{"list":"other","total":95,"rows":[{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"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":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"1801.07829","title":"Dynamic Graph CNN for Learning on Point Clouds","created":"2018-01-24","cited_by_count":2223},{"id":"1409.7495","title":"Unsupervised Domain Adaptation by Backpropagation","created":"2014-09-26","cited_by_count":1917},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"2103.03230","title":"Barlow Twins: Self-Supervised Learning via Redundancy Reduction","created":"2021-03-04","cited_by_count":1838},{"id":"1803.07728","title":"Unsupervised Representation Learning by Predicting Image Rotations","created":"2018-03-21","cited_by_count":1591},{"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":"1801.07455","title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2018-01-23","cited_by_count":1209},{"id":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"2105.04906","title":"VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning","created":"2021-05-11","cited_by_count":1057},{"id":"2301.08243","title":"Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture","created":"2023-01-19","cited_by_count":1039},{"id":"1807.05520","title":"Deep Clustering for Unsupervised Learning of Visual Features","created":"2018-07-15","cited_by_count":1028},{"id":"2309.16588","title":"Vision Transformers Need Registers","created":"2023-09-28","cited_by_count":871},{"id":"2005.10243","title":"What Makes for Good Views for Contrastive Learning?","created":"2020-05-20","cited_by_count":846},{"id":"1604.02808","title":"NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis","created":"2016-04-11","cited_by_count":686},{"id":"2005.04966","title":"Prototypical Contrastive Learning of Unsupervised Representations","created":"2020-05-11","cited_by_count":640},{"id":"2010.04592","title":"Contrastive Learning with Hard Negative Samples","created":"2020-10-09","cited_by_count":628},{"id":"1905.04757","title":"NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding","created":"2019-05-12","cited_by_count":533},{"id":"2404.08471","title":"Revisiting Feature Prediction for Learning Visual Representations from Video","created":"2024-02-15","cited_by_count":531},{"id":"2110.09348","title":"Understanding Dimensional Collapse in Contrastive Self-supervised Learning","created":"2021-10-18","cited_by_count":378},{"id":"2107.12213","title":"Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition","created":"2021-07-26","cited_by_count":322},{"id":"2106.09696","title":"BABEL: Bodies, Action and Behavior with English Labels","created":"2021-06-17","cited_by_count":265},{"id":"1708.01246","title":"Unsupervised Representation Learning by Sorting Sequences","created":"2017-08-03","cited_by_count":221},{"id":"2305.00976","title":"TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis","created":"2023-05-02","cited_by_count":198},{"id":"2210.06551","title":"MotionBERT: A Unified Perspective on Learning Human Motion Representations","created":"2022-10-12","cited_by_count":193},{"id":"2302.02318","title":"Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining","created":"2023-02-05","cited_by_count":164},{"id":"1405.2941","title":"Cross-view Action Modeling, Learning and Recognition","created":"2014-05-12","cited_by_count":134},{"id":"2011.11765","title":"Boosting Contrastive Self-Supervised Learning with False Negative Cancellation","created":"2020-11-23","cited_by_count":119},{"id":"2104.14466","title":"3D Human Action Representation Learning via Cross-View Consistency Pursuit","created":"2021-04-29","cited_by_count":106},{"id":"2006.10645","title":"Online Deep Clustering for Unsupervised Representation Learning","created":"2020-06-18","cited_by_count":100},{"id":"2104.00946","title":"UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehicles","created":"2021-04-02","cited_by_count":96},{"id":"2010.05599","title":"MS$^2$L: Multi-Task Self-Supervised Learning for Skeleton Based Action Recognition","created":"2020-10-12","cited_by_count":92},{"id":"1911.12409","title":"PREDICT & CLUSTER: Unsupervised Skeleton Based Action Recognition","created":"2019-11-27","cited_by_count":91},{"id":"2112.03590","title":"Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognition","created":"2021-12-07","cited_by_count":90},{"id":"2210.08344","title":"How Mask Matters: Towards Theoretical Understandings of Masked Autoencoders","created":"2022-10-15","cited_by_count":86},{"id":"2208.10741","title":"Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2022-08-23","cited_by_count":85},{"id":"2109.08685","title":"Self-supervised learning methods and applications in medical imaging analysis: A survey","created":"2021-09-17","cited_by_count":77},{"id":"2108.03656","title":"Skeleton-Contrastive 3D Action Representation Learning","created":"2021-08-08","cited_by_count":76},{"id":"2206.07706","title":"Masked Frequency Modeling for Self-Supervised Visual Pre-Training","created":"2022-06-15","cited_by_count":71},{"id":"2303.03729","title":"Learning Discriminative Representations for Skeleton Based Action Recognition","created":"2023-03-07","cited_by_count":62},{"id":"2008.00188","title":"Augmented Skeleton Based Contrastive Action Learning with Momentum LSTM for Unsupervised Action Recognition","created":"2020-08-01","cited_by_count":60},{"id":"2108.01959","title":"Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learning","created":"2021-08-04","cited_by_count":58},{"id":"2106.03719","title":"Incremental False Negative Detection for Contrastive Learning","created":"2021-06-07","cited_by_count":48},{"id":"2303.06242","title":"HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations","created":"2023-03-10","cited_by_count":44},{"id":"2010.14982","title":"Toyota Smarthome Untrimmed: Real-World Untrimmed Videos for Activity Detection","created":"2020-10-28","cited_by_count":42},{"id":"2303.10904","title":"Actionlet-Dependent Contrastive Learning for Unsupervised Skeleton-Based Action Recognition","created":"2023-03-20","cited_by_count":42},{"id":"2307.08476","title":"SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-training","created":"2023-07-17","cited_by_count":41},{"id":"2308.07092","title":"Masked Motion Predictors are Strong 3D Action Representation Learners","created":"2023-08-14","cited_by_count":41},{"id":"2208.12448","title":"CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual Distillation","created":"2022-08-26","cited_by_count":38},{"id":"2008.11702","title":"Delving into Inter-Image Invariance for Unsupervised Visual Representations","created":"2020-08-26","cited_by_count":37},{"id":"1712.00108","title":"Graph Distillation for Action Detection with Privileged Modalities","created":"2017-11-30","cited_by_count":35},{"id":"2208.03497","title":"Contrastive Positive Mining for Unsupervised 3D Action Representation Learning","created":"2022-08-06","cited_by_count":34},{"id":"2207.06101","title":"Global-local Motion Transformer for Unsupervised Skeleton-based Action Learning","created":"2022-07-13","cited_by_count":33},{"id":"1809.01844","title":"Unsupervised Learning of View-invariant Action Representations","created":"2018-09-06","cited_by_count":32},{"id":"2007.07053","title":"Unsupervised 3D Human Pose Representation with Viewpoint and Pose Disentanglement","created":"2020-07-14","cited_by_count":32},{"id":"2211.13466","title":"Hierarchical Consistent Contrastive Learning for Skeleton-Based Action Recognition with Growing Augmentations","created":"2022-11-24","cited_by_count":31},{"id":"2203.01593","title":"3D Human Motion Prediction: A Survey","created":"2022-03-03","cited_by_count":30},{"id":"2207.09644","title":"Hierarchically Self-Supervised Transformer for Human Skeleton Representation Learning","created":"2022-07-20","cited_by_count":30},{"id":"2212.02082","title":"Hierarchical Contrast for Unsupervised Skeleton-based Action Representation Learning","created":"2022-12-05","cited_by_count":30},{"id":"2209.02399","title":"SkeletonMAE: Spatial-Temporal Masked Autoencoders for Self-supervised Skeleton Action Recognition","created":"2022-09-01","cited_by_count":29},{"id":"1409.6813","title":"Histogram of Oriented Principal Components for Cross-View Action Recognition","created":"2014-09-24","cited_by_count":27},{"id":"2011.07236","title":"Prototypical Contrast and Reverse Prediction: Unsupervised Skeleton Based Action Recognition","created":"2020-11-14","cited_by_count":25},{"id":"2302.09018","title":"Self-supervised Action Representation Learning from Partial Spatio-Temporal Skeleton Sequences","created":"2023-02-17","cited_by_count":25},{"id":"2304.00387","title":"HaLP: Hallucinating Latent Positives for Skeleton-based Self-Supervised Learning of Actions","created":"2023-04-01","cited_by_count":25},{"id":"2209.00065","title":"ViA: View-invariant Skeleton Action Representation Learning via Motion Retargeting","created":"2022-08-31","cited_by_count":22},{"id":"2405.04771","title":"Exploring Vision Transformers for 3D Human Motion-Language Models with Motion Patches","created":"2024-05-08","cited_by_count":22},{"id":"2007.03263","title":"Decoupled Spatial-Temporal Attention Network for Skeleton-Based Action Recognition","created":"2020-07-07","cited_by_count":21},{"id":"2305.00666","title":"Part Aware Contrastive Learning for Self-Supervised Action Recognition","created":"2023-05-01","cited_by_count":21},{"id":"2311.03106","title":"Unified Multi-modal Unsupervised Representation Learning for Skeleton-based Action Understanding","created":"2023-11-06","cited_by_count":20},{"id":"2111.11051","title":"Contrast-reconstruction Representation Learning for Self-supervised Skeleton-based Action Recognition","created":"2021-11-22","cited_by_count":19},{"id":"2207.09176","title":"Self-Supervision Can Be a Good Few-Shot Learner","created":"2022-07-19","cited_by_count":19},{"id":"2308.03975","title":"Prompted Contrast with Masked Motion Modeling: Towards Versatile 3D Action Representation Learning","created":"2023-08-08","cited_by_count":19},{"id":"2207.03065","title":"Contrastive Learning from Spatio-Temporal Mixed Skeleton Sequences for Self-Supervised Skeleton-Based Action Recognition","created":"2022-07-07","cited_by_count":17},{"id":"2110.00529","title":"Unsupervised Motion Representation Learning with Capsule Autoencoders","created":"2021-10-01","cited_by_count":16},{"id":"2304.08799","title":"Self-Supervised 3D Action Representation Learning with Skeleton Cloud Colorization","created":"2023-04-18","cited_by_count":16},{"id":"2308.14500","title":"LAC: Latent Action Composition for Skeleton-based Action Segmentation","created":"2023-08-28","cited_by_count":15},{"id":"2002.11669","title":"Pedestrian Models for Autonomous Driving Part I: Low-Level Models, from Sensing to Tracking","created":"2020-02-26","cited_by_count":13},{"id":"1905.06774","title":"Richly Activated Graph Convolutional Network for Action Recognition with Incomplete Skeletons","created":"2019-05-16","cited_by_count":12},{"id":"2303.05475","title":"Mimic before Reconstruct: Enhancing Masked Autoencoders with Feature Mimicking","created":"2023-03-09","cited_by_count":12},{"id":"2110.13555","title":"Directional Self-supervised Learning for Heavy Image Augmentations","created":"2021-10-26","cited_by_count":11},{"id":"2303.12670","title":"Correlational Image Modeling for Self-Supervised Visual Pre-Training","created":"2023-03-22","cited_by_count":11},{"id":"2310.18737","title":"Pre-training with Random Orthogonal Projection Image Modeling","created":"2023-10-28","cited_by_count":11},{"id":"2204.10312","title":"Unsupervised Human Action Recognition with Skeletal Graph Laplacian and Self-Supervised Viewpoints Invariance","created":"2022-04-21","cited_by_count":10},{"id":"2307.12917","title":"Hierarchical Skeleton Meta-Prototype Contrastive Learning with Hard Skeleton Mining for Unsupervised Person Re-Identification","created":"2023-07-24","cited_by_count":9},{"id":"2304.00858","title":"Focalized Contrastive View-invariant Learning for Self-supervised Skeleton-based Action Recognition","created":"2023-04-03","cited_by_count":6},{"id":"2209.11634","title":"View-Invariant Skeleton-based Action Recognition via Global-Local Contrastive Learning","created":"2022-09-23","cited_by_count":1}],"next_cursor":null}