{"total":66,"rows":[{"id":"2112.01514","title":"Self-supervised Video Transformer","created":"2021-12-02","cited_by_count":64,"area":null},{"id":"2311.17404","title":"VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models","created":"2023-11-29","cited_by_count":55,"area":null},{"id":"2110.15128","title":"Contrast and Mix: Temporal Contrastive Video Domain Adaptation with Background Mixing","created":"2021-10-28","cited_by_count":49,"area":null},{"id":"2112.01715","title":"Self-Supervised Material and Texture Representation Learning for Remote Sensing Tasks","created":"2021-12-03","cited_by_count":49,"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":"2108.02722","title":"Video Contrastive Learning with Global Context","created":"2021-08-05","cited_by_count":41,"area":null},{"id":"2210.06096","title":"Masked Motion Encoding for Self-Supervised Video Representation Learning","created":"2022-10-12","cited_by_count":39,"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":"2112.03587","title":"TCGL: Temporal Contrastive Graph for Self-supervised Video Representation Learning","created":"2021-12-07","cited_by_count":31,"area":null},{"id":"2203.13609","title":"Unsupervised Pre-training for Temporal Action Localization Tasks","created":"2022-03-25","cited_by_count":31,"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":"2211.12883","title":"Mitigating and Evaluating Static Bias of Action Representations in the Background and the Foreground","created":"2022-11-23","cited_by_count":27,"area":null},{"id":"2104.09124","title":"DisCo: Remedy Self-supervised Learning on Lightweight Models with Distilled Contrastive Learning","created":"2021-04-19","cited_by_count":26,"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":"2112.05883","title":"Self-supervised Spatiotemporal Representation Learning by Exploiting Video Continuity","created":"2021-12-11","cited_by_count":22,"area":null},{"id":"2503.15871","title":"MASH-VLM: Mitigating Action-Scene Hallucination in Video-LLMs through Disentangled Spatial-Temporal Representations","created":"2025-03-20","cited_by_count":22,"area":null},{"id":"2306.08913","title":"Advancing Volumetric Medical Image Segmentation via Global-Local Masked Autoencoder","created":"2023-06-15","cited_by_count":21,"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":"2310.17942","title":"Diversifying Spatial-Temporal Perception for Video Domain Generalization","created":"2023-10-27","cited_by_count":19,"area":null},{"id":"2207.05340","title":"Dual Contrastive Learning for Spatio-temporal Representation","created":"2022-07-12","cited_by_count":15,"area":null},{"id":"2403.01560","title":"XOV-Action: Towards Generalizable Open-Vocabulary Action Recognition","created":"2024-03-03","cited_by_count":15,"area":null},{"id":"2205.13313","title":"Cross-Architecture Self-supervised Video Representation Learning","created":"2022-05-26","cited_by_count":13,"area":null},{"id":"2303.11003","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":"2208.06105","title":"Motion Sensitive Contrastive Learning for Self-supervised Video Representation","created":"2022-08-12","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":"2307.10922","title":"Language-based Action Concept Spaces Improve Video Self-Supervised Learning","created":"2023-07-20","cited_by_count":10,"area":null},{"id":"2211.09146","title":"A Unified Multimodal De- and Re-coupling Framework for RGB-D Motion Recognition","created":"2022-11-16","cited_by_count":9,"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":"2407.10860","title":"Human-Centric Transformer for Domain Adaptive Action Recognition","created":"2024-07-15","cited_by_count":8,"area":null},{"id":"2109.11475","title":"Self-supervised Learning for Semi-supervised Temporal Language Grounding","created":"2021-09-23","cited_by_count":7,"area":null},{"id":"2204.00239","title":"ObjectMix: Data Augmentation by Copy-Pasting Objects in Videos for Action Recognition","created":"2022-04-01","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":"2312.00826","title":"DEVIAS: Learning Disentangled Video Representations of Action and Scene","created":"2023-11-30","cited_by_count":7,"area":null},{"id":"2502.20158","title":"Learning to Generalize without Bias for Open-Vocabulary Action Recognition","created":"2025-02-27","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":"2304.00858","title":"Focalized Contrastive View-invariant Learning for Self-supervised Skeleton-based Action Recognition","created":"2023-04-03","cited_by_count":6,"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":"2502.00156","title":"ALBAR: Adversarial Learning approach to mitigate Biases in Action Recognition","created":"2025-01-31","cited_by_count":5,"area":null},{"id":"2502.21201","title":"The PanAf-FGBG Dataset: Understanding the Impact of Backgrounds in Wildlife Behaviour Recognition","created":"2025-02-28","cited_by_count":5,"area":null},{"id":"2112.03803","title":"Suppressing Static Visual Cues via Normalizing Flows for Self-Supervised Video Representation Learning","created":"2021-12-07","cited_by_count":4,"area":null},{"id":"2212.13495","title":"Truncate-Split-Contrast: A Framework for Learning from Mislabeled Videos","created":"2022-12-27","cited_by_count":4,"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":"2507.02271","title":"Spotlighting Partially Visible Cinematic Language for Video-to-Audio Generation via Self-distillation","created":"2025-07-03","cited_by_count":4,"area":"distill"},{"id":"2204.03865","title":"Frequency Selective Augmentation for Video Representation Learning","created":"2022-04-08","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":"2212.10870","title":"MoQuad: Motion-focused Quadruple Construction for Video Contrastive Learning","created":"2022-12-21","cited_by_count":2,"area":null},{"id":"2307.14866","title":"Sample Less, Learn More: Efficient Action Recognition via Frame Feature Restoration","created":"2023-07-27","cited_by_count":2,"area":null},{"id":"2308.15169","title":"Uncovering the Unseen: Discover Hidden Intentions by Micro-Behavior Graph Reasoning","created":"2023-08-29","cited_by_count":2,"area":null},{"id":"2403.09506","title":"Don't Judge by the Look: Towards Motion Coherent Video Representation","created":"2024-03-14","cited_by_count":2,"area":null},{"id":"2512.01048","title":"TRoVe: Discovering Error-Inducing Static Feature Biases in Temporal Vision-Language Models","created":"2025-11-30","cited_by_count":2,"area":"mllm"},{"id":"2512.17953","title":"Seeing Beyond the Scene: Analyzing and Mitigating Background Bias in Action Recognition","created":"2025-12-17","cited_by_count":2,"area":null},{"id":"2606.07770","title":"Contrast encodes inductive bias: separating slow noise from dynamics in predictive representation learning","created":"2026-06-05","cited_by_count":2,"area":null},{"id":"2204.04607","title":"Self-Supervised Video Representation Learning with Motion-Contrastive Perception","created":"2022-04-10","cited_by_count":1,"area":null},{"id":"2209.00760","title":"Temporal Contrastive Learning with Curriculum","created":"2022-09-02","cited_by_count":1,"area":null},{"id":"2411.17584","title":"Pre-training for Action Recognition with Automatically Generated Fractal Datasets","created":"2024-11-26","cited_by_count":1,"area":null},{"id":"2606.03490","title":"TrAction: Action Recognition with Sparse Trajectories","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2205.07201","title":"Real-centric Consistency Learning for Deepfake Detection","created":"2022-05-15","cited_by_count":0,"area":null},{"id":"2206.08339","title":"iBoot: Image-bootstrapped Self-Supervised Video Representation Learning","created":"2022-06-16","cited_by_count":0,"area":null},{"id":"2407.14069","title":"Self-Supervised Video Representation Learning in a Heuristic Decoupled Perspective","created":"2024-07-19","cited_by_count":0,"area":null},{"id":"2508.02981","title":"MoExDA: Domain Adaptation for Edge-based Action Recognition","created":"2025-08-05","cited_by_count":0,"area":null},{"id":"2509.23009","title":"Disentangling Static and Dynamic Information for Reducing Static Bias in Action Recognition","created":"2025-09-27","cited_by_count":0,"area":null},{"id":"2601.16211","title":"Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition","created":"2026-01-22","cited_by_count":0,"area":null},{"id":"2603.07222","title":"VINO: Video-driven Invariance for Non-contextual Objects via Structural Prior Guided De-contextualization","created":"2026-03-07","cited_by_count":0,"area":"distill"}],"next_cursor":null}