{"list":"other","total":64,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2302.08453","title":"T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models","created":"2023-02-16","cited_by_count":1351},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"1812.08008","title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2018-12-18","cited_by_count":1162},{"id":"2107.08430","title":"YOLOX: Exceeding YOLO Series in 2021","created":"2021-07-18","cited_by_count":1071},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"2210.03142","title":"On Distillation of Guided Diffusion Models","created":"2022-10-06","cited_by_count":725},{"id":"1906.08172","title":"MediaPipe: A Framework for Building Perception Pipelines","created":"2019-06-14","cited_by_count":583},{"id":"1804.06208","title":"Simple Baselines for Human Pose Estimation and Tracking","created":"2018-04-17","cited_by_count":502},{"id":"2008.11200","title":"GRAB: A Dataset of Whole-Body Human Grasping of Objects","created":"2020-08-25","cited_by_count":405},{"id":"2203.08679","title":"Decoupled Knowledge Distillation","created":"2022-03-16","cited_by_count":388},{"id":"2204.13662","title":"ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation","created":"2022-04-28","cited_by_count":312},{"id":"1312.4659","title":"DeepPose: Human Pose Estimation via Deep Neural Networks","created":"2013-12-17","cited_by_count":305},{"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":"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":"2306.16940","title":"BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion","created":"2023-06-29","cited_by_count":236},{"id":"2307.00818","title":"Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset","created":"2023-07-03","cited_by_count":227},{"id":"1611.05424","title":"Associative Embedding: End-to-End Learning for Joint Detection and Grouping","created":"2016-11-16","cited_by_count":212},{"id":"2205.10536","title":"Knowledge Distillation from A Stronger Teacher","created":"2022-05-21","cited_by_count":208},{"id":"2301.12900","title":"DepGraph: Towards Any Structural Pruning","created":"2023-01-30","cited_by_count":203},{"id":"2211.03375","title":"AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time","created":"2022-11-07","cited_by_count":200},{"id":"2212.04420","title":"Generating Holistic 3D Human Motion from Speech","created":"2022-12-08","cited_by_count":180},{"id":"2007.11858","title":"Whole-Body Human Pose Estimation in the Wild","created":"2020-07-23","cited_by_count":178},{"id":"2203.05297","title":"BEAT: A Large-Scale Semantic and Emotional Multi-Modal Dataset for Conversational Gestures Synthesis","created":"2022-03-10","cited_by_count":178},{"id":"2303.07399","title":"RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose","created":"2023-03-13","cited_by_count":175},{"id":"2011.13256","title":"Channel-wise Knowledge Distillation for Dense Prediction","created":"2020-11-26","cited_by_count":163},{"id":"2006.10214","title":"MediaPipe Hands: On-device Real-time Hand Tracking","created":"2020-06-18","cited_by_count":161},{"id":"2111.11837","title":"Focal and Global Knowledge Distillation for Detectors","created":"2021-11-23","cited_by_count":142},{"id":"2303.16160","title":"One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer","created":"2023-03-28","cited_by_count":130},{"id":"2102.00650","title":"Rethinking Soft Labels for Knowledge Distillation: A Bias-Variance Tradeoff Perspective","created":"2021-02-01","cited_by_count":119},{"id":"2205.01529","title":"Masked Generative Distillation","created":"2022-05-03","cited_by_count":107},{"id":"2304.04269","title":"HumanSD: A Native Skeleton-Guided Diffusion Model for Human Image Generation","created":"2023-04-09","cited_by_count":105},{"id":"2204.08680","title":"Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer","created":"2022-04-19","cited_by_count":101},{"id":"2305.04789","title":"AvatarReX: Real-time Expressive Full-body Avatars","created":"2023-05-08","cited_by_count":84},{"id":"2011.11534","title":"Accurate 3D Hand Pose Estimation for Whole-Body 3D Human Mesh Estimation","created":"2020-11-23","cited_by_count":81},{"id":"2305.18247","title":"TaleCrafter: Interactive Story Visualization with Multiple Characters","created":"2023-05-29","cited_by_count":73},{"id":"2303.13005","title":"From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and Customized Soft Labels","created":"2023-03-23","cited_by_count":69},{"id":"2107.03332","title":"SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimation","created":"2021-07-07","cited_by_count":68},{"id":"2211.09386","title":"BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object Detection","created":"2022-11-17","cited_by_count":66},{"id":"1805.05563","title":"Facial Landmark Detection: a Literature Survey","created":"2018-05-15","cited_by_count":63},{"id":"2108.02092","title":"Online Knowledge Distillation for Efficient Pose Estimation","created":"2021-08-04","cited_by_count":55},{"id":"2302.01593","title":"Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimation","created":"2023-02-03","cited_by_count":48},{"id":"2206.06067","title":"Better Teacher Better Student: Dynamic Prior Knowledge for Knowledge Distillation","created":"2022-06-13","cited_by_count":41},{"id":"2211.15444","title":"DAMO-YOLO : A Report on Real-Time Object Detection Design","created":"2022-11-23","cited_by_count":38},{"id":"2006.13108","title":"Distilling Object Detectors with Task Adaptive Regularization","created":"2020-06-23","cited_by_count":36},{"id":"2209.02432","title":"ViTKD: Practical Guidelines for ViT feature knowledge distillation","created":"2022-09-06","cited_by_count":34},{"id":"2208.10808","title":"Towards Accurate Facial Landmark Detection via Cascaded Transformers","created":"2022-08-23","cited_by_count":31},{"id":"1908.09216","title":"Dynamic Kernel Distillation for Efficient Pose Estimation in Videos","created":"2019-08-24","cited_by_count":30},{"id":"2008.09457","title":"DOPE: Distillation Of Part Experts for whole-body 3D pose estimation in the wild","created":"2020-08-21","cited_by_count":25},{"id":"1909.13423","title":"Single-Network Whole-Body Pose Estimation","created":"2019-09-30","cited_by_count":24},{"id":"2208.11547","title":"ZoomNAS: Searching for Whole-body Human Pose Estimation in the Wild","created":"2022-08-23","cited_by_count":23},{"id":"2305.10727","title":"Boost Vision Transformer with GPU-Friendly Sparsity and Quantization","created":"2023-05-18","cited_by_count":20},{"id":"2302.14771","title":"Generic-to-Specific Distillation of Masked Autoencoders","created":"2023-02-28","cited_by_count":19},{"id":"2202.13393","title":"TransKD: Transformer Knowledge Distillation for Efficient Semantic Segmentation","created":"2022-02-27","cited_by_count":17},{"id":"2304.10482","title":"Reconstructing Signing Avatars From Video Using Linguistic Priors","created":"2023-04-20","cited_by_count":12},{"id":"2208.10139","title":"Rethinking Knowledge Distillation via Cross-Entropy","created":"2022-08-22","cited_by_count":9},{"id":"1903.01013","title":"Hand Pose Estimation: A Survey","created":"2019-03-03","cited_by_count":8},{"id":"2305.19412","title":"Are Large Kernels Better Teachers than Transformers for ConvNets?","created":"2023-05-30","cited_by_count":8}],"next_cursor":null}