{"list":"other","total":57,"rows":[{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"1702.03118","title":"Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning","created":"2017-02-10","cited_by_count":950},{"id":"1806.10574","title":"This Looks Like That: Deep Learning for Interpretable Image Recognition","created":"2018-06-27","cited_by_count":737},{"id":"1804.06208","title":"Simple Baselines for Human Pose Estimation and Tracking","created":"2018-04-17","cited_by_count":502},{"id":"2104.08527","title":"PARE: Part Attention Regressor for 3D Human Body Estimation","created":"2021-04-17","cited_by_count":337},{"id":"2105.04668","title":"HuMoR: 3D Human Motion Model for Robust Pose Estimation","created":"2021-05-10","cited_by_count":324},{"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":"2203.12575","title":"NeuMan: Neural Human Radiance Field from a Single Video","created":"2022-03-23","cited_by_count":244},{"id":"2408.12569","title":"Sapiens: Foundation for Human Vision Models","created":"2024-08-22","cited_by_count":229},{"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":"2008.12272","title":"Monocular, One-stage, Regression of Multiple 3D People","created":"2020-08-27","cited_by_count":218},{"id":"1710.10000","title":"PoseTrack: A Benchmark for Human Pose Estimation and Tracking","created":"2017-10-27","cited_by_count":173},{"id":"2110.09408","title":"HRFormer: High-Resolution Transformer for Dense Prediction","created":"2021-10-18","cited_by_count":149},{"id":"2112.08274","title":"Putting People in their Place: Monocular Regression of 3D People in Depth","created":"2021-12-15","cited_by_count":142},{"id":"2203.15102","title":"Rethinking Semantic Segmentation: A Prototype View","created":"2022-03-28","cited_by_count":140},{"id":"2103.17265","title":"Human POSEitioning System (HPS): 3D Human Pose Estimation and Self-localization in Large Scenes from Body-Mounted Sensors","created":"2021-03-31","cited_by_count":137},{"id":"2102.13086","title":"Simple multi-dataset detection","created":"2021-02-25","cited_by_count":127},{"id":"2108.12617","title":"AP-10K: A Benchmark for Animal Pose Estimation in the Wild","created":"2021-08-28","cited_by_count":123},{"id":"2112.13762","title":"MSeg: A Composite Dataset for Multi-domain Semantic Segmentation","created":"2021-12-27","cited_by_count":122},{"id":"2111.15000","title":"Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypes","created":"2021-11-29","cited_by_count":120},{"id":"1803.10683","title":"Pose2Seg: Detection Free Human Instance Segmentation","created":"2018-03-28","cited_by_count":107},{"id":"1905.06549","title":"TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning","created":"2019-05-16","cited_by_count":91},{"id":"1904.04402","title":"Towards Universal Object Detection by Domain Attention","created":"2019-04-09","cited_by_count":89},{"id":"2407.21686","title":"Expressive Whole-Body 3D Gaussian Avatar","created":"2024-07-31","cited_by_count":89},{"id":"2110.07110","title":"Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrast","created":"2021-10-14","cited_by_count":85},{"id":"1907.10045","title":"xR-EgoPose: Egocentric 3D Human Pose from an HMD Camera","created":"2019-07-23","cited_by_count":79},{"id":"1711.06475","title":"AI Challenger : A Large-scale Dataset for Going Deeper in Image Understanding","created":"2017-11-17","cited_by_count":73},{"id":"2107.03332","title":"SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimation","created":"2021-07-07","cited_by_count":68},{"id":"2008.06614","title":"Object Detection with a Unified Label Space from Multiple Datasets","created":"2020-08-15","cited_by_count":65},{"id":"2104.07300","title":"Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenes","created":"2021-04-15","cited_by_count":65},{"id":"2212.04246","title":"ViTPose++: Vision Transformer for Generic Body Pose Estimation","created":"2022-12-07","cited_by_count":65},{"id":"2011.11232","title":"NeuralAnnot: Neural Annotator for 3D Human Mesh Training Sets","created":"2020-11-23","cited_by_count":62},{"id":"2107.02156","title":"Do Different Tracking Tasks Require Different Appearance Models?","created":"2021-07-05","cited_by_count":62},{"id":"2303.02936","title":"UniHCP: A Unified Model for Human-Centric Perceptions","created":"2023-03-06","cited_by_count":59},{"id":"2206.05683","title":"APT-36K: A Large-scale Benchmark for Animal Pose Estimation and Tracking","created":"2022-06-12","cited_by_count":56},{"id":"2009.04960","title":"Prototype Completion with Primitive Knowledge for Few-Shot Learning","created":"2020-09-10","cited_by_count":50},{"id":"2212.14474","title":"Learning 3D Human Pose Estimation from Dozens of Datasets using a Geometry-Aware Autoencoder to Bridge Between Skeleton Formats","created":"2022-12-29","cited_by_count":50},{"id":"2303.11638","title":"Human Pose as Compositional Tokens","created":"2023-03-21","cited_by_count":45},{"id":"2303.06880","title":"Uni3D: A Unified Baseline for Multi-dataset 3D Object Detection","created":"2023-03-13","cited_by_count":39},{"id":"2301.04011","title":"Learning Support and Trivial Prototypes for Interpretable Image Classification","created":"2023-01-08","cited_by_count":38},{"id":"2310.14729","title":"MAS: Multi-view Ancestral Sampling for 3D motion generation using 2D diffusion","created":"2023-10-23","cited_by_count":37},{"id":"2207.10387","title":"Pose for Everything: Towards Category-Agnostic Pose Estimation","created":"2022-07-21","cited_by_count":36},{"id":"2107.08580","title":"UNIK: A Unified Framework for Real-world Skeleton-based Action Recognition","created":"2021-07-19","cited_by_count":35},{"id":"2203.08547","title":"Non-isotropy Regularization for Proxy-based Deep Metric Learning","created":"2022-03-16","cited_by_count":33},{"id":"2211.03889","title":"Common Pets in 3D: Dynamic New-View Synthesis of Real-Life Deformable Categories","created":"2022-11-07","cited_by_count":29},{"id":"2210.11940","title":"JRDB-Pose: A Large-scale Dataset for Multi-Person Pose Estimation and Tracking","created":"2022-10-20","cited_by_count":25},{"id":"2002.07417","title":"Universal-RCNN: Universal Object Detector via Transferable Graph R-CNN","created":"2020-02-18","cited_by_count":18},{"id":"2311.17891","title":"A Graph-Based Approach for Category-Agnostic Pose Estimation","created":"2023-11-29","cited_by_count":17},{"id":"2306.04849","title":"ScaleDet: A Scalable Multi-Dataset Object Detector","created":"2023-06-08","cited_by_count":16},{"id":"2303.06819","title":"TranSG: Transformer-Based Skeleton Graph Prototype Contrastive Learning with Structure-Trajectory Prompted Reconstruction for Person Re-Identification","created":"2023-03-13","cited_by_count":14},{"id":"2404.01686","title":"JRDB-PanoTrack: An Open-world Panoptic Segmentation and Tracking Robotic Dataset in Crowded Human Environments","created":"2024-04-02","cited_by_count":11},{"id":"2304.04875","title":"Three Recipes for Better 3D Pseudo-GTs of 3D Human Mesh Estimation in the Wild","created":"2023-04-10","cited_by_count":9},{"id":"1707.07608","title":"Vision-Based Fallen Person Detection for the Elderly","created":"2017-07-24","cited_by_count":5},{"id":"2405.19833","title":"KITRO: Refining Human Mesh by 2D Clues and Kinematic-tree Rotation","created":"2024-05-30","cited_by_count":5},{"id":"2406.04999","title":"ProMotion: Prototypes As Motion Learners","created":"2024-06-07","cited_by_count":5}],"next_cursor":null}