{"list":"other","total":56,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"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":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"id":"1904.03278","title":"AMASS: Archive of Motion Capture as Surface Shapes","created":"2019-04-05","cited_by_count":1236},{"id":"1801.07455","title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2018-01-23","cited_by_count":1209},{"id":"1807.05520","title":"Deep Clustering for Unsupervised Learning of Visual Features","created":"2018-07-15","cited_by_count":1028},{"id":"2104.10157","title":"VideoGPT: Video Generation using VQ-VAE and Transformers","created":"2021-04-20","cited_by_count":658},{"id":"2005.00341","title":"Jukebox: A Generative Model for Music","created":"2020-04-30","cited_by_count":542},{"id":"1611.05267","title":"Temporal Convolutional Networks for Action Segmentation and Detection","created":"2016-11-16","cited_by_count":508},{"id":"2205.09113","title":"Masked Autoencoders As Spatiotemporal Learners","created":"2022-05-18","cited_by_count":429},{"id":"1903.01945","title":"MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation","created":"2019-03-05","cited_by_count":373},{"id":"2106.09696","title":"BABEL: Bodies, Action and Behavior with English Labels","created":"2021-06-17","cited_by_count":265},{"id":"1506.09215","title":"Unsupervised Learning from Narrated Instruction Videos","created":"2015-06-30","cited_by_count":116},{"id":"2104.14466","title":"3D Human Action Representation Learning via Cross-View Consistency Pursuit","created":"2021-04-29","cited_by_count":106},{"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":"2210.10352","title":"Temporal Action Segmentation: An Analysis of Modern Techniques","created":"2022-10-19","cited_by_count":85},{"id":"1904.04189","title":"Unsupervised learning of action classes with continuous temporal embedding","created":"2019-04-08","cited_by_count":76},{"id":"2412.04445","title":"Moto: Latent Motion Token as the Bridging Language for Learning Robot Manipulation from Videos","created":"2024-12-05","cited_by_count":69},{"id":"1803.09490","title":"Unsupervised Learning and Segmentation of Complex Activities from Video","created":"2018-03-26","cited_by_count":61},{"id":"2105.13353","title":"Unsupervised Action Segmentation by Joint Representation Learning and Online Clustering","created":"2021-05-27","cited_by_count":49},{"id":"2001.11122","title":"Joint Visual-Temporal Embedding for Unsupervised Learning of Actions in Untrimmed Sequences","created":"2020-01-29","cited_by_count":45},{"id":"2303.10904","title":"Actionlet-Dependent Contrastive Learning for Unsupervised Skeleton-Based Action Recognition","created":"2023-03-20","cited_by_count":42},{"id":"2404.01518","title":"Temporally Consistent Unbalanced Optimal Transport for Unsupervised Action Segmentation","created":"2024-04-01","cited_by_count":38},{"id":"1906.01028","title":"A Hybrid RNN-HMM Approach for Weakly Supervised Temporal Action Segmentation","created":"2019-06-03","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":"2104.02116","title":"Action Shuffle Alternating Learning for Unsupervised Action Segmentation","created":"2021-04-05","cited_by_count":33},{"id":"1506.08438","title":"Unsupervised Semantic Parsing of Video Collections","created":"2015-06-28","cited_by_count":26},{"id":"2202.01727","title":"Skeleton-Based Action Segmentation with Multi-Stage Spatial-Temporal Graph Convolutional Neural Networks","created":"2022-02-03","cited_by_count":20},{"id":"2412.17640","title":"Hierarchical Vector Quantization for Unsupervised Action Segmentation","created":"2024-12-23","cited_by_count":19},{"id":"2206.15031","title":"Timestamp-Supervised Action Segmentation with Graph Convolutional Networks","created":"2022-06-30","cited_by_count":18},{"id":"2305.19478","title":"Permutation-Aware Action Segmentation via Unsupervised Frame-to-Segment Alignment","created":"2023-05-31","cited_by_count":17},{"id":"1705.08506","title":"HuGaDB: Human Gait Database for Activity Recognition from Wearable Inertial Sensor Networks","created":"2017-05-10","cited_by_count":16},{"id":"2110.00529","title":"Unsupervised Motion Representation Learning with Capsule Autoencoders","created":"2021-10-01","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":"1705.07818","title":"TricorNet: A Hybrid Temporal Convolutional and Recurrent Network for Video Action Segmentation","created":"2017-05-22","cited_by_count":14},{"id":"2503.01206","title":"Action Tokenizer Matters in In-Context Imitation Learning","created":"2025-03-03","cited_by_count":14},{"id":"2204.12223","title":"Context-Aware Sequence Alignment using 4D Skeletal Augmentation","created":"2022-04-26","cited_by_count":11},{"id":"2503.16832","title":"Joint Self-Supervised Video Alignment and Action Segmentation","created":"2025-03-21","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":"1912.03442","title":"Spatio-Temporal Pyramid Graph Convolutions for Human Action Recognition and Postural Assessment","created":"2019-12-07","cited_by_count":9},{"id":"2312.05830","title":"A Decoupled Spatio-Temporal Framework for Skeleton-based Action Segmentation","created":"2023-12-10","cited_by_count":8},{"id":"2207.09925","title":"An Efficient Framework for Few-shot Skeleton-based Temporal Action Segmentation","created":"2022-07-20","cited_by_count":7},{"id":"2309.06462","title":"Action Segmentation Using 2D Skeleton Heatmaps and Multi-Modality Fusion","created":"2023-09-12","cited_by_count":6},{"id":"2507.03539","title":"CLOT: Closed Loop Optimal Transport for Unsupervised Action Segmentation","created":"2025-07-04","cited_by_count":6},{"id":"2508.04513","title":"Skeleton Motion Words for Unsupervised Skeleton-Based Temporal Action Segmentation","created":"2025-08-06","cited_by_count":6},{"id":"2507.15540","title":"Procedure Learning via Regularized Gromov-Wasserstein Optimal Transport","created":"2025-07-21","cited_by_count":4},{"id":"1911.04969","title":"Deep-Aligned Convolutional Neural Network for Skeleton-based Action Recognition and Segmentation","created":"2019-11-12","cited_by_count":3},{"id":"2305.19480","title":"Learning by Aligning 2D Skeleton Sequences and Multi-Modality Fusion","created":"2023-05-31","cited_by_count":3}],"next_cursor":null}