{"list":"other","total":78,"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"2303.04137","title":"Diffusion Policy: Visuomotor Policy Learning via Action Diffusion","created":"2023-03-07","cited_by_count":2838},{"id":"2001.07685","title":"FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence","created":"2020-01-21","cited_by_count":2085},{"id":"1708.04552","title":"Improved Regularization of Convolutional Neural Networks with Cutout","created":"2017-08-15","cited_by_count":1628},{"id":"2304.13705","title":"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware","created":"2023-04-23","cited_by_count":1568},{"id":"1905.02249","title":"MixMatch: A Holistic Approach to Semi-Supervised Learning","created":"2019-05-06","cited_by_count":1391},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"2104.00298","title":"EfficientNetV2: Smaller Models and Faster Training","created":"2021-04-01","cited_by_count":1135},{"id":"1904.12848","title":"Unsupervised Data Augmentation for Consistency Training","created":"2019-04-29","cited_by_count":1060},{"id":"1610.02242","title":"Temporal Ensembling for Semi-Supervised Learning","created":"2016-10-07","cited_by_count":1057},{"id":"1704.08063","title":"SphereFace: Deep Hypersphere Embedding for Face Recognition","created":"2017-04-26","cited_by_count":737},{"id":"2110.08263","title":"FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling","created":"2021-10-15","cited_by_count":540},{"id":"1703.07332","title":"How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)","created":"2017-03-21","cited_by_count":525},{"id":"2101.03697","title":"RepVGG: Making VGG-style ConvNets Great Again","created":"2021-01-11","cited_by_count":522},{"id":"2312.05251","title":"Reconstructing Hands in 3D with Transformers","created":"2023-12-08","cited_by_count":306},{"id":"1511.06523","title":"WIDER FACE: A Face Detection Benchmark","created":"2015-11-20","cited_by_count":298},{"id":"1805.00123","title":"CrowdHuman: A Benchmark for Detecting Human in a Crowd","created":"2018-04-30","cited_by_count":284},{"id":"2207.10666","title":"TinyViT: Fast Pretraining Distillation for Small Vision Transformers","created":"2022-07-21","cited_by_count":234},{"id":"2009.09960","title":"Towards Fast, Accurate and Stable 3D Dense Face Alignment","created":"2020-09-21","cited_by_count":219},{"id":"2208.09910","title":"Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation","created":"2022-08-21","cited_by_count":178},{"id":"1905.06817","title":"Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision","created":"2019-05-16","cited_by_count":176},{"id":"1710.00925","title":"Fine-Grained Head Pose Estimation Without Keypoints","created":"2017-10-02","cited_by_count":163},{"id":"1712.04440","title":"Data Distillation: Towards Omni-Supervised Learning","created":"2017-12-12","cited_by_count":126},{"id":"1603.01249","title":"HyperFace: A Deep Multi-task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition","created":"2016-03-03","cited_by_count":104},{"id":"2303.13071","title":"PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360$^{\\circ}$","created":"2023-03-23","cited_by_count":93},{"id":"2006.14616","title":"An Analysis of SVD for Deep Rotation Estimation","created":"2020-06-25","cited_by_count":86},{"id":"2004.06468","title":"Self6D: Self-Supervised Monocular 6D Object Pose Estimation","created":"2020-04-14","cited_by_count":79},{"id":"2111.09833","title":"TransMix: Attend to Mix for Vision Transformers","created":"2021-11-18","cited_by_count":79},{"id":"1804.01110","title":"Unsupervised Geometry-Aware Representation for 3D Human Pose Estimation","created":"2018-04-03","cited_by_count":73},{"id":"2103.16725","title":"SimPLE: Similar Pseudo Label Exploitation for Semi-Supervised Classification","created":"2021-03-30","cited_by_count":68},{"id":"2106.05965","title":"Implicit-PDF: Non-Parametric Representation of Probability Distributions on the Rotation Manifold","created":"2021-06-10","cited_by_count":65},{"id":"2202.12555","title":"6D Rotation Representation For Unconstrained Head Pose Estimation","created":"2022-02-25","cited_by_count":64},{"id":"2203.02261","title":"Class-Aware Contrastive Semi-Supervised Learning","created":"2022-03-04","cited_by_count":62},{"id":"2012.07791","title":"img2pose: Face Alignment and Detection via 6DoF, Face Pose Estimation","created":"2020-12-14","cited_by_count":58},{"id":"2207.08409","title":"TokenMix: Rethinking Image Mixing for Data Augmentation in Vision Transformers","created":"2022-07-18","cited_by_count":48},{"id":"2005.10353","title":"WHENet: Real-time Fine-Grained Estimation for Wide Range Head Pose","created":"2020-05-20","cited_by_count":47},{"id":"1803.09331","title":"StarMap for Category-Agnostic Keypoint and Viewpoint Estimation","created":"2018-03-25","cited_by_count":42},{"id":"2101.12378","title":"NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose Estimation","created":"2021-01-29","cited_by_count":41},{"id":"2311.06922","title":"A Survey on Socially Aware Robot Navigation: Taxonomy and Future Challenges","created":"2023-11-12","cited_by_count":39},{"id":"1904.05404","title":"Spherical Regression: Learning Viewpoints, Surface Normals and 3D Rotations on n-Spheres","created":"2019-04-10","cited_by_count":37},{"id":"2006.09740","title":"Probabilistic orientation estimation with matrix Fisher distributions","created":"2020-06-17","cited_by_count":36},{"id":"2010.07184","title":"A Vector-based Representation to Enhance Head Pose Estimation","created":"2020-10-14","cited_by_count":35},{"id":"2203.10339","title":"Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimation","created":"2022-03-19","cited_by_count":34},{"id":"2104.05248","title":"All Labels Are Not Created Equal: Enhancing Semi-supervision via Label Grouping and Co-training","created":"2021-04-12","cited_by_count":32},{"id":"2204.03688","title":"DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single Image","created":"2022-04-07","cited_by_count":31},{"id":"2202.06851","title":"HAKE: A Knowledge Engine Foundation for Human Activity Understanding","created":"2022-02-14","cited_by_count":28},{"id":"2106.03021","title":"SADRNet: Self-Aligned Dual Face Regression Networks for Robust 3D Dense Face Alignment and Reconstruction","created":"2021-06-06","cited_by_count":27},{"id":"2110.09772","title":"Synergy between 3DMM and 3D Landmarks for Accurate 3D Facial Geometry","created":"2021-10-19","cited_by_count":27},{"id":"2303.11066","title":"Boosting Semi-Supervised Learning by Exploiting All Unlabeled Data","created":"2023-03-20","cited_by_count":26},{"id":"2202.02299","title":"Multi-task head pose estimation in-the-wild","created":"2022-02-04","cited_by_count":23},{"id":"2011.12498","title":"An Empirical Study of the Collapsing Problem in Semi-Supervised 2D Human Pose Estimation","created":"2020-11-25","cited_by_count":21},{"id":"2111.10958","title":"MUM : Mix Image Tiles and UnMix Feature Tiles for Semi-Supervised Object Detection","created":"2021-11-22","cited_by_count":21},{"id":"2203.15765","title":"FisherMatch: Semi-Supervised Rotation Regression via Entropy-based Filtering","created":"2022-03-29","cited_by_count":16},{"id":"2110.14213","title":"Neural View Synthesis and Matching for Semi-Supervised Few-Shot Learning of 3D Pose","created":"2021-10-27","cited_by_count":15},{"id":"2304.03937","title":"Delving into Discrete Normalizing Flows on SO(3) Manifold for Probabilistic Rotation Modeling","created":"2023-04-08","cited_by_count":14},{"id":"2303.13556","title":"ProtoCon: Pseudo-label Refinement via Online Clustering and Prototypical Consistency for Efficient Semi-supervised Learning","created":"2023-03-22","cited_by_count":13},{"id":"2401.05807","title":"On the representation and methodology for wide and short range head pose estimation","created":"2024-01-11","cited_by_count":12},{"id":"2005.10984","title":"RankPose: Learning Generalised Feature with Rank Supervision for Head Pose Estimation","created":"2020-05-22","cited_by_count":11},{"id":"2303.04346","title":"Semi-Supervised 2D Human Pose Estimation Driven by Position Inconsistency Pseudo Label Correction Module","created":"2023-03-08","cited_by_count":10},{"id":"2111.01440","title":"HHP-Net: A light Heteroscedastic neural network for Head Pose estimation with uncertainty","created":"2021-11-02","cited_by_count":9},{"id":"2205.04126","title":"Towards 3D Face Reconstruction in Perspective Projection: Estimating 6DoF Face Pose from Monocular Image","created":"2022-05-09","cited_by_count":9},{"id":"2303.01743","title":"A Laplace-inspired Distribution on SO(3) for Probabilistic Rotation Estimation","created":"2023-03-03","cited_by_count":9},{"id":"2303.01503","title":"FeatAug-DETR: Enriching One-to-Many Matching for DETRs with Feature Augmentation","created":"2023-03-02","cited_by_count":7},{"id":"2302.01110","title":"DirectMHP: Direct 2D Multi-Person Head Pose Estimation with Full-range Angles","created":"2023-02-02","cited_by_count":6},{"id":"2305.11522","title":"DSFNet: Dual Space Fusion Network for Occlusion-Robust 3D Dense Face Alignment","created":"2023-05-19","cited_by_count":6},{"id":"2308.05382","title":"Interaction-aware Joint Attention Estimation Using People Attributes","created":"2023-08-10","cited_by_count":6},{"id":"2312.17205","title":"EFHQ: Multi-purpose ExtremePose-Face-HQ dataset","created":"2023-12-28","cited_by_count":6},{"id":"2212.07652","title":"Body-Part Joint Detection and Association via Extended Object Representation","created":"2022-12-15","cited_by_count":5},{"id":"2305.10465","title":"Towards Robust Probabilistic Modeling on SO(3) via Rotation Laplace Distribution","created":"2023-05-17","cited_by_count":5},{"id":"2309.03598","title":"Enhancing Sample Utilization through Sample Adaptive Augmentation in Semi-Supervised Learning","created":"2023-09-07","cited_by_count":5},{"id":"2210.15586","title":"Joint Multi-Person Body Detection and Orientation Estimation via One Unified Embedding","created":"2022-10-27","cited_by_count":3},{"id":"2304.10765","title":"BPJDet: Extended Object Representation for Generic Body-Part Joint Detection","created":"2023-04-21","cited_by_count":2}],"next_cursor":null}