{"total":72,"rows":[{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109,"area":"mllm"},{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040,"area":null},{"id":"2303.08128","title":"ViperGPT: Visual Inference via Python Execution for Reasoning","created":"2023-03-14","cited_by_count":603,"area":"lr"},{"id":"2311.04257","title":"mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration","created":"2023-11-07","cited_by_count":547,"area":"mllm"},{"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":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206,"area":null},{"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":"2303.16058","title":"Unmasked Teacher: Towards Training-Efficient Video Foundation Models","created":"2023-03-28","cited_by_count":199,"area":null},{"id":"2305.18500","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","created":"2023-05-29","cited_by_count":169,"area":null},{"id":"2302.00402","title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","created":"2023-02-01","cited_by_count":154,"area":null},{"id":"2501.03230","title":"Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition","created":"2024-05-07","cited_by_count":153,"area":"lr"},{"id":"2309.01327","title":"Can I Trust Your Answer? Visually Grounded Video Question Answering","created":"2023-09-04","cited_by_count":135,"area":null},{"id":"2310.10196","title":"Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook","created":"2023-10-16","cited_by_count":110,"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":"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":"2412.11959","title":"Gramian Multimodal Representation Learning and Alignment","created":"2024-12-16","cited_by_count":54,"area":null},{"id":"2310.15747","title":"Large Language Models are Temporal and Causal Reasoners for Video Question Answering","created":"2023-10-24","cited_by_count":51,"area":"lr"},{"id":"2310.19060","title":"TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding","created":"2023-10-29","cited_by_count":49,"area":null},{"id":"2402.05861","title":"Memory Consolidation Enables Long-Context Video Understanding","created":"2024-02-08","cited_by_count":45,"area":null},{"id":"2309.15785","title":"BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning","created":"2023-09-27","cited_by_count":41,"area":null},{"id":"2311.13627","title":"Vamos: Versatile Action Models for Video Understanding","created":"2023-11-22","cited_by_count":40,"area":null},{"id":"2312.00937","title":"Zero-Shot Video Question Answering with Procedural Programs","created":"2023-12-01","cited_by_count":37,"area":null},{"id":"2306.04362","title":"Youku-mPLUG: A 10 Million Large-scale Chinese Video-Language Dataset for Pre-training and Benchmarks","created":"2023-06-07","cited_by_count":36,"area":"mllm"},{"id":"2310.04900","title":"HowToCaption: Prompting LLMs to Transform Video Annotations at Scale","created":"2023-10-07","cited_by_count":34,"area":null},{"id":"2406.19255","title":"Enhancing Video-Language Representations with Structural Spatio-Temporal Alignment","created":"2024-06-27","cited_by_count":32,"area":null},{"id":"2403.16998","title":"Understanding Long Videos with Multimodal Language Models","created":"2024-03-25","cited_by_count":25,"area":"mllm"},{"id":"2404.01476","title":"TraveLER: A Modular Multi-LMM Agent Framework for Video Question-Answering","created":"2024-04-01","cited_by_count":25,"area":"mllm"},{"id":"2312.11897","title":"Text-Conditioned Resampler For Long Form Video Understanding","created":"2023-12-19","cited_by_count":24,"area":null},{"id":"2312.08367","title":"ViLA: Efficient Video-Language Alignment for Video Question Answering","created":"2023-12-13","cited_by_count":23,"area":null},{"id":"2407.15047","title":"End-to-End Video Question Answering with Frame Scoring Mechanisms and Adaptive Sampling","created":"2024-07-21","cited_by_count":19,"area":null},{"id":"2507.17343","title":"Principled Multimodal Representation Learning","created":"2025-07-23","cited_by_count":19,"area":null},{"id":"2509.24734","title":"A TRIANGLE Enables Multimodal Alignment Beyond Cosine Similarity","created":"2025-09-29","cited_by_count":18,"area":null},{"id":"2305.13167","title":"VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending","created":"2023-05-22","cited_by_count":17,"area":null},{"id":"2311.05698","title":"Mirasol3B: A Multimodal Autoregressive model for time-aligned and contextual modalities","created":"2023-11-09","cited_by_count":15,"area":null},{"id":"2401.01974","title":"Towards Truly Zero-shot Compositional Visual Reasoning with LLMs as Programmers","created":"2024-01-03","cited_by_count":14,"area":"lr"},{"id":"2401.10711","title":"Weakly Supervised Gaussian Contrastive Grounding with Large Multimodal Models for Video Question Answering","created":"2024-01-19","cited_by_count":14,"area":"mllm"},{"id":"2310.04991","title":"Video-Teller: Enhancing Cross-Modal Generation with Fusion and Decoupling","created":"2023-10-08","cited_by_count":12,"area":null},{"id":"2306.09085","title":"COSA: Concatenated Sample Pretrained Vision-Language Foundation Model","created":"2023-06-15","cited_by_count":11,"area":"mllm"},{"id":"2410.05714","title":"Enhancing Temporal Modeling of Video LLMs via Time Gating","created":"2024-10-08","cited_by_count":10,"area":null},{"id":"2403.18074","title":"Every Shot Counts: Using Exemplars for Repetition Counting in Videos","created":"2024-03-26","cited_by_count":9,"area":null},{"id":"2407.07478","title":"EA-VTR: Event-Aware Video-Text Retrieval","created":"2024-07-10","cited_by_count":8,"area":null},{"id":"2501.19061","title":"EgoMe: A New Dataset and Challenge for Following Me via Egocentric View in Real World","created":"2025-01-31","cited_by_count":8,"area":"offlinerl"},{"id":"2402.10896","title":"PaLM2-VAdapter: Progressively Aligned Language Model Makes a Strong Vision-language Adapter","created":"2024-02-16","cited_by_count":7,"area":"alignment"},{"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":"2312.02249","title":"Recursive Visual Programming","created":"2023-12-04","cited_by_count":6,"area":null},{"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":"2504.18856","title":"Multi-Resolution Pathology-Language Pre-training Model with Text-Guided Visual Representation","created":"2025-04-26","cited_by_count":6,"area":"mllm"},{"id":"2401.17797","title":"M2-RAAP: A Multi-Modal Recipe for Advancing Adaptation-based Pre-training towards Effective and Efficient Zero-shot Video-text Retrieval","created":"2024-01-31","cited_by_count":5,"area":null},{"id":"2402.13546","title":"LLMs Meet Long Video: Advancing Long Video Question Answering with An Interactive Visual Adapter in LLMs","created":"2024-02-21","cited_by_count":5,"area":null},{"id":"2412.12833","title":"FocusChat: Text-guided Long Video Understanding via Spatiotemporal Information Filtering","created":"2024-12-17","cited_by_count":5,"area":"mllm"},{"id":"2505.15928","title":"ViQAgent: Zero-Shot Video Question Answering via Agent with Open-Vocabulary Grounding Validation","created":"2025-05-21","cited_by_count":5,"area":"agents"},{"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":"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":"2505.17114","title":"RAVEN: Query-Guided Representation Alignment for Question Answering over Audio, Video, Embedded Sensors, and Natural Language","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2509.11862","title":"Bridging Vision Language Models and Symbolic Grounding for Video Question Answering","created":"2025-09-15","cited_by_count":4,"area":"mllm"},{"id":"2602.09507","title":"Towards Uniformity and Alignment for Multimodal Representation Learning","created":"2026-02-10","cited_by_count":4,"area":null},{"id":"2305.03204","title":"VideoOFA: Two-Stage Pre-Training for Video-to-Text Generation","created":"2023-05-04","cited_by_count":3,"area":"lr"},{"id":"2309.02290","title":"ATM: Action Temporality Modeling for Video Question Answering","created":"2023-09-05","cited_by_count":3,"area":"lr"},{"id":"2412.00049","title":"A Survey of Recent Advances and Challenges in Deep Audio-Visual Correlation Learning","created":"2024-11-24","cited_by_count":2,"area":null},{"id":"2412.19304","title":"Perceive, Query & Reason: Enhancing Video QA with Question-Guided Temporal Queries","created":"2024-12-26","cited_by_count":2,"area":"lr"},{"id":"2503.06820","title":"Towards Fine-Grained Video Question Answering","created":"2025-03-10","cited_by_count":2,"area":null},{"id":"2509.21559","title":"X-CoT: Explainable Text-to-Video Retrieval via LLM-based Chain-of-Thought Reasoning","created":"2025-09-25","cited_by_count":2,"area":"lr"},{"id":"2603.22953","title":"Cluster-Wise Spatio-Temporal Masking for Efficient Video-Language Pretraining","created":"2026-03-24","cited_by_count":2,"area":null},{"id":"2412.07704","title":"GEXIA: Granularity Expansion and Iterative Approximation for Scalable Multi-grained Video-language Learning","created":"2024-12-10","cited_by_count":1,"area":null},{"id":"2407.08507","title":"Bootstrapping Vision-language Models for Self-supervised Remote Physiological Measurement","created":"2024-07-11","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":"2509.15642","title":"UNIV: Unified Foundation Model for Infrared and Visible Modalities","created":"2025-09-19","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":"2609.15320","title":"Hypergraph-Regularized Gramian Volumes for Multimodal Retrieval","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.35090","title":"Advancing Video-Text Pretraining with Multi-View Captions","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}