{"total":76,"rows":[{"id":"2403.10517","title":"VideoAgent: Long-form Video Understanding with Large Language Model as Agent","created":"2024-03-15","cited_by_count":332,"area":"agents"},{"id":"2305.06988","title":"Self-Chained Image-Language Model for Video Localization and Question Answering","created":"2023-05-11","cited_by_count":203,"area":null},{"id":"2312.17235","title":"A Simple LLM Framework for Long-Range Video Question-Answering","created":"2023-12-28","cited_by_count":178,"area":null},{"id":"2402.13217","title":"VideoPrism: A Foundational Visual Encoder for Video Understanding","created":"2024-02-20","cited_by_count":105,"area":null},{"id":"2404.06511","title":"MoReVQA: Exploring Modular Reasoning Models for Video Question Answering","created":"2024-04-09","cited_by_count":74,"area":"lr"},{"id":"2503.06661","title":"AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIP","created":"2025-03-09","cited_by_count":73,"area":null},{"id":"2406.09396","title":"Too Many Frames, Not All Useful: Efficient Strategies for Long-Form Video QA","created":"2024-06-13","cited_by_count":68,"area":null},{"id":"2403.14622","title":"Language Repository for Long Video Understanding","created":"2024-03-21","cited_by_count":55,"area":null},{"id":"2305.10683","title":"Paxion: Patching Action Knowledge in Video-Language Foundation Models","created":"2023-05-18","cited_by_count":42,"area":null},{"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":"2312.09788","title":"Collaborating Foundation Models for Domain Generalized Semantic Segmentation","created":"2023-12-15","cited_by_count":34,"area":null},{"id":"2311.10111","title":"VideoCon: Robust Video-Language Alignment via Contrast Captions","created":"2023-11-15","cited_by_count":30,"area":null},{"id":"2311.17518","title":"The devil is in the fine-grained details: Evaluating open-vocabulary object detectors for fine-grained understanding","created":"2023-11-29","cited_by_count":29,"area":"mllm"},{"id":"2311.03964","title":"Enhancing Multimodal Compositional Reasoning of Visual Language Models with Generative Negative Mining","created":"2023-11-07","cited_by_count":25,"area":"lr"},{"id":"2403.16998","title":"Understanding Long Videos with Multimodal Language Models","created":"2024-03-25","cited_by_count":25,"area":"mllm"},{"id":"2311.12919","title":"SPOT! Revisiting Video-Language Models for Event Understanding","created":"2023-11-21","cited_by_count":20,"area":null},{"id":"2311.13833","title":"Lego: Learning to Disentangle and Invert Personalized Concepts Beyond Object Appearance in Text-to-Image Diffusion Models","created":"2023-11-23","cited_by_count":19,"area":"diffusion"},{"id":"2404.05426","title":"Test-Time Zero-Shot Temporal Action Localization","created":"2024-04-08","cited_by_count":19,"area":null},{"id":"2409.00951","title":"Semantically Controllable Augmentations for Generalizable Robot Learning","created":"2024-09-02","cited_by_count":18,"area":null},{"id":"2405.09931","title":"Learning from Observer Gaze:Zero-Shot Attention Prediction Oriented by Human-Object Interaction Recognition","created":"2024-05-16","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":"2403.01560","title":"XOV-Action: Towards Generalizable Open-Vocabulary Action Recognition","created":"2024-03-03","cited_by_count":15,"area":null},{"id":"2503.16980","title":"VQToken: Neural Discrete Token Representation Learning for Extreme Token Reduction in Video Large Language Models","created":"2025-03-21","cited_by_count":12,"area":"inference"},{"id":"2405.17719","title":"Do Egocentric Video-Language Models Truly Understand Hand-Object Interactions?","created":"2024-05-28","cited_by_count":11,"area":null},{"id":"2409.04388","title":"Question-Answering Dense Video Events","created":"2024-09-06","cited_by_count":11,"area":null},{"id":"2412.02071","title":"Progress-Aware Video Frame Captioning","created":"2024-12-03","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":"2312.04931","title":"Long Video Understanding with Learnable Retrieval in Video-Language Models","created":"2023-12-08","cited_by_count":9,"area":null},{"id":"2402.10698","title":"Question-Instructed Visual Descriptions for Zero-Shot Video Question Answering","created":"2024-02-16","cited_by_count":9,"area":"mllm"},{"id":"2306.08889","title":"Dissecting Multimodality in VideoQA Transformer Models by Impairing Modality Fusion","created":"2023-06-15","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":"2405.17201","title":"Diagnosing the Compositional Knowledge of Vision Language Models from a Game-Theoretic View","created":"2024-05-27","cited_by_count":7,"area":"lr"},{"id":"2503.16406","title":"VerbDiff: Text-Only Diffusion Models with Enhanced Interaction Awareness","created":"2025-03-20","cited_by_count":7,"area":"diffusion"},{"id":"2505.03173","title":"RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph","created":"2025-05-06","cited_by_count":7,"area":"mllm"},{"id":"2402.10534","title":"Using Left and Right Brains Together: Towards Vision and Language Planning","created":"2024-02-16","cited_by_count":6,"area":null},{"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":"2412.06182","title":"Towards Long Video Understanding via Fine-detailed Video Story Generation","created":"2024-12-09","cited_by_count":6,"area":null},{"id":"2412.09353","title":"Causal Graphical Models for Vision-Language Compositional Understanding","created":"2024-12-12","cited_by_count":6,"area":"mllm"},{"id":"2503.16106","title":"OSLoPrompt: Bridging Low-Supervision Challenges and Open-Set Domain Generalization in CLIP","created":"2025-03-20","cited_by_count":6,"area":null},{"id":"2312.00055","title":"LEAP: LLM-Generation of Egocentric Action Programs","created":"2023-11-29","cited_by_count":5,"area":null},{"id":"2312.00414","title":"Vision-Language Models Learn Super Images for Efficient Partially Relevant Video Retrieval","created":"2023-12-01","cited_by_count":5,"area":"mllm"},{"id":"2403.14870","title":"VidLA: Video-Language Alignment at Scale","created":"2024-03-21","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":"2410.09380","title":"Prompting Video-Language Foundation Models with Domain-specific Fine-grained Heuristics for Video Question Answering","created":"2024-10-12","cited_by_count":5,"area":null},{"id":"2410.23676","title":"Web-Scale Visual Entity Recognition: An LLM-Driven Data Approach","created":"2024-10-31","cited_by_count":5,"area":"mllm"},{"id":"2601.11210","title":"VidLeaks: Membership Inference Attacks Against Text-to-Video Models","created":"2026-01-16","cited_by_count":5,"area":"safety"},{"id":"2605.27894","title":"Towards Unified Vision-Language Models with Incomplete Multi-Modal Inputs","created":"2026-05-27","cited_by_count":5,"area":"lr"},{"id":"2310.20633","title":"Defining a New NLP Playground","created":"2023-10-31","cited_by_count":4,"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":"2502.02885","title":"Expertized Caption Auto-Enhancement for Video-Text Retrieval","created":"2025-02-05","cited_by_count":4,"area":null},{"id":"2504.20860","title":"FedMVP: Federated Multimodal Visual Prompt Tuning for Vision-Language Models","created":"2025-04-29","cited_by_count":4,"area":"mllm"},{"id":"2309.02290","title":"ATM: Action Temporality Modeling for Video Question Answering","created":"2023-09-05","cited_by_count":3,"area":"lr"},{"id":"2410.24219","title":"Enhancing Motion in Text-to-Video Generation with Decomposed Encoding and Conditioning","created":"2024-10-31","cited_by_count":3,"area":null},{"id":"2411.13683","title":"Extending Video Masked Autoencoders to 128 frames","created":"2024-11-20","cited_by_count":3,"area":null},{"id":"2507.18616","title":"SynC: Synthetic Image Caption Dataset Refinement with One-to-many Mapping for Zero-shot Image Captioning","created":"2025-07-24","cited_by_count":3,"area":null},{"id":"2412.17415","title":"VidCtx: Context-aware Video Question Answering with Image Models","created":"2024-12-23","cited_by_count":2,"area":"mllm"},{"id":"2309.15086","title":"Video-adverb retrieval with compositional adverb-action embeddings","created":"2023-09-26","cited_by_count":1,"area":null},{"id":"2312.06699","title":"Leveraging Generative Language Models for Weakly Supervised Sentence Component Analysis in Video-Language Joint Learning","created":"2023-12-10","cited_by_count":1,"area":null},{"id":"2410.12407","title":"Beyond Coarse-Grained Matching in Video-Text Retrieval","created":"2024-10-16","cited_by_count":1,"area":null},{"id":"2411.15628","title":"ACE: Action Concept Enhancement of Video-Language Models in Procedural Videos","created":"2024-11-23","cited_by_count":1,"area":"mllm"},{"id":"2412.07161","title":"Compositional Zero-Shot Learning with Contextualized Cues and Adaptive Contrastive Training","created":"2024-12-10","cited_by_count":1,"area":null},{"id":"2503.09130","title":"Reference-free Human-Object Interaction Editing","created":"2025-03-12","cited_by_count":1,"area":null},{"id":"2503.18507","title":"Can Text-to-Video Generation help Video-Language Alignment?","created":"2025-03-24","cited_by_count":1,"area":null},{"id":"2505.22943","title":"Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates","created":"2025-05-28","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":"2406.05075","title":"Diving Deep into the Motion Representation of Video-Text Models","created":"2024-06-07","cited_by_count":0,"area":null},{"id":"2501.08771","title":"Admitting Ignorance Helps the Video Question Answering Models to Answer","created":"2025-01-15","cited_by_count":0,"area":null},{"id":"2504.05463","title":"REVEAL: Relation-based Video Representation Learning for Video-Question-Answering","created":"2025-04-07","cited_by_count":0,"area":null},{"id":"2505.03374","title":"Reducing Annotation Burden in Physical Activity Research Using Vision-Language Models","created":"2025-05-06","cited_by_count":0,"area":"mllm"},{"id":"2512.13511","title":"Adapting MLLMs for Nuanced Video Retrieval","created":"2025-12-15","cited_by_count":0,"area":null},{"id":"2604.08762","title":"InstrAct: Towards Action-Centric Understanding in Instructional Videos","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2604.14069","title":"Towards Unconstrained Human-Object Interaction","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2605.22201","title":"Zero-Shot Temporal Action Localization Through Textual Guidance","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2607.09263","title":"Semantic Hardness Is Not Visual Hardness: Sign-Aware Hard Negative Mining for Sign Language Retrieval","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2607.10350","title":"ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memory","created":"2026-07-11","cited_by_count":0,"area":"agents"},{"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}