{"total":136,"rows":[{"id":"2302.12422","title":"MimicPlay: Long-Horizon Imitation Learning by Watching Human Play","created":"2023-02-24","cited_by_count":223,"area":"offlinerl"},{"id":"2603.14482","title":"V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning","created":"2026-03-15","cited_by_count":117,"area":null},{"id":"2207.00419","title":"Self-Supervised Learning for Videos: A Survey","created":"2022-06-18","cited_by_count":85,"area":null},{"id":"2304.06708","title":"Verbs in Action: Improving verb understanding in video-language models","created":"2023-04-13","cited_by_count":76,"area":null},{"id":"2112.01514","title":"Self-supervised Video Transformer","created":"2021-12-02","cited_by_count":64,"area":null},{"id":"2307.15615","title":"A survey on deep learning in medical image registration: new technologies, uncertainty, evaluation metrics, and beyond","created":"2023-07-28","cited_by_count":55,"area":null},{"id":"2301.02074","title":"Test of Time: Instilling Video-Language Models with a Sense of Time","created":"2023-01-05","cited_by_count":51,"area":null},{"id":"2203.15205","title":"SPAct: Self-supervised Privacy Preservation for Action Recognition","created":"2022-03-29","cited_by_count":47,"area":null},{"id":"2112.03624","title":"Time-Equivariant Contrastive Video Representation Learning","created":"2021-12-07","cited_by_count":44,"area":null},{"id":"2603.12231","title":"Temporal Straightening for Latent Planning","created":"2026-03-12","cited_by_count":38,"area":"wm"},{"id":"2201.11736","title":"Ranking Info Noise Contrastive Estimation: Boosting Contrastive Learning via Ranked Positives","created":"2022-01-27","cited_by_count":37,"area":null},{"id":"2304.00946","title":"MoLo: Motion-augmented Long-short Contrastive Learning for Few-shot Action Recognition","created":"2023-04-03","cited_by_count":37,"area":null},{"id":"2307.05916","title":"SwiFT: Swin 4D fMRI Transformer","created":"2023-07-12","cited_by_count":36,"area":null},{"id":"2204.03946","title":"Probabilistic Representations for Video Contrastive Learning","created":"2022-04-08","cited_by_count":34,"area":null},{"id":"2212.05330","title":"Complete-to-Partial 4D Distillation for Self-Supervised Point Cloud Sequence Representation Learning","created":"2022-12-10","cited_by_count":30,"area":"distill"},{"id":"2401.03717","title":"Universal Time-Series Representation Learning: A Survey","created":"2024-01-08","cited_by_count":30,"area":null},{"id":"2207.01398","title":"Large-scale Robustness Analysis of Video Action Recognition Models","created":"2022-07-04","cited_by_count":29,"area":null},{"id":"2212.01141","title":"MHCCL: Masked Hierarchical Cluster-Wise Contrastive Learning for Multivariate Time Series","created":"2022-12-02","cited_by_count":28,"area":null},{"id":"2111.06265","title":"Dense Unsupervised Learning for Video Segmentation","created":"2021-11-11","cited_by_count":26,"area":null},{"id":"2206.13964","title":"Learning Gait Representation from Massive Unlabelled Walking Videos: A Benchmark","created":"2022-06-28","cited_by_count":25,"area":null},{"id":"2201.04029","title":"Motion-Focused Contrastive Learning of Video Representations","created":"2022-01-11","cited_by_count":23,"area":null},{"id":"2203.14221","title":"How Severe is Benchmark-Sensitivity in Video Self-Supervised Learning?","created":"2022-03-27","cited_by_count":23,"area":null},{"id":"2207.12795","title":"Static and Dynamic Concepts for Self-supervised Video Representation Learning","created":"2022-07-26","cited_by_count":23,"area":null},{"id":"2308.11072","title":"TeD-SPAD: Temporal Distinctiveness for Self-supervised Privacy-preservation for video Anomaly Detection","created":"2023-08-21","cited_by_count":23,"area":null},{"id":"2112.05883","title":"Self-supervised Spatiotemporal Representation Learning by Exploiting Video Continuity","created":"2021-12-11","cited_by_count":22,"area":null},{"id":"2203.01265","title":"Self-supervised Transformer for Deepfake Detection","created":"2022-03-02","cited_by_count":22,"area":null},{"id":"2304.00571","title":"DropMAE: Learning Representations via Masked Autoencoders with Spatial-Attention Dropout for Temporal Matching Tasks","created":"2023-04-02","cited_by_count":22,"area":null},{"id":"2210.06433","title":"Self-supervised video pretraining yields robust and more human-aligned visual representations","created":"2022-10-12","cited_by_count":20,"area":null},{"id":"2302.07702","title":"Audio-Visual Contrastive Learning with Temporal Self-Supervision","created":"2023-02-15","cited_by_count":18,"area":null},{"id":"2201.05277","title":"Boundary-aware Self-supervised Learning for Video Scene Segmentation","created":"2022-01-14","cited_by_count":17,"area":null},{"id":"2206.12534","title":"SLIC: Self-Supervised Learning with Iterative Clustering for Human Action Videos","created":"2022-06-25","cited_by_count":17,"area":null},{"id":"2309.01270","title":"COMEDIAN: Self-Supervised Learning and Knowledge Distillation for Action Spotting using Transformers","created":"2023-09-03","cited_by_count":17,"area":"distill"},{"id":"2403.17823","title":"Efficient Image Pre-Training with Siamese Cropped Masked Autoencoders","created":"2024-03-26","cited_by_count":17,"area":null},{"id":"2105.09270","title":"Do We Really Need to Learn Representations from In-domain Data for Outlier Detection?","created":"2021-05-19","cited_by_count":16,"area":null},{"id":"2112.11700","title":"Adaptive Contrast for Image Regression in Computer-Aided Disease Assessment","created":"2021-12-22","cited_by_count":16,"area":null},{"id":"2303.16268","title":"TimeBalance: Temporally-Invariant and Temporally-Distinctive Video Representations for Semi-Supervised Action Recognition","created":"2023-03-28","cited_by_count":16,"area":null},{"id":"2308.10603","title":"A step towards understanding why classification helps regression","created":"2023-08-21","cited_by_count":15,"area":null},{"id":"2311.01851","title":"Holistic Representation Learning for Multitask Trajectory Anomaly Detection","created":"2023-11-03","cited_by_count":15,"area":null},{"id":"2308.01578","title":"Unsupervised Representation Learning for Time Series: A Review","created":"2023-08-03","cited_by_count":14,"area":null},{"id":"2407.15447","title":"SIGMA: Sinkhorn-Guided Masked Video Modeling","created":"2024-07-22","cited_by_count":14,"area":null},{"id":"2205.13313","title":"Cross-Architecture Self-supervised Video Representation Learning","created":"2022-05-26","cited_by_count":13,"area":null},{"id":"2303.14395","title":"MDQE: Mining Discriminative Query Embeddings to Segment Occluded Instances on Challenging Videos","created":"2023-03-25","cited_by_count":13,"area":null},{"id":"2312.10308","title":"Event-Based Contrastive Learning for Medical Time Series","created":"2023-12-16","cited_by_count":13,"area":null},{"id":"2303.11003","title":"Tubelet-Contrastive Self-Supervision for Video-Efficient Generalization","created":"2023-03-20","cited_by_count":12,"area":null},{"id":"2112.08913","title":"Contrastive Spatio-Temporal Pretext Learning for Self-supervised Video Representation","created":"2021-12-16","cited_by_count":11,"area":null},{"id":"2204.12223","title":"Context-Aware Sequence Alignment using 4D Skeletal Augmentation","created":"2022-04-26","cited_by_count":11,"area":null},{"id":"2208.06105","title":"Motion Sensitive Contrastive Learning for Self-supervised Video Representation","created":"2022-08-12","cited_by_count":11,"area":null},{"id":"2308.13711","title":"EventTransAct: A video transformer-based framework for Event-camera based action recognition","created":"2023-08-25","cited_by_count":11,"area":null},{"id":"2312.06721","title":"Understanding Physical Dynamics with Counterfactual World Modeling","created":"2023-12-11","cited_by_count":11,"area":"wm"},{"id":"2312.13008","title":"No More Shortcuts: Realizing the Potential of Temporal Self-Supervision","created":"2023-12-20","cited_by_count":11,"area":null},{"id":"2503.16832","title":"Joint Self-Supervised Video Alignment and Action Segmentation","created":"2025-03-21","cited_by_count":11,"area":null},{"id":"2509.08502","title":"Chirality in Action: Time-Aware Video Representation Learning by Latent Straightening","created":"2025-09-10","cited_by_count":11,"area":null},{"id":"2203.16632","title":"Controllable Augmentations for Video Representation Learning","created":"2022-03-30","cited_by_count":10,"area":null},{"id":"2210.08423","title":"TransVisDrone: Spatio-Temporal Transformer for Vision-based Drone-to-Drone Detection in Aerial Videos","created":"2022-10-16","cited_by_count":10,"area":null},{"id":"2307.10922","title":"Language-based Action Concept Spaces Improve Video Self-Supervised Learning","created":"2023-07-20","cited_by_count":10,"area":null},{"id":"2201.08625","title":"VIPriors 2: Visual Inductive Priors for Data-Efficient Deep Learning Challenges","created":"2022-01-21","cited_by_count":8,"area":null},{"id":"2209.12074","title":"Self-supervised Learning for Unintentional Action Prediction","created":"2022-09-24","cited_by_count":7,"area":null},{"id":"2308.09775","title":"Long-range Multimodal Pretraining for Movie Understanding","created":"2023-08-18","cited_by_count":7,"area":null},{"id":"2309.00297","title":"Fine-Grained Spatiotemporal Motion Alignment for Contrastive Video Representation Learning","created":"2023-09-01","cited_by_count":7,"area":null},{"id":"2209.15280","title":"Learning Transferable Spatiotemporal Representations from Natural Script Knowledge","created":"2022-09-30","cited_by_count":6,"area":null},{"id":"2306.06010","title":"A Large-Scale Analysis on Self-Supervised Video Representation Learning","created":"2023-06-09","cited_by_count":5,"area":null},{"id":"2311.16535","title":"Contrastive encoder pre-training-based clustered federated learning for heterogeneous data","created":"2023-11-28","cited_by_count":5,"area":null},{"id":"2507.09513","title":"Animal behavioral analysis and neural encoding with transformer-based self-supervised pretraining","created":"2025-07-13","cited_by_count":5,"area":null},{"id":"2510.13768","title":"Scaling Vision Transformers for Functional MRI with Flat Maps","created":"2025-10-15","cited_by_count":5,"area":null},{"id":"2410.12018","title":"LocoMotion: Learning Motion-Focused Video-Language Representations","created":"2024-10-15","cited_by_count":4,"area":null},{"id":"2504.05706","title":"SEVERE++: Evaluating Benchmark Sensitivity in Generalization of Video Representation Learning","created":"2025-04-08","cited_by_count":4,"area":null},{"id":"2507.15540","title":"Procedure Learning via Regularized Gromov-Wasserstein Optimal Transport","created":"2025-07-21","cited_by_count":4,"area":null},{"id":"2509.10156","title":"LayerLock: Non-collapsing Representation Learning with Progressive Freezing","created":"2025-09-12","cited_by_count":4,"area":null},{"id":"2510.11204","title":"Class Prototypes based Contrastive Learning for Classifying Multi-Label and Fine-Grained Educational Videos","created":"2025-10-13","cited_by_count":4,"area":null},{"id":"2203.13166","title":"Self-supervised Video-centralised Transformer for Video Face Clustering","created":"2022-03-24","cited_by_count":3,"area":null},{"id":"2204.03865","title":"Frequency Selective Augmentation for Video Representation Learning","created":"2022-04-08","cited_by_count":3,"area":null},{"id":"2206.04676","title":"Extending Momentum Contrast with Cross Similarity Consistency Regularization","created":"2022-06-07","cited_by_count":3,"area":null},{"id":"2209.11870","title":"Leveraging Self-Supervised Training for Unintentional Action Recognition","created":"2022-09-23","cited_by_count":3,"area":null},{"id":"2210.05574","title":"Motion Aware Self-Supervision for Generic Event Boundary Detection","created":"2022-10-11","cited_by_count":3,"area":null},{"id":"2305.19480","title":"Learning by Aligning 2D Skeleton Sequences and Multi-Modality Fusion","created":"2023-05-31","cited_by_count":3,"area":null},{"id":"2404.06243","title":"ActNetFormer: Transformer-ResNet Hybrid Method for Semi-Supervised Action Recognition in Videos","created":"2024-04-09","cited_by_count":3,"area":null},{"id":"2409.01448","title":"FinePseudo: Improving Pseudo-Labelling through Temporal-Alignablity for Semi-Supervised Fine-Grained Action Recognition","created":"2024-09-02","cited_by_count":3,"area":null},{"id":"2409.02371","title":"Unfolding Videos Dynamics via Taylor Expansion","created":"2024-09-04","cited_by_count":3,"area":null},{"id":"2504.06153","title":"A Large-Scale Analysis on Contextual Self-Supervised Video Representation Learning","created":"2025-04-08","cited_by_count":3,"area":null},{"id":"2510.26782","title":"Cloning Deterministic Worlds: The Critical Role of Latent Geometry in Long-Horizon World Models","created":"2025-10-30","cited_by_count":3,"area":"wm"},{"id":"2603.00461","title":"ReMoT: Reinforcement Learning with Motion Contrast Triplets","created":"2026-02-28","cited_by_count":3,"area":null},{"id":"2112.00804","title":"PreViTS: Contrastive Pretraining with Video Tracking Supervision","created":"2021-12-01","cited_by_count":2,"area":null},{"id":"2211.17042","title":"Spatio-Temporal Crop Aggregation for Video Representation Learning","created":"2022-11-30","cited_by_count":2,"area":null},{"id":"2212.11187","title":"Similarity Contrastive Estimation for Image and Video Soft Contrastive Self-Supervised Learning","created":"2022-12-21","cited_by_count":2,"area":null},{"id":"2304.07354","title":"NEV-NCD: Negative Learning, Entropy, and Variance regularization based novel action categories discovery","created":"2023-04-14","cited_by_count":2,"area":null},{"id":"2402.02275","title":"SudokuSens: Enhancing Deep Learning Robustness for IoT Sensing Applications using a Generative Approach","created":"2024-02-03","cited_by_count":2,"area":null},{"id":"2402.10478","title":"CodaMal: Contrastive Domain Adaptation for Malaria Detection in Low-Cost Microscopes","created":"2024-02-16","cited_by_count":2,"area":null},{"id":"2403.07513","title":"Spatiotemporal Representation Learning for Short and Long Medical Image Time Series","created":"2024-03-12","cited_by_count":2,"area":null},{"id":"2404.16416","title":"Learning Discriminative Spatio-temporal Representations for Semi-supervised Action Recognition","created":"2024-04-25","cited_by_count":2,"area":"lr"},{"id":"2410.11281","title":"DynaCLR: Contrastive Learning of Cellular Dynamics with Temporal Regularization","created":"2024-10-15","cited_by_count":2,"area":null},{"id":"2412.00049","title":"A Survey of Recent Advances and Challenges in Deep Audio-Visual Correlation Learning","created":"2024-11-24","cited_by_count":2,"area":null},{"id":"2506.17516","title":"EASE: Embodied Active Event Perception via Self-Supervised Energy Minimization","created":"2025-06-20","cited_by_count":2,"area":null},{"id":"2507.12426","title":"DVFL-Net: A Lightweight Distilled Video Focal Modulation Network for Spatio-Temporal Action Recognition","created":"2025-07-16","cited_by_count":2,"area":null},{"id":"2205.05609","title":"Video-ReTime: Learning Temporally Varying Speediness for Time Remapping","created":"2022-05-11","cited_by_count":1,"area":null},{"id":"2207.10158","title":"GOCA: Guided Online Cluster Assignment for Self-Supervised Video Representation Learning","created":"2022-07-20","cited_by_count":1,"area":null},{"id":"2207.10862","title":"Contrastive Self-Supervised Learning Leads to Higher Adversarial Susceptibility","created":"2022-07-22","cited_by_count":1,"area":null},{"id":"2301.05213","title":"Learning to Summarize Videos by Contrasting Clips","created":"2023-01-12","cited_by_count":1,"area":null},{"id":"2309.13962","title":"Egocentric RGB+Depth Action Recognition in Industry-Like Settings","created":"2023-09-25","cited_by_count":1,"area":null},{"id":"2408.00498","title":"How Effective are Self-Supervised Models for Contact Identification in Videos","created":"2024-08-01","cited_by_count":1,"area":null},{"id":"2409.01445","title":"Sync from the Sea: Retrieving Alignable Videos from Large-Scale Datasets","created":"2024-09-02","cited_by_count":1,"area":null}],"next_cursor":"100"}