{"total":118,"rows":[{"id":"2306.05424","title":"Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models","created":"2023-06-08","cited_by_count":1062,"area":null},{"id":"2307.06948","title":"Self-regulating Prompts: Foundational Model Adaptation without Forgetting","created":"2023-07-13","cited_by_count":272,"area":null},{"id":"2306.15880","title":"Towards Open Vocabulary Learning: A Survey","created":"2023-06-28","cited_by_count":166,"area":null},{"id":"2311.07042","title":"Open-Vocabulary Video Anomaly Detection","created":"2023-11-13","cited_by_count":57,"area":null},{"id":"2308.14746","title":"CoVR-2: Automatic Data Construction for Composed Video Retrieval","created":"2023-08-28","cited_by_count":52,"area":null},{"id":"2308.13382","title":"Prompting Visual-Language Models for Dynamic Facial Expression Recognition","created":"2023-08-25","cited_by_count":44,"area":null},{"id":"2303.08914","title":"MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge","created":"2023-03-15","cited_by_count":43,"area":null},{"id":"2303.02982","title":"CLIP-guided Prototype Modulating for Few-shot Action Recognition","created":"2023-03-06","cited_by_count":41,"area":null},{"id":"2312.09627","title":"TF-CLIP: Learning Text-free CLIP for Video-based Person Re-Identification","created":"2023-12-15","cited_by_count":40,"area":null},{"id":"2404.00801","title":"$R^2$-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding","created":"2024-03-31","cited_by_count":34,"area":null},{"id":"2406.07471","title":"OphNet: A Large-Scale Video Benchmark for Ophthalmic Surgical Workflow Understanding","created":"2024-06-11","cited_by_count":32,"area":null},{"id":"2403.16997","title":"Composed Video Retrieval via Enriched Context and Discriminative Embeddings","created":"2024-03-25","cited_by_count":26,"area":null},{"id":"2312.04076","title":"Large Language Models are Good Prompt Learners for Low-Shot Image Classification","created":"2023-12-07","cited_by_count":21,"area":null},{"id":"2403.10801","title":"Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples","created":"2024-03-16","cited_by_count":21,"area":null},{"id":"2410.18882","title":"A Survey of Multimodal Sarcasm Detection","created":"2024-10-24","cited_by_count":19,"area":null},{"id":"2408.07500","title":"Cross-Platform Video Person ReID: A New Benchmark Dataset and Adaptation Approach","created":"2024-08-14","cited_by_count":17,"area":null},{"id":"2410.02131","title":"Boosting Masked ECG-Text Auto-Encoders as Discriminative Learners","created":"2024-10-03","cited_by_count":17,"area":null},{"id":"2409.17523","title":"EAGLE: Egocentric AGgregated Language-video Engine","created":"2024-09-26","cited_by_count":16,"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":"2503.08270","title":"HERO: Human Reaction Generation from Videos","created":"2025-03-11","cited_by_count":15,"area":null},{"id":"2312.08010","title":"EZ-CLIP: Efficient Zeroshot Video Action Recognition","created":"2023-12-13","cited_by_count":14,"area":null},{"id":"2507.22264","title":"SmartCLIP: Modular Vision-language Alignment with Identification Guarantees","created":"2025-07-29","cited_by_count":14,"area":null},{"id":"2410.09750","title":"Surgical-LLaVA: Toward Surgical Scenario Understanding via Large Language and Vision Models","created":"2024-10-13","cited_by_count":13,"area":null},{"id":"2311.15619","title":"Align before Adapt: Leveraging Entity-to-Region Alignments for Generalizable Video Action Recognition","created":"2023-11-27","cited_by_count":12,"area":null},{"id":"2405.03280","title":"Animate Your Thoughts: Decoupled Reconstruction of Dynamic Natural Vision from Slow Brain Activity","created":"2024-05-06","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":"2307.10922","title":"Language-based Action Concept Spaces Improve Video Self-Supervised Learning","created":"2023-07-20","cited_by_count":10,"area":null},{"id":"2311.16514","title":"Video Anomaly Detection via Spatio-Temporal Pseudo-Anomaly Generation : A Unified Approach","created":"2023-11-27","cited_by_count":10,"area":null},{"id":"2401.03522","title":"Text-Driven Traffic Anomaly Detection with Temporal High-Frequency Modeling in Driving Videos","created":"2024-01-07","cited_by_count":9,"area":null},{"id":"2404.09490","title":"Leveraging Temporal Contextualization for Video Action Recognition","created":"2024-04-15","cited_by_count":9,"area":null},{"id":"2412.09895","title":"Building a Multi-modal Spatiotemporal Expert for Zero-shot Action Recognition with CLIP","created":"2024-12-13","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":"2307.10763","title":"Actor-agnostic Multi-label Action Recognition with Multi-modal Query","created":"2023-07-20","cited_by_count":8,"area":null},{"id":"2312.02226","title":"Generating Action-conditioned Prompts for Open-vocabulary Video Action Recognition","created":"2023-12-04","cited_by_count":8,"area":null},{"id":"2401.11654","title":"ActionHub: A Large-scale Action Video Description Dataset for Zero-shot Action Recognition","created":"2024-01-22","cited_by_count":8,"area":null},{"id":"2411.10922","title":"Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection","created":"2024-11-17","cited_by_count":8,"area":null},{"id":"2503.13160","title":"Language-guided Open-world Video Anomaly Detection under Weak Supervision","created":"2025-03-17","cited_by_count":8,"area":null},{"id":"2603.20190","title":"CoVR-R:Reason-Aware Composed Video Retrieval","created":"2026-03-20","cited_by_count":8,"area":null},{"id":"2308.05787","title":"Temporally-Adaptive Models for Efficient Video Understanding","created":"2023-08-10","cited_by_count":7,"area":null},{"id":"2310.01430","title":"Sarcasm in Sight and Sound: Benchmarking and Expansion to Improve Multimodal Sarcasm Detection","created":"2023-09-29","cited_by_count":7,"area":null},{"id":"2406.09390","title":"LLAVIDAL: A Large LAnguage VIsion Model for Daily Activities of Living","created":"2024-06-13","cited_by_count":7,"area":null},{"id":"2409.07078","title":"Multimodal Emotion Recognition with Vision-language Prompting and Modality Dropout","created":"2024-09-11","cited_by_count":7,"area":null},{"id":"2410.01817","title":"Aligning AI with Public Values: Deliberation and Decision-Making for Governing Multimodal LLMs in Political Video Analysis","created":"2024-09-15","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":"2306.02243","title":"Retrieval-Enhanced Visual Prompt Learning for Few-shot Classification","created":"2023-06-04","cited_by_count":6,"area":null},{"id":"2308.06897","title":"Orthogonal Temporal Interpolation for Zero-Shot Video Recognition","created":"2023-08-14","cited_by_count":6,"area":null},{"id":"2404.17498","title":"Learning text-to-video retrieval from image captioning","created":"2024-04-26","cited_by_count":6,"area":null},{"id":"2405.18808","title":"BRACTIVE: A Brain Activation Approach to Human Visual Brain Learning","created":"2024-05-29","cited_by_count":6,"area":null},{"id":"2410.01341","title":"Cognition Transferring and Decoupling for Text-supervised Egocentric Semantic Segmentation","created":"2024-10-02","cited_by_count":6,"area":null},{"id":"2501.12681","title":"Can masking background and object reduce static bias for zero-shot action recognition?","created":"2025-01-22","cited_by_count":6,"area":null},{"id":"2505.20680","title":"Continual Learning on CLIP via Incremental Prompt Tuning with Intrinsic Textual Anchors","created":"2025-05-27","cited_by_count":6,"area":null},{"id":"2505.21549","title":"Distill CLIP (DCLIP): Enhancing Image-Text Retrieval via Cross-Modal Transformer Distillation","created":"2025-05-25","cited_by_count":6,"area":null},{"id":"2507.00286","title":"\"Before, I Asked My Mom, Now I Ask ChatGPT\": Visual Privacy Management with Generative AI for Blind and Low-Vision People","created":"2025-06-30","cited_by_count":6,"area":null},{"id":"2508.14039","title":"Beyond Simple Edits: Composed Video Retrieval with Dense Modifications","created":"2025-08-19","cited_by_count":6,"area":null},{"id":"2304.01200","title":"Video Instance Segmentation in an Open-World","created":"2023-04-03","cited_by_count":5,"area":null},{"id":"2306.12642","title":"TaCA: Upgrading Your Visual Foundation Model with Task-agnostic Compatible Adapter","created":"2023-06-22","cited_by_count":5,"area":null},{"id":"2307.04192","title":"Self-Adaptive Sampling for Efficient Video Question-Answering on Image--Text Models","created":"2023-07-09","cited_by_count":5,"area":null},{"id":"2405.10832","title":"Open-Vocabulary Spatio-Temporal Action Detection","created":"2024-05-17","cited_by_count":5,"area":null},{"id":"2410.10589","title":"MoTE: Reconciling Generalization with Specialization for Visual-Language to Video Knowledge Transfer","created":"2024-10-14","cited_by_count":5,"area":null},{"id":"2502.05432","title":"MoFM: A Large-Scale Human Motion Foundation Model","created":"2025-02-08","cited_by_count":5,"area":null},{"id":"2401.07669","title":"SRL-CLIP: Efficient CLIP Video Adaptation via Structured Semantic Role Labels","created":"2024-01-15","cited_by_count":4,"area":null},{"id":"2402.12706","title":"Learning Causal Domain-Invariant Temporal Dynamics for Few-Shot Action Recognition","created":"2024-02-20","cited_by_count":4,"area":null},{"id":"2403.06295","title":"A streamlined Approach to Multimodal Few-Shot Class Incremental Learning for Fine-Grained Datasets","created":"2024-03-10","cited_by_count":4,"area":null},{"id":"2405.06128","title":"Enhanced Multimodal Content Moderation of Children's Videos using Audiovisual Fusion","created":"2024-05-09","cited_by_count":4,"area":null},{"id":"2407.12987","title":"ActionSwitch: Class-agnostic Detection of Simultaneous Actions in Streaming Videos","created":"2024-07-17","cited_by_count":4,"area":null},{"id":"2410.14238","title":"Storyboard guided Alignment for Fine-grained Video Action Recognition","created":"2024-10-18","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":"2410.18267","title":"Backdoor in Seconds: Unlocking Vulnerabilities in Large Pre-trained Models via Model Editing","created":"2024-10-23","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":"2505.13123","title":"Just Dance with $\\pi$! A Poly-modal Inductor for Weakly-supervised Video Anomaly Detection","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2506.22967","title":"ActAlign: Zero-Shot Fine-Grained Video Classification via Language-Guided Sequence Alignment","created":"2025-06-28","cited_by_count":3,"area":null},{"id":"2508.07312","title":"MobileViCLIP: An Efficient Video-Text Model for Mobile Devices","created":"2025-08-10","cited_by_count":3,"area":null},{"id":"2409.01690","title":"Taming CLIP for Fine-grained and Structured Visual Understanding of Museum Exhibits","created":"2024-09-03","cited_by_count":2,"area":null},{"id":"2503.23266","title":"OwlSight: A Robust Illumination Adaptation Framework for Dark Video Human Action Recognition","created":"2025-03-30","cited_by_count":2,"area":null},{"id":"2505.19495","title":"The Role of Video Generation in Enhancing Data-Limited Action Understanding","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2506.05543","title":"FRAME: Pre-Training Video Feature Representations via Anticipation and Memory","created":"2025-06-05","cited_by_count":2,"area":null},{"id":"2507.00724","title":"Holmes: Towards Effective and Harmless Model Ownership Verification to Personalized Large Vision Models via Decoupling Common Features","created":"2025-06-24","cited_by_count":2,"area":null},{"id":"2508.14197","title":"CLIPSym: Delving into Symmetry Detection with CLIP","created":"2025-08-19","cited_by_count":2,"area":null},{"id":"2510.10671","title":"Image-to-Video Transfer Learning based on Image-Language Foundation Models: A Comprehensive Survey","created":"2025-10-12","cited_by_count":2,"area":null},{"id":"2605.17336","title":"Tactile-based Multimodal Fusion in Embodied Intelligence: A Survey of Vision, Language, and Contact-Driven Paradigms","created":"2026-05-17","cited_by_count":2,"area":null},{"id":"2406.03447","title":"FILS: Self-Supervised Video Feature Prediction In Semantic Language Space","created":"2024-06-05","cited_by_count":1,"area":null},{"id":"2407.19520","title":"Ego-VPA: Egocentric Video Understanding with Parameter-efficient Adaptation","created":"2024-07-28","cited_by_count":1,"area":null},{"id":"2409.05007","title":"Audio-Guided Fusion Techniques for Multimodal Emotion Analysis","created":"2024-09-08","cited_by_count":1,"area":null},{"id":"2505.00569","title":"AnimalMotionCLIP: Embedding motion in CLIP for Animal Behavior Analysis","created":"2025-04-30","cited_by_count":1,"area":null},{"id":"2506.00903","title":"Leveraging CLIP Encoder for Multimodal Emotion Recognition","created":"2025-06-01","cited_by_count":1,"area":null},{"id":"2508.00085","title":"Punching Bag vs. Punching Person: Motion Transferability in Videos","created":"2025-07-31","cited_by_count":1,"area":null},{"id":"2510.06820","title":"Efficient Discriminative Joint Encoders for Large Scale Vision-Language Reranking","created":"2025-10-08","cited_by_count":1,"area":null},{"id":"2510.09203","title":"Cattle-CLIP: A Multimodal Framework for Cattle Behaviour Recognition from Video","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2510.21798","title":"An Evaluation of Hybrid Annotation Workflows on High-Ambiguity Spatiotemporal Video Footage","created":"2025-10-20","cited_by_count":1,"area":null},{"id":"2602.21819","title":"SemVideo: Reconstructs What You Watch from Brain Activity via Hierarchical Semantic Guidance","created":"2026-02-25","cited_by_count":1,"area":null},{"id":"2606.30638","title":"Open-Vocabulary and Referring Segmentation for 3D Gaussians Using 2D Detectors","created":"2026-06-29","cited_by_count":1,"area":null},{"id":"2401.12471","title":"Training-Free Action Recognition and Goal Inference with Dynamic Frame Selection","created":"2024-01-23","cited_by_count":0,"area":null},{"id":"2403.06136","title":"RESTORE: Towards Feature Shift for Vision-Language Prompt Learning","created":"2024-03-10","cited_by_count":0,"area":null},{"id":"2405.17729","title":"Hierarchical Action Recognition: A Contrastive Video-Language Approach with Hierarchical Interactions","created":"2024-05-28","cited_by_count":0,"area":null},{"id":"2406.05075","title":"Diving Deep into the Motion Representation of Video-Text Models","created":"2024-06-07","cited_by_count":0,"area":null},{"id":"2406.05776","title":"Utilizing Grounded SAM for self-supervised frugal camouflaged human detection","created":"2024-06-09","cited_by_count":0,"area":null},{"id":"2408.06840","title":"Dynamic and Compressive Adaptation of Transformers From Images to Videos","created":"2024-08-13","cited_by_count":0,"area":null},{"id":"2410.07635","title":"Shift and matching queries for video semantic segmentation","created":"2024-10-10","cited_by_count":0,"area":null},{"id":"2503.08064","title":"Continual Learning for Multiple Modalities","created":"2025-03-11","cited_by_count":0,"area":null},{"id":"2504.03096","title":"Scaling Open-Vocabulary Action Detection","created":"2025-04-04","cited_by_count":0,"area":null}],"next_cursor":"100"}