{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"2108.01073","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","created":"2021-08-02","cited_by_count":1937},{"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":"1604.02808","title":"NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis","created":"2016-04-11","cited_by_count":686},{"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":"2111.15640","title":"Diffusion Autoencoders: Toward a Meaningful and Decodable Representation","created":"2021-11-30","cited_by_count":449},{"id":"2103.03404","title":"Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth","created":"2021-03-05","cited_by_count":419},{"id":"2210.06551","title":"MotionBERT: A Unified Perspective on Learning Human Motion Representations","created":"2022-10-12","cited_by_count":193},{"id":"2104.14466","title":"3D Human Action Representation Learning via Cross-View Consistency Pursuit","created":"2021-04-29","cited_by_count":106},{"id":"2211.16940","title":"DiffPose: Toward More Reliable 3D Pose Estimation","created":"2022-11-30","cited_by_count":100},{"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":"2302.03665","title":"HumanMAC: Masked Motion Completion for Human Motion Prediction","created":"2023-02-07","cited_by_count":81},{"id":"2311.17901","title":"SODA: Bottleneck Diffusion Models for Representation Learning","created":"2023-11-29","cited_by_count":77},{"id":"2108.03656","title":"Skeleton-Contrastive 3D Action Representation Learning","created":"2021-08-08","cited_by_count":76},{"id":"2304.09355","title":"To Compress or Not to Compress- Self-Supervised Learning and Information Theory: A Review","created":"2023-04-19","cited_by_count":72},{"id":"2203.07004","title":"Rethinking Minimal Sufficient Representation in Contrastive Learning","created":"2022-03-14","cited_by_count":69},{"id":"2004.14941","title":"The Information Bottleneck Problem and Its Applications in Machine Learning","created":"2020-04-30","cited_by_count":66},{"id":"2008.09864","title":"Tackling Over-Smoothing for General Graph Convolutional Networks","created":"2020-08-22","cited_by_count":66},{"id":"2211.13976","title":"Expanding Small-Scale Datasets with Guided Imagination","created":"2022-11-25","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":"2303.02936","title":"UniHCP: A Unified Model for Human-Centric Perceptions","created":"2023-03-06","cited_by_count":59},{"id":"2212.08641","title":"GFPose: Learning 3D Human Pose Prior with Gradient Fields","created":"2022-12-16","cited_by_count":57},{"id":"2212.12990","title":"Unsupervised Representation Learning from Pre-trained Diffusion Probabilistic Models","created":"2022-12-26","cited_by_count":54},{"id":"2401.11739","title":"EmerDiff: Emerging Pixel-level Semantic Knowledge in Diffusion Models","created":"2024-01-22","cited_by_count":43},{"id":"2303.10904","title":"Actionlet-Dependent Contrastive Learning for Unsupervised Skeleton-Based Action Recognition","created":"2023-03-20","cited_by_count":42},{"id":"2307.07205","title":"Multimodal Motion Conditioned Diffusion Model for Skeleton-based Video Anomaly Detection","created":"2023-07-14","cited_by_count":42},{"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":"2310.10402","title":"Real-Fake: Effective Training Data Synthesis Through Distribution Matching","created":"2023-10-16","cited_by_count":36},{"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":"2207.09644","title":"Hierarchically Self-Supervised Transformer for Human Skeleton Representation Learning","created":"2022-07-20","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":"2312.03703","title":"Skeleton-in-Context: Unified Skeleton Sequence Modeling with In-Context Learning","created":"2023-12-06","cited_by_count":27},{"id":"2305.19094","title":"Diffusion Model for Dense Matching","created":"2023-05-30","cited_by_count":21},{"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":"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":"2211.09013","title":"Masked Reconstruction Contrastive Learning with Information Bottleneck Principle","created":"2022-11-15","cited_by_count":2}],"next_cursor":null}