{"total":116,"rows":[{"id":"2205.14100","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","created":"2022-05-27","cited_by_count":537,"area":null},{"id":"2402.19479","title":"Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers","created":"2024-02-29","cited_by_count":393,"area":null},{"id":"2302.14115","title":"Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning","created":"2023-02-27","cited_by_count":263,"area":"mllm"},{"id":"2305.18565","title":"PaLI-X: On Scaling up a Multilingual Vision and Language Model","created":"2023-05-29","cited_by_count":255,"area":null},{"id":"2206.08155","title":"Zero-Shot Video Question Answering via Frozen Bidirectional Language Models","created":"2022-06-16","cited_by_count":229,"area":null},{"id":"2212.04501","title":"Learning Video Representations from Large Language Models","created":"2022-12-08","cited_by_count":205,"area":null},{"id":"2305.11846","title":"Any-to-Any Generation via Composable Diffusion","created":"2023-05-19","cited_by_count":204,"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":"2302.10035","title":"Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey","created":"2023-02-20","cited_by_count":153,"area":null},{"id":"2304.08345","title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","created":"2023-04-17","cited_by_count":140,"area":null},{"id":"2205.10747","title":"Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners","created":"2022-05-22","cited_by_count":117,"area":null},{"id":"2402.13250","title":"Video ReCap: Recursive Captioning of Hour-Long Videos","created":"2024-02-20","cited_by_count":89,"area":null},{"id":"2212.05051","title":"VindLU: A Recipe for Effective Video-and-Language Pretraining","created":"2022-12-09","cited_by_count":87,"area":null},{"id":"2304.06708","title":"Verbs in Action: Improving verb understanding in video-language models","created":"2023-04-13","cited_by_count":76,"area":null},{"id":"2209.01540","title":"An Empirical Study of End-to-End Video-Language Transformers with Masked Visual Modeling","created":"2022-09-04","cited_by_count":74,"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":"2206.07160","title":"LAVENDER: Unifying Video-Language Understanding as Masked Language Modeling","created":"2022-06-14","cited_by_count":73,"area":null},{"id":"2212.14546","title":"HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training","created":"2022-12-30","cited_by_count":72,"area":null},{"id":"2212.04979","title":"VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners","created":"2022-12-09","cited_by_count":70,"area":null},{"id":"2311.18775","title":"CoDi-2: In-Context, Interleaved, and Interactive Any-to-Any Generation","created":"2023-11-30","cited_by_count":63,"area":"mllm"},{"id":"2304.01008","title":"Self-Supervised Multimodal Learning: A Survey","created":"2023-03-31","cited_by_count":58,"area":null},{"id":"2304.04565","title":"SoccerNet-Caption: Dense Video Captioning for Soccer Broadcasts Commentaries","created":"2023-04-10","cited_by_count":57,"area":null},{"id":"2305.10435","title":"Generative Pre-trained Transformer: A Comprehensive Review on Enabling Technologies, Potential Applications, Emerging Challenges, and Future Directions","created":"2023-05-11","cited_by_count":55,"area":null},{"id":"2412.02104","title":"Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey","created":"2024-12-03","cited_by_count":52,"area":"mllm"},{"id":"2303.16899","title":"AutoAD: Movie Description in Context","created":"2023-03-29","cited_by_count":50,"area":null},{"id":"2310.06838","title":"AutoAD II: The Sequel -- Who, When, and What in Movie Audio Description","created":"2023-10-10","cited_by_count":49,"area":null},{"id":"2303.18230","title":"Procedure-Aware Pretraining for Instructional Video Understanding","created":"2023-03-31","cited_by_count":48,"area":null},{"id":"2401.01578","title":"Context-Guided Spatio-Temporal Video Grounding","created":"2024-01-03","cited_by_count":46,"area":null},{"id":"2307.16184","title":"UnIVAL: Unified Model for Image, Video, Audio and Language Tasks","created":"2023-07-30","cited_by_count":45,"area":null},{"id":"2305.12328","title":"InstructVid2Vid: Controllable Video Editing with Natural Language Instructions","created":"2023-05-21","cited_by_count":44,"area":null},{"id":"2304.04227","title":"Video ChatCaptioner: Towards Enriched Spatiotemporal Descriptions","created":"2023-04-09","cited_by_count":42,"area":null},{"id":"2305.00355","title":"MH-DETR: Video Moment and Highlight Detection with Cross-modal Transformer","created":"2023-04-29","cited_by_count":40,"area":null},{"id":"2309.13952","title":"VidChapters-7M: Video Chapters at Scale","created":"2023-09-25","cited_by_count":39,"area":null},{"id":"2404.07610","title":"Do You Remember? Dense Video Captioning with Cross-Modal Memory Retrieval","created":"2024-04-11","cited_by_count":36,"area":null},{"id":"2404.14412","title":"AutoAD III: The Prequel -- Back to the Pixels","created":"2024-04-22","cited_by_count":35,"area":null},{"id":"2303.11403","title":"eP-ALM: Efficient Perceptual Augmentation of Language Models","created":"2023-03-20","cited_by_count":34,"area":null},{"id":"2310.04900","title":"HowToCaption: Prompting LLMs to Transform Video Annotations at Scale","created":"2023-10-07","cited_by_count":34,"area":null},{"id":"2305.12876","title":"Gloss-Free End-to-End Sign Language Translation","created":"2023-05-22","cited_by_count":32,"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":"2303.12423","title":"Text with Knowledge Graph Augmented Transformer for Video Captioning","created":"2023-03-22","cited_by_count":28,"area":null},{"id":"2303.14655","title":"GOAL: A Challenging Knowledge-grounded Video Captioning Benchmark for Real-time Soccer Commentary Generation","created":"2023-03-26","cited_by_count":28,"area":null},{"id":"2304.11431","title":"A Review of Deep Learning for Video Captioning","created":"2023-04-22","cited_by_count":28,"area":null},{"id":"2306.11732","title":"Retrieving-to-Answer: Zero-Shot Video Question Answering with Frozen Large Language Models","created":"2023-06-15","cited_by_count":27,"area":null},{"id":"2311.07022","title":"ViLMA: A Zero-Shot Benchmark for Linguistic and Temporal Grounding in Video-Language Models","created":"2023-11-13","cited_by_count":26,"area":null},{"id":"2303.16839","title":"MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks","created":"2023-03-29","cited_by_count":24,"area":null},{"id":"2407.15850","title":"AutoAD-Zero: A Training-Free Framework for Zero-Shot Audio Description","created":"2024-07-22","cited_by_count":23,"area":null},{"id":"2309.12867","title":"Accurate and Fast Compressed Video Captioning","created":"2023-09-22","cited_by_count":22,"area":null},{"id":"2303.16342","title":"Language-Guided Audio-Visual Source Separation via Trimodal Consistency","created":"2023-03-28","cited_by_count":20,"area":null},{"id":"2411.18042","title":"HyperGLM: HyperGraph for Video Scene Graph Generation and Anticipation","created":"2024-11-27","cited_by_count":19,"area":"mllm"},{"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":"2403.00691","title":"Tri-Modal Motion Retrieval by Learning a Joint Embedding Space","created":"2024-03-01","cited_by_count":16,"area":null},{"id":"2403.13507","title":"FMM-Attack: A Flow-based Multi-modal Adversarial Attack on Video-based LLMs","created":"2024-03-20","cited_by_count":14,"area":null},{"id":"2210.16428","title":"Visually-Aware Audio Captioning With Adaptive Audio-Visual Attention","created":"2022-10-28","cited_by_count":13,"area":null},{"id":"2301.11507","title":"Semi-Parametric Video-Grounded Text Generation","created":"2023-01-27","cited_by_count":13,"area":null},{"id":"2308.13218","title":"MultiCapCLIP: Auto-Encoding Prompts for Zero-Shot Multilingual Visual Captioning","created":"2023-08-25","cited_by_count":13,"area":null},{"id":"2301.07463","title":"Temporal Perceiving Video-Language Pre-training","created":"2023-01-18","cited_by_count":12,"area":null},{"id":"2403.05021","title":"Beyond MOT: Semantic Multi-Object Tracking","created":"2024-03-08","cited_by_count":12,"area":null},{"id":"2405.07354","title":"SoccerNet-Echoes: A Soccer Game Audio Commentary Dataset","created":"2024-05-12","cited_by_count":12,"area":null},{"id":"2411.18180","title":"DistinctAD: Distinctive Audio Description Generation in Contexts","created":"2024-11-27","cited_by_count":12,"area":null},{"id":"2310.16754","title":"CAD -- Contextual Multi-modal Alignment for Dynamic AVQA","created":"2023-10-25","cited_by_count":10,"area":null},{"id":"2403.07469","title":"A Comprehensive Survey of 3D Dense Captioning: Localizing and Describing Objects in 3D Scenes","created":"2024-03-12","cited_by_count":10,"area":null},{"id":"2405.11483","title":"MICap: A Unified Model for Identity-aware Movie Descriptions","created":"2024-05-19","cited_by_count":9,"area":null},{"id":"2406.13719","title":"GUI Action Narrator: Where and When Did That Action Take Place?","created":"2024-06-19","cited_by_count":9,"area":"mllm"},{"id":"2504.00072","title":"Chapter-Llama: Efficient Chaptering in Hour-Long Videos with LLMs","created":"2025-03-31","cited_by_count":9,"area":null},{"id":"2308.11171","title":"ViCo: Engaging Video Comment Generation with Human Preference Rewards","created":"2023-08-22","cited_by_count":8,"area":"alignment"},{"id":"2312.00347","title":"RTQ: Rethinking Video-language Understanding Based on Image-text Model","created":"2023-12-01","cited_by_count":8,"area":null},{"id":"2407.03788","title":"MAMA: Meta-optimized Angular Margin Contrastive Framework for Video-Language Representation Learning","created":"2024-07-04","cited_by_count":8,"area":null},{"id":"2310.00670","title":"A Hierarchical Graph-based Approach for Recognition and Description Generation of Bimanual Actions in Videos","created":"2023-10-01","cited_by_count":7,"area":null},{"id":"2407.02411","title":"Video Watermarking: Safeguarding Your Video from (Unauthorized) Annotations by Video-based LLMs","created":"2024-07-02","cited_by_count":7,"area":"safety"},{"id":"2407.18908","title":"Wolf: Dense Video Captioning with a World Summarization Framework","created":"2024-07-26","cited_by_count":7,"area":null},{"id":"2303.14829","title":"SEM-POS: Grammatically and Semantically Correct Video Captioning","created":"2023-03-26","cited_by_count":6,"area":null},{"id":"2307.05435","title":"One-Versus-Others Attention: Scalable Multimodal Integration for Biomedical Data","created":"2023-07-11","cited_by_count":6,"area":null},{"id":"2311.07285","title":"Multi Sentence Description of Complex Manipulation Action Videos","created":"2023-11-13","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":"2411.17130","title":"TechCoach: Towards Technical-Point-Aware Descriptive Action Coaching","created":"2024-11-26","cited_by_count":6,"area":null},{"id":"2301.02307","title":"What You Say Is What You Show: Visual Narration Detection in Instructional Videos","created":"2023-01-05","cited_by_count":5,"area":null},{"id":"2302.09736","title":"STOA-VLP: Spatial-Temporal Modeling of Object and Action for Video-Language Pre-training","created":"2023-02-20","cited_by_count":5,"area":null},{"id":"2412.20964","title":"Hierarchical Banzhaf Interaction for General Video-Language Representation Learning","created":"2024-12-30","cited_by_count":4,"area":null},{"id":"2504.07594","title":"Extending Visual Dynamics for Video-to-Music Generation","created":"2025-04-10","cited_by_count":4,"area":null},{"id":"2304.02080","title":"Scalable and Accurate Self-supervised Multimodal Representation Learning without Aligned Video and Text Data","created":"2023-04-04","cited_by_count":3,"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":"2306.12559","title":"Exploring the Role of Audio in Video Captioning","created":"2023-06-21","cited_by_count":3,"area":null},{"id":"2410.11702","title":"It's Just Another Day: Unique Video Captioning by Discriminative Prompting","created":"2024-10-15","cited_by_count":3,"area":null},{"id":"2410.17098","title":"Activity Recognition on Avatar-Anonymized Datasets with Masked Differential Privacy","created":"2024-10-22","cited_by_count":3,"area":null},{"id":"2503.01201","title":"Parameter-free Video Segmentation for Vision and Language Understanding","created":"2025-03-03","cited_by_count":3,"area":null},{"id":"2504.12157","title":"FocusedAD: Character-centric Movie Audio Description","created":"2025-04-16","cited_by_count":3,"area":null},{"id":"2510.10022","title":"Q-Adapter: Visual Query Adapter for Extracting Textually-related Features in Video Captioning","created":"2025-10-11","cited_by_count":3,"area":null},{"id":"2210.02762","title":"Vision Transformer Based Model for Describing a Set of Images as a Story","created":"2022-10-06","cited_by_count":2,"area":null},{"id":"2210.03941","title":"Learning Fine-Grained Visual Understanding for Video Question Answering via Decoupling Spatial-Temporal Modeling","created":"2022-10-08","cited_by_count":2,"area":null},{"id":"2303.00181","title":"Selectively Hard Negative Mining for Alleviating Gradient Vanishing in Image-Text Matching","created":"2023-03-01","cited_by_count":2,"area":null},{"id":"2401.04903","title":"SnapCap: Efficient Snapshot Compressive Video Captioning","created":"2024-01-10","cited_by_count":2,"area":null},{"id":"2401.12419","title":"Multi-modal News Understanding with Professionally Labelled Videos (ReutersViLNews)","created":"2024-01-23","cited_by_count":2,"area":null},{"id":"2405.08427","title":"Impact of Stickers on Multimodal Sentiment and Intent in Social Media: A New Task, Dataset and Baseline","created":"2024-05-14","cited_by_count":2,"area":null},{"id":"2507.17456","title":"Dynamic Scoring with Enhanced Semantics for Training-Free Human-Object Interaction Detection","created":"2025-07-23","cited_by_count":2,"area":null},{"id":"2512.21015","title":"FluencyVE: Marrying Temporal-Aware Mamba with Bypass Attention for Video Editing","created":"2025-12-24","cited_by_count":2,"area":"diffusion"},{"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":"2211.07210","title":"Grafting Pre-trained Models for Multimodal Headline Generation","created":"2022-11-14","cited_by_count":1,"area":null},{"id":"2212.10690","title":"METEOR Guided Divergence for Video Captioning","created":"2022-12-20","cited_by_count":1,"area":null},{"id":"2303.07545","title":"Implicit and Explicit Commonsense for Multi-sentence Video Captioning","created":"2023-03-14","cited_by_count":1,"area":null},{"id":"2310.07259","title":"Uncovering Hidden Connections: Iterative Search and Reasoning for Video-grounded Dialog","created":"2023-10-11","cited_by_count":1,"area":null}],"next_cursor":"100"}