{"list":"other","total":55,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2003.00196","title":"First Order Motion Model for Image Animation","created":"2020-02-29","cited_by_count":704},{"id":"2204.11918","title":"Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Items","created":"2022-04-25","cited_by_count":612},{"id":"2112.03126","title":"Label-Efficient Semantic Segmentation with Diffusion Models","created":"2021-12-06","cited_by_count":499},{"id":"2306.03881","title":"Emergent Correspondence from Image Diffusion","created":"2023-06-06","cited_by_count":446},{"id":"1705.03098","title":"A simple yet effective baseline for 3d human pose estimation","created":"2017-05-08","cited_by_count":401},{"id":"2303.04803","title":"Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models","created":"2023-03-08","cited_by_count":375},{"id":"2305.15347","title":"A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence","created":"2023-05-24","cited_by_count":301},{"id":"1711.08229","title":"Integral Human Pose Regression","created":"2017-11-22","cited_by_count":256},{"id":"2305.14334","title":"Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence","created":"2023-05-23","cited_by_count":214},{"id":"1812.08861","title":"Animating Arbitrary Objects via Deep Motion Transfer","created":"2018-12-20","cited_by_count":208},{"id":"1905.05754","title":"Learnable Triangulation of Human Pose","created":"2019-05-14","cited_by_count":161},{"id":"2108.12617","title":"AP-10K: A Benchmark for Animal Pose Estimation in the Wild","created":"2021-08-28","cited_by_count":123},{"id":"2305.15581","title":"Unsupervised Semantic Correspondence Using Stable Diffusion","created":"2023-05-24","cited_by_count":120},{"id":"1704.02447","title":"Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach","created":"2017-04-08","cited_by_count":115},{"id":"1806.07823","title":"Unsupervised Learning of Object Landmarks through Conditional Image Generation","created":"2018-06-20","cited_by_count":114},{"id":"1906.11883","title":"Unsupervised Learning of Object Keypoints for Perception and Control","created":"2019-06-19","cited_by_count":109},{"id":"1711.07399","title":"V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map","created":"2017-11-20","cited_by_count":102},{"id":"1905.01298","title":"SCOPS: Self-Supervised Co-Part Segmentation","created":"2019-05-03","cited_by_count":100},{"id":"1903.02330","title":"Self-Supervised Learning of 3D Human Pose using Multi-view Geometry","created":"2019-03-06","cited_by_count":98},{"id":"1904.04812","title":"Unsupervised 3D Pose Estimation with Geometric Self-Supervision","created":"2019-04-09","cited_by_count":95},{"id":"2308.10916","title":"Diffusion Model as Representation Learner","created":"2023-08-21","cited_by_count":95},{"id":"1906.07889","title":"Unsupervised Learning of Object Structure and Dynamics from Videos","created":"2019-06-19","cited_by_count":92},{"id":"1902.09868","title":"RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimation","created":"2019-02-26","cited_by_count":85},{"id":"1807.03146","title":"Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning","created":"2018-07-05","cited_by_count":79},{"id":"1804.04412","title":"Unsupervised Discovery of Object Landmarks as Structural Representations","created":"2018-04-12","cited_by_count":73},{"id":"1903.06946","title":"Unsupervised Part-Based Disentangling of Object Shape and Appearance","created":"2019-03-16","cited_by_count":67},{"id":"2003.07581","title":"Weakly-Supervised 3D Human Pose Learning via Multi-view Images in the Wild","created":"2020-03-17","cited_by_count":66},{"id":"2011.14679","title":"CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the Wild","created":"2020-11-30","cited_by_count":65},{"id":"1705.02193","title":"Unsupervised learning of object landmarks by factorized spatial embeddings","created":"2017-05-05","cited_by_count":64},{"id":"2111.06349","title":"Unsupervised Part Discovery from Contrastive Reconstruction","created":"2021-11-11","cited_by_count":57},{"id":"1704.04793","title":"Harvesting Multiple Views for Marker-less 3D Human Pose Annotations","created":"2017-04-16","cited_by_count":48},{"id":"1808.07182","title":"Can 3D Pose be Learned from 2D Projections Alone?","created":"2018-08-22","cited_by_count":44},{"id":"2004.04400","title":"Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image Synthesis","created":"2020-04-09","cited_by_count":44},{"id":"2401.11739","title":"EmerDiff: Emerging Pixel-level Semantic Knowledge in Diffusion Models","created":"2024-01-22","cited_by_count":43},{"id":"1910.02027","title":"Unsupervised Keypoint Learning for Guiding Class-Conditional Video Prediction","created":"2019-10-04","cited_by_count":36},{"id":"2401.11430","title":"Exploring Diffusion Time-steps for Unsupervised Representation Learning","created":"2024-01-21","cited_by_count":36},{"id":"2112.07088","title":"ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera Elevation and Learning Normalizing Flows on 2D Poses","created":"2021-12-14","cited_by_count":35},{"id":"1608.03075","title":"3D Human Pose Estimation Using Convolutional Neural Networks with 2D Pose Information","created":"2016-08-10","cited_by_count":28},{"id":"2004.03234","title":"Motion-supervised Co-Part Segmentation","created":"2020-04-07","cited_by_count":28},{"id":"2006.14107","title":"Kinematic-Structure-Preserved Representation for Unsupervised 3D Human Pose Estimation","created":"2020-06-24","cited_by_count":26},{"id":"2112.05121","title":"Self-Supervised Keypoint Discovery in Behavioral Videos","created":"2021-12-09","cited_by_count":23},{"id":"2112.01036","title":"GANSeg: Learning to Segment by Unsupervised Hierarchical Image Generation","created":"2021-12-02","cited_by_count":19},{"id":"2311.10983","title":"Multiple View Geometry Transformers for 3D Human Pose Estimation","created":"2023-11-18","cited_by_count":19},{"id":"2403.14554","title":"Gaussian Frosting: Editable Complex Radiance Fields with Real-Time Rendering","created":"2024-03-21","cited_by_count":19},{"id":"2205.10636","title":"AutoLink: Self-supervised Learning of Human Skeletons and Object Outlines by Linking Keypoints","created":"2022-05-21","cited_by_count":17},{"id":"2312.00065","title":"Unsupervised Keypoints from Pretrained Diffusion Models","created":"2023-11-29","cited_by_count":15},{"id":"2108.04869","title":"MetaPose: Fast 3D Pose from Multiple Views without 3D Supervision","created":"2021-08-10","cited_by_count":12},{"id":"2212.07401","title":"BKinD-3D: Self-Supervised 3D Keypoint Discovery from Multi-View Videos","created":"2022-12-14","cited_by_count":10},{"id":"2304.02349","title":"Self-supervised 3D Human Pose Estimation from a Single Image","created":"2023-04-05","cited_by_count":8},{"id":"2211.12829","title":"Unsupervised 3D Keypoint Discovery with Multi-View Geometry","created":"2022-11-23","cited_by_count":2},{"id":"2312.07051","title":"Mask as Supervision: Leveraging Unified Mask Information for Unsupervised 3D Pose Estimation","created":"2023-12-12","cited_by_count":2}],"next_cursor":null}