{"list":"other","total":98,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1411.7766","title":"Deep Learning Face Attributes in the Wild","created":"2014-11-28","cited_by_count":3693},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"id":"1603.09246","title":"Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles","created":"2016-03-30","cited_by_count":1382},{"id":"1801.09414","title":"CosFace: Large Margin Cosine Loss for Deep Face Recognition","created":"2018-01-29","cited_by_count":971},{"id":"1704.03976","title":"Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning","created":"2017-04-13","cited_by_count":920},{"id":"2111.11432","title":"Florence: A New Foundation Model for Computer Vision","created":"2021-11-22","cited_by_count":804},{"id":"1907.11922","title":"MaskGAN: Towards Diverse and Interactive Facial Image Manipulation","created":"2019-07-27","cited_by_count":628},{"id":"1607.08221","title":"MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition","created":"2016-07-27","cited_by_count":624},{"id":"1707.03237","title":"Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations","created":"2017-07-11","cited_by_count":620},{"id":"2304.06718","title":"Segment Everything Everywhere All at Once","created":"2023-04-13","cited_by_count":548},{"id":"1708.03985","title":"AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild","created":"2017-08-14","cited_by_count":492},{"id":"1702.08423","title":"Age Progression/Regression by Conditional Adversarial Autoencoder","created":"2017-02-27","cited_by_count":429},{"id":"2204.00964","title":"AdaFace: Quality Adaptive Margin for Face Recognition","created":"2022-04-03","cited_by_count":391},{"id":"1708.08197","title":"Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments","created":"2017-08-28","cited_by_count":260},{"id":"1911.12861","title":"SEAN: Image Synthesis with Semantic Region-Adaptive Normalization","created":"2019-11-28","cited_by_count":253},{"id":"2103.04098","title":"WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition","created":"2021-03-06","cited_by_count":223},{"id":"2112.03109","title":"General Facial Representation Learning in a Visual-Linguistic Manner","created":"2021-12-06","cited_by_count":195},{"id":"2306.05422","title":"Tracking Everything Everywhere All at Once","created":"2023-06-08","cited_by_count":193},{"id":"1511.03339","title":"Attention to Scale: Scale-aware Semantic Image Segmentation","created":"2015-11-10","cited_by_count":169},{"id":"1710.00925","title":"Fine-Grained Head Pose Estimation Without Keypoints","created":"2017-10-02","cited_by_count":163},{"id":"2010.05222","title":"Partial FC: Training 10 Million Identities on a Single Machine","created":"2020-10-11","cited_by_count":163},{"id":"1406.4773","title":"Deep Learning Face Representation by Joint Identification-Verification","created":"2014-06-18","cited_by_count":162},{"id":"2002.10392","title":"Suppressing Uncertainties for Large-Scale Facial Expression Recognition","created":"2020-02-24","cited_by_count":157},{"id":"2209.07526","title":"OmniVL:One Foundation Model for Image-Language and Video-Language Tasks","created":"2022-09-15","cited_by_count":143},{"id":"2303.10826","title":"Visual Prompt Multi-Modal Tracking","created":"2023-03-20","cited_by_count":142},{"id":"1805.10483","title":"Look at Boundary: A Boundary-Aware Face Alignment Algorithm","created":"2018-05-26","cited_by_count":138},{"id":"1901.07884","title":"Rank consistent ordinal regression for neural networks with application to age estimation","created":"2019-01-20","cited_by_count":133},{"id":"2107.10834","title":"Query2Label: A Simple Transformer Way to Multi-Label Classification","created":"2021-07-22","cited_by_count":128},{"id":"1905.04075","title":"Region Attention Networks for Pose and Occlusion Robust Facial Expression Recognition","created":"2019-05-10","cited_by_count":127},{"id":"1711.06753","title":"Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks","created":"2017-11-17","cited_by_count":109},{"id":"2103.02023","title":"EnD: Entangling and Disentangling deep representations for bias correction","created":"2021-03-02","cited_by_count":105},{"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":"1512.00570","title":"Attribute2Image: Conditional Image Generation from Visual Attributes","created":"2015-12-02","cited_by_count":93},{"id":"2104.00232","title":"Dive into Ambiguity: Latent Distribution Mining and Pairwise Uncertainty Estimation for Facial Expression Recognition","created":"2021-04-01","cited_by_count":89},{"id":"2004.02980","title":"LUVLi Face Alignment: Estimating Landmarks' Location, Uncertainty, and Visibility Likelihood","created":"2020-04-06","cited_by_count":87},{"id":"2401.10229","title":"OMG-Seg: Is One Model Good Enough For All Segmentation?","created":"2024-01-18","cited_by_count":75},{"id":"2003.03771","title":"Pixel-in-Pixel Net: Towards Efficient Facial Landmark Detection in the Wild","created":"2020-03-08","cited_by_count":74},{"id":"2204.02776","title":"3D face reconstruction with dense landmarks","created":"2022-04-06","cited_by_count":70},{"id":"2202.12555","title":"6D Rotation Representation For Unconstrained Head Pose Estimation","created":"2022-02-25","cited_by_count":64},{"id":"2303.11749","title":"Detecting Everything in the Open World: Towards Universal Object Detection","created":"2023-03-21","cited_by_count":62},{"id":"1803.04108","title":"Style Aggregated Network for Facial Landmark Detection","created":"2018-03-12","cited_by_count":60},{"id":"2012.07791","title":"img2pose: Face Alignment and Detection via 6DoF, Face Pose Estimation","created":"2020-12-14","cited_by_count":58},{"id":"2103.13629","title":"Learning Probabilistic Ordinal Embeddings for Uncertainty-Aware Regression","created":"2021-03-25","cited_by_count":58},{"id":"1807.00966","title":"Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark Detectors","created":"2018-07-03","cited_by_count":49},{"id":"2005.10353","title":"WHENet: Real-time Fine-Grained Estimation for Wide Range Head Pose","created":"2020-05-20","cited_by_count":47},{"id":"2203.06541","title":"Sparse Local Patch Transformer for Robust Face Alignment and Landmarks Inherent Relation Learning","created":"2022-03-13","cited_by_count":47},{"id":"1904.02549","title":"DeCaFA: Deep Convolutional Cascade for Face Alignment In The Wild","created":"2019-04-04","cited_by_count":46},{"id":"1611.00851","title":"An All-In-One Convolutional Neural Network for Face Analysis","created":"2016-11-03","cited_by_count":45},{"id":"2203.13122","title":"Moving Window Regression: A Novel Approach to Ordinal Regression","created":"2022-03-24","cited_by_count":44},{"id":"1706.00906","title":"Heterogeneous Face Attribute Estimation: A Deep Multi-Task Learning Approach","created":"2017-06-03","cited_by_count":43},{"id":"2306.02763","title":"STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detection","created":"2023-06-05","cited_by_count":43},{"id":"2307.04616","title":"MiVOLO: Multi-input Transformer for Age and Gender Estimation","created":"2023-07-10","cited_by_count":42},{"id":"1803.05982","title":"Real-time Deep Pose Estimation with Geodesic Loss for Image-to-Template Rigid Registration","created":"2018-03-15","cited_by_count":40},{"id":"2308.11509","title":"SwinFace: A Multi-task Transformer for Face Recognition, Expression Recognition, Age Estimation and Attribute Estimation","created":"2023-08-22","cited_by_count":39},{"id":"1805.04855","title":"Covariance Pooling For Facial Expression Recognition","created":"2018-05-13","cited_by_count":37},{"id":"2010.07184","title":"A Vector-based Representation to Enhance Head Pose Estimation","created":"2020-10-14","cited_by_count":35},{"id":"1603.07027","title":"MOON: A Mixed Objective Optimization Network for the Recognition of Facial Attributes","created":"2016-03-22","cited_by_count":34},{"id":"1906.01342","title":"Face Parsing with RoI Tanh-Warping","created":"2019-06-04","cited_by_count":33},{"id":"2304.00600","title":"Recurrence without Recurrence: Stable Video Landmark Detection with Deep Equilibrium Models","created":"2023-04-02","cited_by_count":27},{"id":"2007.11240","title":"Edge-aware Graph Representation Learning and Reasoning for Face Parsing","created":"2020-07-22","cited_by_count":26},{"id":"2203.14448","title":"Decoupled Multi-task Learning with Cyclical Self-Regulation for Face Parsing","created":"2022-03-28","cited_by_count":26},{"id":"1311.5591","title":"PANDA: Pose Aligned Networks for Deep Attribute Modeling","created":"2013-11-21","cited_by_count":23},{"id":"2202.02299","title":"Multi-task head pose estimation in-the-wild","created":"2022-02-04","cited_by_count":23},{"id":"2002.03683","title":"Deep Multi-task Multi-label CNN for Effective Facial Attribute Classification","created":"2020-02-10","cited_by_count":22},{"id":"2307.04570","title":"A Call to Reflect on Evaluation Practices for Age Estimation: Comparative Analysis of the State-of-the-Art and a Unified Benchmark","created":"2023-07-10","cited_by_count":19},{"id":"2006.15864","title":"Deep Ordinal Regression with Label Diversity","created":"2020-06-29","cited_by_count":17},{"id":"1704.08740","title":"Improving Facial Attribute Prediction using Semantic Segmentation","created":"2017-04-27","cited_by_count":16},{"id":"2101.07034","title":"AGRNet: Adaptive Graph Representation Learning and Reasoning for Face Parsing","created":"2021-01-18","cited_by_count":16},{"id":"2104.03100","title":"HIH: Towards More Accurate Face Alignment via Heatmap in Heatmap","created":"2021-04-07","cited_by_count":15},{"id":"2207.03917","title":"RePFormer: Refinement Pyramid Transformer for Robust Facial Landmark Detection","created":"2022-07-08","cited_by_count":13},{"id":"2403.09500","title":"Faceptor: A Generalist Model for Face Perception","created":"2024-03-14","cited_by_count":13},{"id":"1609.09642","title":"A CNN Cascade for Landmark Guided Semantic Part Segmentation","created":"2016-09-30","cited_by_count":12},{"id":"1709.08127","title":"Robust Facial Landmark Detection under Significant Head Poses and Occlusion","created":"2017-09-23","cited_by_count":12},{"id":"1709.08130","title":"Simultaneous Facial Landmark Detection, Pose and Deformation Estimation under Facial Occlusion","created":"2017-09-23","cited_by_count":12},{"id":"1805.01290","title":"Multi-task Learning of Cascaded CNN for Facial Attribute Classification","created":"2018-05-03","cited_by_count":12},{"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":"2304.02530","title":"Face Transformer: Towards High Fidelity and Accurate Face Swapping","created":"2023-04-05","cited_by_count":11},{"id":"1611.10152","title":"Combining Data-driven and Model-driven Methods for Robust Facial Landmark Detection","created":"2016-11-30","cited_by_count":8},{"id":"1902.01831","title":"Face Alignment using a 3D Deeply-initialized Ensemble of Regression Trees","created":"2019-02-05","cited_by_count":8},{"id":"2007.04514","title":"Deep Multi-task Learning for Facial Expression Recognition and Synthesis Based on Selective Feature Sharing","created":"2020-07-09","cited_by_count":8},{"id":"2303.15122","title":"Parameter Efficient Local Implicit Image Function Network for Face Segmentation","created":"2023-03-27","cited_by_count":8},{"id":"1801.03546","title":"Segment-based Methods for Facial Attribute Detection from Partial Faces","created":"2018-01-10","cited_by_count":7},{"id":"2007.01771","title":"Learning Expectation of Label Distribution for Facial Age and Attractiveness Estimation","created":"2020-07-03","cited_by_count":7},{"id":"1911.03281","title":"Dynamic Multi-Task Learning for Face Recognition with Facial Expression","created":"2019-11-08","cited_by_count":6},{"id":"2112.08022","title":"Segmentation-Reconstruction-Guided Facial Image De-occlusion","created":"2021-12-15","cited_by_count":6},{"id":"2311.01929","title":"ProS: Facial Omni-Representation Learning via Prototype-based Self-Distillation","created":"2023-11-03","cited_by_count":3}],"next_cursor":null}