{"total":179,"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":"2311.13435","title":"PG-Video-LLaVA: Pixel Grounding Large Video-Language Models","created":"2023-11-22","cited_by_count":51,"area":"mllm"},{"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":"2407.20171","title":"Diffusion Feedback Helps CLIP See Better","created":"2024-07-29","cited_by_count":38,"area":"diffusion"},{"id":"2402.03241","title":"FROSTER: Frozen CLIP Is A Strong Teacher for Open-Vocabulary Action Recognition","created":"2024-02-05","cited_by_count":36,"area":"distill"},{"id":"2308.03135","title":"EventBind: Learning a Unified Representation to Bind Them All for Event-based Open-world Understanding","created":"2023-08-06","cited_by_count":34,"area":"mllm"},{"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":"2304.02560","title":"VicTR: Video-conditioned Text Representations for Activity Recognition","created":"2023-04-05","cited_by_count":28,"area":"mllm"},{"id":"2407.04603","title":"AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation","created":"2024-07-05","cited_by_count":28,"area":"mllm"},{"id":"2403.16997","title":"Composed Video Retrieval via Enriched Context and Discriminative Embeddings","created":"2024-03-25","cited_by_count":26,"area":null},{"id":"2510.08480","title":"Video-STAR: Reinforcing Open-Vocabulary Action Recognition with Tools","created":"2025-10-09","cited_by_count":26,"area":"mllm"},{"id":"2409.19291","title":"CLIP-MoE: Towards Building Mixture of Experts for CLIP with Diversified Multiplet Upcycling","created":"2024-09-28","cited_by_count":23,"area":"moe"},{"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":"2506.03179","title":"Vid-SME: Membership Inference Attacks against Large Video Understanding Models","created":"2025-05-29","cited_by_count":19,"area":"mllm"},{"id":"2503.13443","title":"DPC: Dual-Prompt Collaboration for Tuning Vision-Language Models","created":"2025-03-17","cited_by_count":18,"area":"mllm"},{"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":"2312.00096","title":"OST: Refining Text Knowledge with Optimal Spatio-Temporal Descriptor for General Video Recognition","created":"2023-11-30","cited_by_count":16,"area":"mllm"},{"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":"2404.06244","title":"Anchor-based Robust Finetuning of Vision-Language Models","created":"2024-04-09","cited_by_count":11,"area":"mllm"},{"id":"2404.11605","title":"VG4D: Vision-Language Model Goes 4D Video Recognition","created":"2024-04-17","cited_by_count":11,"area":"mllm"},{"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":"2406.10889","title":"VELOCITI: Benchmarking Video-Language Compositional Reasoning with Strict Entailment","created":"2024-06-16","cited_by_count":10,"area":"lr"},{"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":"2403.09948","title":"RadCLIP: Enhancing Radiologic Image Analysis through Contrastive Language-Image Pre-training","created":"2024-03-15","cited_by_count":8,"area":"mllm"},{"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":"2410.11201","title":"Tree of Attributes Prompt Learning for Vision-Language Models","created":"2024-10-15","cited_by_count":7,"area":"mllm"},{"id":"2502.15809","title":"Black Sheep in the Herd: Playing with Spuriously Correlated Attributes for Vision-Language Recognition","created":"2025-02-19","cited_by_count":7,"area":"mllm"},{"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":"2403.19811","title":"X-MIC: Cross-Modal Instance Conditioning for Egocentric Action Generalization","created":"2024-03-28","cited_by_count":6,"area":"mllm"},{"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":"2406.13653","title":"Dual-Phase Continual Learning: Supervised Adaptation Meets Unsupervised Retention","created":"2024-06-19","cited_by_count":6,"area":"mllm"},{"id":"2407.07024","title":"Exploring Scalability of Self-Training for Open-Vocabulary Temporal Action Localization","created":"2024-07-09","cited_by_count":6,"area":"mllm"},{"id":"2408.16412","title":"Text-Enhanced Zero-Shot Action Recognition: A training-free approach","created":"2024-08-29","cited_by_count":6,"area":"mllm"},{"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":"2509.12145","title":"Open-ended Hierarchical Streaming Video Understanding with Vision Language Models","created":"2025-09-15","cited_by_count":6,"area":"mllm"},{"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":"2309.15915","title":"Zero-Shot and Few-Shot Video Question Answering with Multi-Modal Prompts","created":"2023-09-27","cited_by_count":5,"area":"mllm"},{"id":"2310.15324","title":"Videoprompter: an ensemble of foundational models for zero-shot video understanding","created":"2023-10-23","cited_by_count":5,"area":"mllm"},{"id":"2405.10832","title":"Open-Vocabulary Spatio-Temporal Action Detection","created":"2024-05-17","cited_by_count":5,"area":null},{"id":"2407.09073","title":"Open Vocabulary Multi-Label Video Classification","created":"2024-07-12","cited_by_count":5,"area":"mllm"},{"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":"2411.16018","title":"Style-Pro: Style-Guided Prompt Learning for Generalizable Vision-Language Models","created":"2024-11-25","cited_by_count":5,"area":"mllm"},{"id":"2502.05432","title":"MoFM: A Large-Scale Human Motion Foundation Model","created":"2025-02-08","cited_by_count":5,"area":null},{"id":"2602.21397","title":"MMLoP: Multi-Modal Low-Rank Prompting for Efficient Vision-Language Adaptation","created":"2026-02-24","cited_by_count":5,"area":"mllm"},{"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":"2409.06166","title":"Revisiting Prompt Pretraining of Vision-Language Models","created":"2024-09-10","cited_by_count":4,"area":"mllm"},{"id":"2410.14238","title":"Storyboard guided Alignment for Fine-grained Video Action Recognition","created":"2024-10-18","cited_by_count":4,"area":null},{"id":"2410.17149","title":"Are Visual-Language Models Effective in Action Recognition? A Comparative Study","created":"2024-10-22","cited_by_count":4,"area":"mllm"},{"id":"2411.11223","title":"Efficient Transfer Learning for Video-language Foundation Models","created":"2024-11-18","cited_by_count":4,"area":"mllm"},{"id":"2503.08906","title":"Prompt-OT: An Optimal Transport Regularization Paradigm for Knowledge Preservation in Vision-Language Model Adaptation","created":"2025-03-11","cited_by_count":4,"area":"mllm"},{"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":"2505.19373","title":"DiSa: Directional Saliency-Aware Prompt Learning for Generalizable Vision-Language Models","created":"2025-05-26","cited_by_count":4,"area":"mllm"},{"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}],"next_cursor":"100"}