{"list":"other","total":71,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"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":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1912.04958","title":"Analyzing and Improving the Image Quality of StyleGAN","created":"2019-12-03","cited_by_count":3588},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"1511.06434","title":"Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks","created":"2015-11-19","cited_by_count":2054},{"id":"1801.01401","title":"Demystifying MMD GANs","created":"2018-01-04","cited_by_count":1293},{"id":"1711.11585","title":"High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs","created":"2017-11-30","cited_by_count":1179},{"id":"1611.00712","title":"The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables","created":"2016-11-02","cited_by_count":1148},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"1711.09020","title":"StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation","created":"2017-11-24","cited_by_count":1039},{"id":"1703.10593","title":"Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks","created":"2017-03-30","cited_by_count":707},{"id":"2007.15651","title":"Contrastive Learning for Unpaired Image-to-Image Translation","created":"2020-07-30","cited_by_count":639},{"id":"1802.00434","title":"DensePose: Dense Human Pose Estimation In The Wild","created":"2018-02-01","cited_by_count":575},{"id":"1904.02689","title":"YOLACT: Real-time Instance Segmentation","created":"2019-04-04","cited_by_count":443},{"id":"2008.11200","title":"GRAB: A Dataset of Whole-Body Human Grasping of Objects","created":"2020-08-25","cited_by_count":405},{"id":"1904.05767","title":"Learning joint reconstruction of hands and manipulated objects","created":"2019-04-11","cited_by_count":378},{"id":"2111.12503","title":"Extracting Triangular 3D Models, Materials, and Lighting From Images","created":"2021-11-24","cited_by_count":366},{"id":"2101.04061","title":"Towards Real-World Blind Face Restoration with Generative Facial Prior","created":"2021-01-11","cited_by_count":349},{"id":"2112.05814","title":"Deep ViT Features as Dense Visual Descriptors","created":"2021-12-10","cited_by_count":330},{"id":"1704.02510","title":"DualGAN: Unsupervised Dual Learning for Image-to-Image Translation","created":"2017-04-08","cited_by_count":310},{"id":"1705.03550","title":"CORe50: a New Dataset and Benchmark for Continuous Object Recognition","created":"2017-05-09","cited_by_count":289},{"id":"1703.05192","title":"Learning to Discover Cross-Domain Relations with Generative Adversarial Networks","created":"2017-03-15","cited_by_count":278},{"id":"1909.04349","title":"FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Images","created":"2019-09-10","cited_by_count":271},{"id":"1705.09368","title":"Pose Guided Person Image Generation","created":"2017-05-25","cited_by_count":251},{"id":"2008.09309","title":"InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image","created":"2020-08-21","cited_by_count":245},{"id":"1705.01389","title":"Learning to Estimate 3D Hand Pose from Single RGB Images","created":"2017-05-03","cited_by_count":234},{"id":"1704.02463","title":"First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations","created":"2017-04-08","cited_by_count":230},{"id":"2201.00424","title":"Splicing ViT Features for Semantic Appearance Transfer","created":"2022-01-02","cited_by_count":209},{"id":"1812.08861","title":"Animating Arbitrary Objects via Deep Motion Transfer","created":"2018-12-20","cited_by_count":208},{"id":"2201.02610","title":"Embodied Hands: Modeling and Capturing Hands and Bodies Together","created":"2022-01-07","cited_by_count":181},{"id":"1904.12785","title":"Style Transfer by Relaxed Optimal Transport and Self-Similarity","created":"2019-04-29","cited_by_count":168},{"id":"1903.09760","title":"Photorealistic Style Transfer via Wavelet Transforms","created":"2019-03-23","cited_by_count":166},{"id":"1712.01057","title":"GANerated Hands for Real-time 3D Hand Tracking from Monocular RGB","created":"2017-12-04","cited_by_count":147},{"id":"2004.01946","title":"Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wild","created":"2020-04-04","cited_by_count":146},{"id":"2103.04559","title":"Parser-Free Virtual Try-on via Distilling Appearance Flows","created":"2021-03-08","cited_by_count":143},{"id":"2001.01629","title":"Deep Snake for Real-Time Instance Segmentation","created":"2020-01-06","cited_by_count":112},{"id":"2003.09572","title":"Monocular Real-time Hand Shape and Motion Capture using Multi-modal Data","created":"2020-03-21","cited_by_count":106},{"id":"2008.00418","title":"Blind Face Restoration via Deep Multi-scale Component Dictionaries","created":"2020-08-02","cited_by_count":106},{"id":"1909.01955","title":"Dense Extreme Inception Network: Towards a Robust CNN Model for Edge Detection","created":"2019-09-04","cited_by_count":104},{"id":"2003.09282","title":"Weakly Supervised 3D Hand Pose Estimation via Biomechanical Constraints","created":"2020-03-20","cited_by_count":97},{"id":"1804.04829","title":"Learning Warped Guidance for Blind Face Restoration","created":"2018-04-13","cited_by_count":87},{"id":"1704.02201","title":"Real-time Hand Tracking under Occlusion from an Egocentric RGB-D Sensor","created":"2017-04-07","cited_by_count":84},{"id":"1911.11897","title":"AttentionGAN: Unpaired Image-to-Image Translation using Attention-Guided Generative Adversarial Networks","created":"2019-11-27","cited_by_count":77},{"id":"2007.02721","title":"Do Not Mask What You Do Not Need to Mask: a Parser-Free Virtual Try-On","created":"2020-07-03","cited_by_count":77},{"id":"2106.08059","title":"Real-time Pose and Shape Reconstruction of Two Interacting Hands With a Single Depth Camera","created":"2021-06-15","cited_by_count":70},{"id":"2103.02845","title":"Camera-Space Hand Mesh Recovery via Semantic Aggregation and Adaptive 2D-1D Registration","created":"2021-03-04","cited_by_count":59},{"id":"1806.02311","title":"Unsupervised Attention-guided Image to Image Translation","created":"2018-06-06","cited_by_count":58},{"id":"1610.04889","title":"Real-time Joint Tracking of a Hand Manipulating an Object from RGB-D Input","created":"2016-10-16","cited_by_count":56},{"id":"2008.08213","title":"DeepHandMesh: A Weakly-supervised Deep Encoder-Decoder Framework for High-fidelity Hand Mesh Modeling","created":"2020-08-19","cited_by_count":49},{"id":"1711.04322","title":"11K Hands: Gender recognition and biometric identification using a large dataset of hand images","created":"2017-11-12","cited_by_count":46},{"id":"2109.06166","title":"Pose with Style: Detail-Preserving Pose-Guided Image Synthesis with Conditional StyleGAN","created":"2021-09-13","cited_by_count":45},{"id":"1610.07214","title":"3D Hand Pose Tracking and Estimation Using Stereo Matching","created":"2016-10-23","cited_by_count":35},{"id":"2007.05168","title":"SeqHAND:RGB-Sequence-Based 3D Hand Pose and Shape Estimation","created":"2020-07-10","cited_by_count":34},{"id":"2107.11646","title":"Hand Image Understanding via Deep Multi-Task Learning","created":"2021-07-24","cited_by_count":31},{"id":"1808.04859","title":"GestureGAN for Hand Gesture-to-Gesture Translation in the Wild","created":"2018-08-14","cited_by_count":27},{"id":"2006.01320","title":"Two-hand Global 3D Pose Estimation Using Monocular RGB","created":"2020-06-01","cited_by_count":27},{"id":"2210.07650","title":"DART: Articulated Hand Model with Diverse Accessories and Rich Textures","created":"2022-10-14","cited_by_count":25},{"id":"2003.13764","title":"Measuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3D Hand Pose Estimation under Hand-Object Interaction","created":"2020-03-30","cited_by_count":24},{"id":"1707.03742","title":"Large-scale Multiview 3D Hand Pose Dataset","created":"2017-07-12","cited_by_count":20},{"id":"2102.09244","title":"HandTailor: Towards High-Precision Monocular 3D Hand Recovery","created":"2021-02-18","cited_by_count":15},{"id":"1807.05380","title":"3D Hand Pose Estimation using Simulation and Partial-Supervision with a Shared Latent Space","created":"2018-07-14","cited_by_count":2},{"id":"2103.15017","title":"H-GAN: the power of GANs in your Hands","created":"2021-03-27","cited_by_count":2}],"next_cursor":null}