{"total":143,"rows":[{"id":"2104.11178","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","created":"2021-04-22","cited_by_count":429,"area":null},{"id":"2104.14558","title":"A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning","created":"2021-04-29","cited_by_count":214,"area":null},{"id":"2106.02036","title":"Anticipative Video Transformer","created":"2021-06-03","cited_by_count":200,"area":null},{"id":"2103.05905","title":"VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples","created":"2021-03-10","cited_by_count":154,"area":null},{"id":"2205.11508","title":"Contrastive and Non-Contrastive Self-Supervised Learning Recover Global and Local Spectral Embedding Methods","created":"2022-05-23","cited_by_count":149,"area":null},{"id":"2206.13188","title":"Self-supervised Learning in Remote Sensing: A Review","created":"2022-06-27","cited_by_count":137,"area":null},{"id":"2101.07974","title":"TCLR: Temporal Contrastive Learning for Video Representation","created":"2021-01-20","cited_by_count":136,"area":null},{"id":"2104.14466","title":"3D Human Action Representation Learning via Cross-View Consistency Pursuit","created":"2021-04-29","cited_by_count":106,"area":null},{"id":"2207.00419","title":"Self-Supervised Learning for Videos: A Survey","created":"2022-06-18","cited_by_count":85,"area":null},{"id":"2207.10883","title":"My View is the Best View: Procedure Learning from Egocentric Videos","created":"2022-07-22","cited_by_count":81,"area":null},{"id":"2103.15916","title":"Robust Audio-Visual Instance Discrimination","created":"2021-03-29","cited_by_count":80,"area":null},{"id":"2108.03656","title":"Skeleton-Contrastive 3D Action Representation Learning","created":"2021-08-08","cited_by_count":76,"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":"2203.01885","title":"TCTrack: Temporal Contexts for Aerial Tracking","created":"2022-03-03","cited_by_count":69,"area":null},{"id":"2107.12960","title":"Enriching Local and Global Contexts for Temporal Action Localization","created":"2021-07-27","cited_by_count":64,"area":null},{"id":"2107.00285","title":"iMiGUE: An Identity-free Video Dataset for Micro-Gesture Understanding and Emotion Analysis","created":"2021-07-01","cited_by_count":63,"area":null},{"id":"2201.05991","title":"Video Transformers: A Survey","created":"2022-01-16","cited_by_count":63,"area":null},{"id":"2207.10172","title":"Video Anomaly Detection by Solving Decoupled Spatio-Temporal Jigsaw Puzzles","created":"2022-07-20","cited_by_count":62,"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":"2104.10955","title":"Distilling Audio-Visual Knowledge by Compositional Contrastive Learning","created":"2021-04-22","cited_by_count":53,"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":"2105.13353","title":"Unsupervised Action Segmentation by Joint Representation Learning and Online Clustering","created":"2021-05-27","cited_by_count":49,"area":null},{"id":"2103.17260","title":"Learning by Aligning Videos in Time","created":"2021-03-31","cited_by_count":48,"area":null},{"id":"2207.00449","title":"Dissecting Self-Supervised Learning Methods for Surgical Computer Vision","created":"2022-07-01","cited_by_count":48,"area":null},{"id":"2303.18230","title":"Procedure-Aware Pretraining for Instructional Video Understanding","created":"2023-03-31","cited_by_count":48,"area":null},{"id":"2109.15130","title":"Motion-aware Contrastive Video Representation Learning via Foreground-background Merging","created":"2021-09-30","cited_by_count":45,"area":null},{"id":"2112.03624","title":"Time-Equivariant Contrastive Video Representation Learning","created":"2021-12-07","cited_by_count":44,"area":null},{"id":"2106.11118","title":"SODA10M: A Large-Scale 2D Self/Semi-Supervised Object Detection Dataset for Autonomous Driving","created":"2021-06-21","cited_by_count":43,"area":null},{"id":"2108.02722","title":"Video Contrastive Learning with Global Context","created":"2021-08-05","cited_by_count":41,"area":null},{"id":"2106.02342","title":"ASCNet: Self-supervised Video Representation Learning with Appearance-Speed Consistency","created":"2021-06-04","cited_by_count":35,"area":null},{"id":"2104.00862","title":"Self-supervised Video Representation Learning by Context and Motion Decoupling","created":"2021-04-02","cited_by_count":34,"area":null},{"id":"2204.03946","title":"Probabilistic Representations for Video Contrastive Learning","created":"2022-04-08","cited_by_count":34,"area":null},{"id":"2104.02116","title":"Action Shuffle Alternating Learning for Unsupervised Action Segmentation","created":"2021-04-05","cited_by_count":33,"area":null},{"id":"2202.07001","title":"Handcrafted Histological Transformer (H2T): Unsupervised Representation of Whole Slide Images","created":"2022-02-14","cited_by_count":32,"area":null},{"id":"2103.10211","title":"Space-Time Crop & Attend: Improving Cross-modal Video Representation Learning","created":"2021-03-18","cited_by_count":31,"area":null},{"id":"2112.03587","title":"TCGL: Temporal Contrastive Graph for Self-supervised Video Representation Learning","created":"2021-12-07","cited_by_count":31,"area":null},{"id":"2109.01305","title":"Video Pose Distillation for Few-Shot, Fine-Grained Sports Action Recognition","created":"2021-09-03","cited_by_count":29,"area":null},{"id":"2112.09690","title":"Cross-Model Pseudo-Labeling for Semi-Supervised Action Recognition","created":"2021-12-17","cited_by_count":29,"area":null},{"id":"2108.08426","title":"Self-Supervised Video Representation Learning with Meta-Contrastive Network","created":"2021-08-19","cited_by_count":28,"area":null},{"id":"2305.15701","title":"Action Sensitivity Learning for Temporal Action Localization","created":"2023-05-25","cited_by_count":28,"area":null},{"id":"2108.02183","title":"Enhancing Self-supervised Video Representation Learning via Multi-level Feature Optimization","created":"2021-08-04","cited_by_count":27,"area":null},{"id":"2203.14333","title":"Locality-Aware Inter-and Intra-Video Reconstruction for Self-Supervised Correspondence Learning","created":"2022-03-27","cited_by_count":26,"area":null},{"id":"2308.10330","title":"Towards Real-World Visual Tracking with Temporal Contexts","created":"2023-08-20","cited_by_count":26,"area":null},{"id":"2207.09812","title":"The Anatomy of Video Editing: A Dataset and Benchmark Suite for AI-Assisted Video Editing","created":"2022-07-20","cited_by_count":25,"area":null},{"id":"2107.07695","title":"Self-supervised Representation Learning Framework for Remote Physiological Measurement Using Spatiotemporal Augmentation Loss","created":"2021-07-16","cited_by_count":24,"area":null},{"id":"2203.16784","title":"Video-Text Representation Learning via Differentiable Weak Temporal Alignment","created":"2022-03-31","cited_by_count":24,"area":null},{"id":"2206.05266","title":"Does Self-supervised Learning Really Improve Reinforcement Learning from Pixels?","created":"2022-06-10","cited_by_count":24,"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":"2209.13583","title":"Learning State-Aware Visual Representations from Audible Interactions","created":"2022-09-27","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":"2104.00240","title":"Self-supervised Motion Learning from Static Images","created":"2021-04-01","cited_by_count":21,"area":null},{"id":"2109.11593","title":"Long Short View Feature Decomposition via Contrastive Video Representation Learning","created":"2021-09-23","cited_by_count":21,"area":null},{"id":"2105.02545","title":"Unsupervised Visual Representation Learning by Tracking Patches in Video","created":"2021-05-06","cited_by_count":20,"area":null},{"id":"2105.06463","title":"Contrastive Learning of Image Representations with Cross-Video Cycle-Consistency","created":"2021-05-13","cited_by_count":19,"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":"2105.01646","title":"Motion-Augmented Self-Training for Video Recognition at Smaller Scale","created":"2021-05-04","cited_by_count":17,"area":null},{"id":"2105.14158","title":"SSCAP: Self-supervised Co-occurrence Action Parsing for Unsupervised Temporal Action Segmentation","created":"2021-05-29","cited_by_count":15,"area":null},{"id":"2207.05340","title":"Dual Contrastive Learning for Spatio-temporal Representation","created":"2022-07-12","cited_by_count":15,"area":null},{"id":"2406.08473","title":"Strategies for Pretraining Neural Operators","created":"2024-06-12","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":"2104.00616","title":"Composable Augmentation Encoding for Video Representation Learning","created":"2021-04-01","cited_by_count":13,"area":null},{"id":"2205.13313","title":"Cross-Architecture Self-supervised Video Representation Learning","created":"2022-05-26","cited_by_count":13,"area":null},{"id":"2301.00794","title":"STEPs: Self-Supervised Key Step Extraction and Localization from Unlabeled Procedural Videos","created":"2023-01-02","cited_by_count":13,"area":null},{"id":"2307.01945","title":"Query-based Video Summarization with Pseudo Label Supervision","created":"2023-07-04","cited_by_count":13,"area":null},{"id":"2311.03550","title":"United We Stand, Divided We Fall: UnityGraph for Unsupervised Procedure Learning from Videos","created":"2023-11-06","cited_by_count":13,"area":null},{"id":"2102.02337","title":"Environment Predictive Coding for Embodied Agents","created":"2021-02-03","cited_by_count":12,"area":null},{"id":"2304.03378","title":"Self-Supervised Video Similarity Learning","created":"2023-04-06","cited_by_count":12,"area":null},{"id":"2104.14764","title":"CoCon: Cooperative-Contrastive Learning","created":"2021-04-30","cited_by_count":11,"area":null},{"id":"2107.12569","title":"Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation","created":"2021-07-27","cited_by_count":11,"area":null},{"id":"2109.15317","title":"Unsupervised Few-Shot Action Recognition via Action-Appearance Aligned Meta-Adaptation","created":"2021-09-30","cited_by_count":11,"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":"2305.06437","title":"Self-Supervised Video Representation Learning via Latent Time Navigation","created":"2023-05-10","cited_by_count":11,"area":null},{"id":"2404.07292","title":"Solving Masked Jigsaw Puzzles with Diffusion Vision Transformers","created":"2024-04-10","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":"2205.02028","title":"TransRank: Self-supervised Video Representation Learning via Ranking-based Transformation Recognition","created":"2022-05-04","cited_by_count":10,"area":null},{"id":"2504.00527","title":"SMILE: Infusing Spatial and Motion Semantics in Masked Video Learning","created":"2025-04-01","cited_by_count":9,"area":null},{"id":"2111.05329","title":"Self-Supervised Audio-Visual Representation Learning with Relaxed Cross-Modal Synchronicity","created":"2021-11-09","cited_by_count":8,"area":null},{"id":"2205.10766","title":"Recent Advances in Embedding Methods for Multi-Object Tracking: A Survey","created":"2022-05-22","cited_by_count":8,"area":null},{"id":"2305.06472","title":"ChatGPT-Like Large-Scale Foundation Models for Prognostics and Health Management: A Survey and Roadmaps","created":"2023-05-10","cited_by_count":8,"area":null},{"id":"2603.19228","title":"SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing","created":"2026-03-19","cited_by_count":8,"area":null},{"id":"2106.03259","title":"Understand and Improve Contrastive Learning Methods for Visual Representation: A Review","created":"2021-06-06","cited_by_count":7,"area":null},{"id":"2209.12074","title":"Self-supervised Learning for Unintentional Action Prediction","created":"2022-09-24","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":"2405.15813","title":"From CNNs to Transformers in Multimodal Human Action Recognition: A Survey","created":"2024-05-22","cited_by_count":7,"area":null},{"id":"2101.00820","title":"Temporal Contrastive Graph Learning for Video Action Recognition and Retrieval","created":"2021-01-04","cited_by_count":6,"area":null},{"id":"2104.05418","title":"Contrastive Learning of Global-Local Video Representations","created":"2021-04-07","cited_by_count":6,"area":null},{"id":"2106.10137","title":"Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting","created":"2021-06-18","cited_by_count":6,"area":null},{"id":"2102.10378","title":"Self-Supervised Learning via multi-Transformation Classification for Action Recognition","created":"2021-02-20","cited_by_count":5,"area":null},{"id":"2107.01194","title":"Inter-intra Variant Dual Representations forSelf-supervised Video Recognition","created":"2021-07-02","cited_by_count":5,"area":null},{"id":"2107.03578","title":"Video 3D Sampling for Self-supervised Representation Learning","created":"2021-07-08","cited_by_count":5,"area":null},{"id":"2112.04480","title":"Exploring Temporal Granularity in Self-Supervised Video Representation Learning","created":"2021-12-08","cited_by_count":5,"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":"2312.13714","title":"Bootstrap Masked Visual Modeling via Hard Patches Mining","created":"2023-12-21","cited_by_count":5,"area":null},{"id":"2407.17616","title":"Pretraining a Neural Operator in Lower Dimensions","created":"2024-07-24","cited_by_count":5,"area":null},{"id":"2503.17975","title":"Shot Sequence Ordering for Video Editing: Benchmarks, Metrics, and Cinematology-Inspired Computing Methods","created":"2025-03-23","cited_by_count":5,"area":null},{"id":"2112.12182","title":"Fine-grained Multi-Modal Self-Supervised Learning","created":"2021-12-22","cited_by_count":4,"area":null}],"next_cursor":"100"}