recognition","created":"2024-12-30","cited_by_count":2},{"id":"1406.2419","title":"Why do linear SVMs trained on HOG features perform so well?","created":"2014-06-10","cited_by_count":1},{"id":"2106.14475","title":"A More Compact Object Detector Head Network with Feature Enhancement and Relational Reasoning","created":"2021-06-28","cited_by_count":1},{"id":"2310.16103","title":"LaksNet: an end-to-end deep learning model for self-driving cars in Udacity simulator","created":"2023-10-24","cited_by_count":1},{"id":"2408.16645","title":"SODAWideNet++: Combining Attention and Convolutions for Salient Object Detection","created":"2024-08-29","cited_by_count":1}],"next_cursor":null}