{"total":40,"rows":[{"id":"2501.03218","title":"Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction","created":"2025-01-06","cited_by_count":127,"area":null},{"id":"2306.16741","title":"Foundation Model for Endoscopy Video Analysis via Large-scale Self-supervised Pre-train","created":"2023-06-29","cited_by_count":75,"area":null},{"id":"2310.16387","title":"Frequency-Aware Transformer for Learned Image Compression","created":"2023-10-25","cited_by_count":58,"area":null},{"id":"2212.03814","title":"iQuery: Instruments as Queries for Audio-Visual Sound Separation","created":"2022-12-07","cited_by_count":29,"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":"2407.09853","title":"Image Compression for Machine and Human Vision with Spatial-Frequency Adaptation","created":"2024-07-13","cited_by_count":26,"area":null},{"id":"2308.04549","title":"Prune Spatio-temporal Tokens by Semantic-aware Temporal Accumulation","created":"2023-08-08","cited_by_count":24,"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":"2308.09951","title":"Semantics Meets Temporal Correspondence: Self-supervised Object-centric Learning in Videos","created":"2023-08-19","cited_by_count":20,"area":null},{"id":"2404.00653","title":"Dual DETRs for Multi-Label Temporal Action Detection","created":"2024-03-31","cited_by_count":20,"area":null},{"id":"2207.05340","title":"Dual Contrastive Learning for Spatio-temporal Representation","created":"2022-07-12","cited_by_count":15,"area":null},{"id":"2308.14500","title":"LAC: Latent Action Composition for Skeleton-based Action Segmentation","created":"2023-08-28","cited_by_count":15,"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":"2305.06437","title":"Self-Supervised Video Representation Learning via Latent Time Navigation","created":"2023-05-10","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":"2311.17893","title":"Betrayed by Attention: A Simple yet Effective Approach for Self-supervised Video Object Segmentation","created":"2023-11-29","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":"2407.06871","title":"Rethinking Image-to-Video Adaptation: An Object-centric Perspective","created":"2024-07-09","cited_by_count":8,"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":"2402.11928","title":"Separating common from salient patterns with Contrastive Representation Learning","created":"2024-02-19","cited_by_count":6,"area":null},{"id":"2208.01036","title":"Face-to-Face Contrastive Learning for Social Intelligence Question-Answering","created":"2022-07-29","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":"2410.12018","title":"LocoMotion: Learning Motion-Focused Video-Language Representations","created":"2024-10-15","cited_by_count":4,"area":null},{"id":"2204.03865","title":"Frequency Selective Augmentation for Video Representation Learning","created":"2022-04-08","cited_by_count":3,"area":null},{"id":"2304.05600","title":"Looking Similar, Sounding Different: Leveraging Counterfactual Cross-Modal Pairs for Audiovisual Representation Learning","created":"2023-04-12","cited_by_count":3,"area":null},{"id":"2503.24108","title":"PolypSegTrack: Unified Foundation Model for Colonoscopy Video Analysis","created":"2025-03-31","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":"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":"2411.17584","title":"Pre-training for Action Recognition with Automatically Generated Fractal Datasets","created":"2024-11-26","cited_by_count":1,"area":null},{"id":"2503.12485","title":"Cross-Modal Consistency Learning for Sign Language Recognition","created":"2025-03-16","cited_by_count":1,"area":null},{"id":"2511.08666","title":"Privacy Beyond Pixels: Latent Anonymization for Privacy-Preserving Video Understanding","created":"2025-11-11","cited_by_count":1,"area":null},{"id":"2401.07584","title":"Collaboratively Self-supervised Video Representation Learning for Action Recognition","created":"2024-01-15","cited_by_count":0,"area":null},{"id":"2411.15729","title":"OccludeNet: A Causal Journey into Mixed-View Actor-Centric Video Action Recognition under Occlusions","created":"2024-11-24","cited_by_count":0,"area":null},{"id":"2507.19730","title":"Quaternion-Based Robust PCA for Efficient Moving Target Detection and Background Recovery in Color Videos","created":"2025-07-26","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":"2603.25778","title":"Focus-to-Perceive Representation Learning: A Cognition-Inspired Hierarchical Framework for Endoscopic Video Analysis","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2607.19889","title":"Latent-Action-Guided Video-Language Feature Learning for Surgical Instrument-Tissue Interaction Recognition","created":"2026-07-22","cited_by_count":0,"area":null}],"next_cursor":null}