{"list":"other","total":73,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1912.04958","title":"Analyzing and Improving the Image Quality of StyleGAN","created":"2019-12-03","cited_by_count":3588},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"id":"1710.08092","title":"VGGFace2: A dataset for recognising faces across pose and age","created":"2017-10-23","cited_by_count":914},{"id":"2211.07636","title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","created":"2022-11-14","cited_by_count":691},{"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":"2303.16203","title":"Your Diffusion Model is Secretly a Zero-Shot Classifier","created":"2023-03-28","cited_by_count":306},{"id":"2207.06405","title":"Masked Autoencoders that Listen","created":"2022-07-13","cited_by_count":273},{"id":"2303.02153","title":"Unleashing Text-to-Image Diffusion Models for Visual Perception","created":"2023-03-03","cited_by_count":269},{"id":"2408.12569","title":"Sapiens: Foundation for Human Vision Models","created":"2024-08-22","cited_by_count":229},{"id":"2109.15102","title":"Fake It Till You Make It: Face analysis in the wild using synthetic data alone","created":"2021-09-30","cited_by_count":200},{"id":"2112.03109","title":"General Facial Representation Learning in a Visual-Linguistic Manner","created":"2021-12-06","cited_by_count":195},{"id":"2205.03409","title":"VFHQ: A High-Quality Dataset and Benchmark for Video Face Super-Resolution","created":"2022-05-06","cited_by_count":176},{"id":"1910.10088","title":"Gaze360: Physically Unconstrained Gaze Estimation in the Wild","created":"2019-10-22","cited_by_count":174},{"id":"1612.03153","title":"Panoptic Studio: A Massively Multiview System for Social Interaction Capture","created":"2016-12-09","cited_by_count":173},{"id":"1606.05814","title":"Eye Tracking for Everyone","created":"2016-06-18","cited_by_count":155},{"id":"1504.02863","title":"Appearance-Based Gaze Estimation in the Wild","created":"2015-04-11","cited_by_count":153},{"id":"2007.15837","title":"ETH-XGaze: A Large Scale Dataset for Gaze Estimation under Extreme Head Pose and Gaze Variation","created":"2020-07-31","cited_by_count":141},{"id":"2303.09769","title":"Denoising Diffusion Autoencoders are Unified Self-supervised Learners","created":"2023-03-17","cited_by_count":130},{"id":"1611.08860","title":"It's Written All Over Your Face: Full-Face Appearance-Based Gaze Estimation","created":"2016-11-27","cited_by_count":123},{"id":"1711.09017","title":"MPIIGaze: Real-World Dataset and Deep Appearance-Based Gaze Estimation","created":"2017-11-24","cited_by_count":118},{"id":"2303.14717","title":"CelebV-Text: A Large-Scale Facial Text-Video Dataset","created":"2023-03-26","cited_by_count":104},{"id":"2104.12668","title":"Appearance-based Gaze Estimation With Deep Learning: A Review and Benchmark","created":"2021-04-26","cited_by_count":82},{"id":"1905.01941","title":"Few-Shot Adaptive Gaze Estimation","created":"2019-05-06","cited_by_count":77},{"id":"2003.02501","title":"Detecting Attended Visual Targets in Video","created":"2020-03-05","cited_by_count":77},{"id":"2105.14424","title":"Gaze Estimation using Transformer","created":"2021-05-30","cited_by_count":68},{"id":"2202.03382","title":"Corrupted Image Modeling for Self-Supervised Visual Pre-Training","created":"2022-02-07","cited_by_count":68},{"id":"2303.13496","title":"The effectiveness of MAE pre-pretraining for billion-scale pretraining","created":"2023-03-23","cited_by_count":68},{"id":"2203.03339","title":"L2CS-Net: Fine-Grained Gaze Estimation in Unconstrained Environments","created":"2022-03-07","cited_by_count":65},{"id":"2211.06627","title":"MARLIN: Masked Autoencoder for facial video Representation LearnINg","created":"2022-11-12","cited_by_count":57},{"id":"2103.13173","title":"PureGaze: Purifying Gaze Feature for Generalizable Gaze Estimation","created":"2021-03-24","cited_by_count":54},{"id":"2404.10242","title":"Masked Autoencoders for Microscopy are Scalable Learners of Cellular Biology","created":"2024-04-16","cited_by_count":52},{"id":"1505.05916","title":"Rendering of Eyes for Eye-Shape Registration and Gaze Estimation","created":"2015-05-21","cited_by_count":49},{"id":"2311.05709","title":"OmniVec: Learning robust representations with cross modal sharing","created":"2023-11-07","cited_by_count":44},{"id":"2410.24223","title":"URAvatar: Universal Relightable Gaussian Codec Avatars","created":"2024-10-31","cited_by_count":43},{"id":"2107.13780","title":"Generalizing Gaze Estimation with Outlier-guided Collaborative Adaptation","created":"2021-07-29","cited_by_count":42},{"id":"2307.07487","title":"DreamTeacher: Pretraining Image Backbones with Deep Generative Models","created":"2023-07-14","cited_by_count":37},{"id":"2108.05479","title":"Automatic Gaze Analysis: A Survey of Deep Learning based Approaches","created":"2021-08-12","cited_by_count":33},{"id":"2010.12307","title":"Self-Learning Transformations for Improving Gaze and Head Redirection","created":"2020-10-23","cited_by_count":28},{"id":"2105.09803","title":"Weakly-Supervised Physically Unconstrained Gaze Estimation","created":"2021-05-20","cited_by_count":28},{"id":"2403.02138","title":"Self-Supervised Facial Representation Learning with Facial Region Awareness","created":"2024-03-04","cited_by_count":17},{"id":"2210.13404","title":"Contrastive Representation Learning for Gaze Estimation","created":"2022-10-24","cited_by_count":14},{"id":"2310.18131","title":"End-to-end Video Gaze Estimation via Capturing Head-face-eye Spatial-temporal Interaction Context","created":"2023-10-27","cited_by_count":14},{"id":"2403.00459","title":"Deformable One-shot Face Stylization via DINO Semantic Guidance","created":"2024-03-01","cited_by_count":14},{"id":"2201.07927","title":"Learning-by-Novel-View-Synthesis for Full-Face Appearance-Based 3D Gaze Estimation","created":"2022-01-20","cited_by_count":13},{"id":"2403.05124","title":"CLIP-Gaze: Towards General Gaze Estimation via Visual-Linguistic Model","created":"2024-03-08","cited_by_count":13},{"id":"2410.20717","title":"Face-MLLM: A Large Face Perception Model","created":"2024-10-28","cited_by_count":13},{"id":"2212.04823","title":"GazeNeRF: 3D-Aware Gaze Redirection with Neural Radiance Fields","created":"2022-12-08","cited_by_count":12},{"id":"2307.01470","title":"A Review of Driver Gaze Estimation and Application in Gaze Behavior Understanding","created":"2023-07-04","cited_by_count":12},{"id":"2212.02997","title":"3DGazeNet: Generalizing Gaze Estimation with Weak-Supervision from Synthetic Views","created":"2022-12-06","cited_by_count":11},{"id":"2302.04530","title":"Gaze-based intention estimation: principles, methodologies, and applications in HRI","created":"2023-02-09","cited_by_count":11},{"id":"2212.14710","title":"NeRF-Gaze: A Head-Eye Redirection Parametric Model for Gaze Estimation","created":"2022-12-30","cited_by_count":10},{"id":"2305.12704","title":"Rotation-Constrained Cross-View Feature Fusion for Multi-View Appearance-based Gaze Estimation","created":"2023-05-22","cited_by_count":10},{"id":"2309.03575","title":"Toward High Quality Facial Representation Learning","created":"2023-09-07","cited_by_count":10},{"id":"2411.08606","title":"LG-Gaze: Learning Geometry-aware Continuous Prompts for Language-Guided Gaze Estimation","created":"2024-11-13","cited_by_count":9},{"id":"2210.02082","title":"Jitter Does Matter: Adapting Gaze Estimation to New Domains","created":"2022-10-05","cited_by_count":6},{"id":"2305.11452","title":"ReDirTrans: Latent-to-Latent Translation for Gaze and Head Redirection","created":"2023-05-19","cited_by_count":6},{"id":"2308.00773","title":"High-Fidelity Eye Animatable Neural Radiance Fields for Human Face","created":"2023-08-01","cited_by_count":6},{"id":"2404.10718","title":"GazeHTA: End-to-end Gaze Target Detection with Head-Target Association","created":"2024-04-16","cited_by_count":6},{"id":"2305.16140","title":"Domain-Adaptive Full-Face Gaze Estimation via Novel-View-Synthesis and Feature Disentanglement","created":"2023-05-25","cited_by_count":3},{"id":"2407.00315","title":"Learning Unsupervised Gaze Representation via Eye Mask Driven Information Bottleneck","created":"2024-06-29","cited_by_count":2},{"id":"2405.01439","title":"Improving Domain Generalization on Gaze Estimation via Branch-out Auxiliary Regularization","created":"2024-05-02","cited_by_count":1}],"next_cursor":null}