{"total":55,"rows":[{"id":"2304.10465","title":"Implicit Temporal Modeling with Learnable Alignment for Video Recognition","created":"2023-04-20","cited_by_count":46,"area":null},{"id":"2312.00081","title":"Synthesize, Diagnose, and Optimize: Towards Fine-Grained Vision-Language Understanding","created":"2023-11-30","cited_by_count":46,"area":"mllm"},{"id":"2412.01694","title":"Enhancing Video-LLM Reasoning via Agent-of-Thoughts Distillation","created":"2024-12-02","cited_by_count":37,"area":"lr"},{"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":"2512.01989","title":"PAI-Bench: A Comprehensive Benchmark For Physical AI","created":"2025-12-01","cited_by_count":34,"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":"2510.08480","title":"Video-STAR: Reinforcing Open-Vocabulary Action Recognition with Tools","created":"2025-10-09","cited_by_count":26,"area":"mllm"},{"id":"2310.05010","title":"Building an Open-Vocabulary Video CLIP Model with Better Architectures, Optimization and Data","created":"2023-10-08","cited_by_count":22,"area":null},{"id":"2406.06465","title":"AID: Adapting Image2Video Diffusion Models for Instruction-guided Video Prediction","created":"2024-06-10","cited_by_count":21,"area":"diffusion"},{"id":"2311.18837","title":"VIDiff: Translating Videos via Multi-Modal Instructions with Diffusion Models","created":"2023-11-30","cited_by_count":19,"area":"diffusion"},{"id":"2310.10651","title":"HairCLIPv2: Unifying Hair Editing via Proxy Feature Blending","created":"2023-10-16","cited_by_count":17,"area":null},{"id":"2311.05464","title":"3DStyle-Diffusion: Pursuing Fine-grained Text-driven 3D Stylization with 2D Diffusion Models","created":"2023-11-09","cited_by_count":17,"area":"diffusion"},{"id":"2403.01560","title":"XOV-Action: Towards Generalizable Open-Vocabulary Action Recognition","created":"2024-03-03","cited_by_count":15,"area":null},{"id":"2408.06158","title":"OmniCLIP: Adapting CLIP for Video Recognition with Spatial-Temporal Omni-Scale Feature Learning","created":"2024-08-12","cited_by_count":14,"area":"mllm"},{"id":"2503.18094","title":"Anomize: Better Open Vocabulary Video Anomaly Detection","created":"2025-03-23","cited_by_count":13,"area":null},{"id":"2308.10315","title":"Improving Adversarial Robustness of Masked Autoencoders via Test-time Frequency-domain Prompting","created":"2023-08-20","cited_by_count":12,"area":null},{"id":"2503.22405","title":"Modeling Multiple Normal Action Representations for Error Detection in Procedural Tasks","created":"2025-03-28","cited_by_count":12,"area":null},{"id":"2310.12152","title":"Learning from Rich Semantics and Coarse Locations for Long-tailed Object Detection","created":"2023-10-18","cited_by_count":11,"area":null},{"id":"2408.15241","title":"GenRec: Unifying Video Generation and Recognition with Diffusion Models","created":"2024-08-27","cited_by_count":11,"area":"diffusion"},{"id":"2408.05775","title":"Efficient Test-Time Prompt Tuning for Vision-Language Models","created":"2024-08-11","cited_by_count":10,"area":"mllm"},{"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":"2502.19128","title":"SCA3D: Enhancing Cross-modal 3D Retrieval via 3D Shape and Caption Paired Data Augmentation","created":"2025-02-26","cited_by_count":9,"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":"2411.10922","title":"Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection","created":"2024-11-17","cited_by_count":8,"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":"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":"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":"2411.11223","title":"Efficient Transfer Learning for Video-language Foundation Models","created":"2024-11-18","cited_by_count":4,"area":"mllm"},{"id":"2511.00613","title":"CueBench: Advancing Unified Understanding of Context-Aware Video Anomalies in Real-World","created":"2025-11-01","cited_by_count":4,"area":null},{"id":"2406.05766","title":"Set-CLIP: Exploring Aligned Semantic From Low-Alignment Multimodal Data Through A Distribution View","created":"2024-06-09","cited_by_count":3,"area":null},{"id":"2409.12499","title":"End-to-end Open-vocabulary Video Visual Relationship Detection using Multi-modal Prompting","created":"2024-09-19","cited_by_count":3,"area":null},{"id":"2511.22664","title":"VaMP: Variational Multi-Modal Prompt Learning for Vision-Language Models","created":"2025-11-27","cited_by_count":3,"area":"mllm"},{"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":"2406.08814","title":"Skim then Focus: Integrating Contextual and Fine-grained Views for Repetitive Action Counting","created":"2024-06-13","cited_by_count":1,"area":null},{"id":"2508.17417","title":"Constrained Prompt Enhancement for Improving Zero-Shot Generalization of Vision-Language Models","created":"2025-08-24","cited_by_count":1,"area":"mllm"},{"id":"2511.16423","title":"TOFA: Training-Free One-Shot Federated Adaptation for Vision-Language Models","created":"2025-11-20","cited_by_count":1,"area":"mllm"},{"id":"2601.11990","title":"DAOS: A Multimodal In-cabin Behavior Monitoring with Driver Action-Object Synergy Dataset","created":"2026-01-17","cited_by_count":1,"area":null},{"id":"2603.03066","title":"EduVQA: Towards Concept-Aware Assessment of Educational AI-Generated Videos","created":"2026-03-03","cited_by_count":1,"area":"moe"},{"id":"2405.08695","title":"The impact of Compositionality in Zero-shot Multi-label action recognition for Object-based tasks","created":"2024-05-14","cited_by_count":0,"area":null},{"id":"2412.08628","title":"EOV-Seg: Efficient Open-Vocabulary Panoptic Segmentation","created":"2024-12-11","cited_by_count":0,"area":null},{"id":"2510.19574","title":"Can You Trust What You See? Alpha Channel No-Box Attacks on Video Object Detection","created":"2025-10-22","cited_by_count":0,"area":null},{"id":"2511.10958","title":"Text-guided Weakly Supervised Framework for Dynamic Facial Expression Recognition","created":"2025-11-14","cited_by_count":0,"area":null},{"id":"2604.00767","title":"ActivityNarrated: An Open-Ended Narrative Paradigm for Wearable Human Activity Understanding","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2604.22595","title":"EV-CLIP: Efficient Visual Prompt Adaptation for CLIP in Few-shot Action Recognition under Visual Challenges","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2605.23288","title":"Spatio-Temporal Similarity Volume Aggregation for Open-Vocabulary Action Recognition","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2605.25479","title":"MAIL++: Multi-Modal Bi-directional Agent Layer for Vision-Language Models","created":"2026-05-25","cited_by_count":0,"area":"mllm"},{"id":"2606.20734","title":"Robust Zero-Shot Generalization for Open-Vocabulary Action Recognition via Task Arithmetic","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2606.25478","title":"TACO: Towards Task-Consistent Open-Vocabulary Adaptation in Video Recognition","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2606.30342","title":"A Classifier-Agnostic Zero-Shot Adversarial Attack Detection via CLIP","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2606.31187","title":"Learning to Deny: Action Denial in Multimodal Large Language Models","created":"2026-06-30","cited_by_count":0,"area":"mllm"},{"id":"2609.00505","title":"ViTAL-X: Video-Text Alignment with Cross-Modal Temporal Edits","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2610.16666","title":"Revisiting Natural Language Prompts from Large Language Models for Open-Vocabulary Video Recognition","created":"2026-10-12","cited_by_count":0,"area":"mllm"}],"next_cursor":null}