{"total":105,"rows":[{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040,"area":null},{"id":"2307.06942","title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","created":"2023-07-13","cited_by_count":497,"area":null},{"id":"2402.17177","title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","created":"2024-02-27","cited_by_count":477,"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":"2403.15377","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","created":"2024-03-22","cited_by_count":317,"area":null},{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206,"area":null},{"id":"2305.11846","title":"Any-to-Any Generation via Composable Diffusion","created":"2023-05-19","cited_by_count":204,"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":"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":"2305.10874","title":"Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation","created":"2023-05-18","cited_by_count":154,"area":null},{"id":"2407.00634","title":"Tarsier: Recipes for Training and Evaluating Large Video Description Models","created":"2024-06-30","cited_by_count":141,"area":null},{"id":"2410.03051","title":"AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark","created":"2024-10-04","cited_by_count":140,"area":null},{"id":"2501.03218","title":"Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction","created":"2025-01-06","cited_by_count":127,"area":null},{"id":"2305.11172","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","created":"2023-05-18","cited_by_count":118,"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":"2404.17176","title":"MovieChat+: Question-aware Sparse Memory for Long Video Question Answering","created":"2024-04-26","cited_by_count":73,"area":null},{"id":"2309.11523","title":"RMT: Retentive Networks Meet Vision Transformers","created":"2023-09-20","cited_by_count":68,"area":null},{"id":"2304.14407","title":"ChatVideo: A Tracklet-centric Multimodal and Versatile Video Understanding System","created":"2023-04-27","cited_by_count":65,"area":null},{"id":"2408.14180","title":"I2EBench: A Comprehensive Benchmark for Instruction-based Image Editing","created":"2024-08-26","cited_by_count":63,"area":null},{"id":"2412.11959","title":"Gramian Multimodal Representation Learning and Alignment","created":"2024-12-16","cited_by_count":54,"area":null},{"id":"2304.04227","title":"Video ChatCaptioner: Towards Enriched Spatiotemporal Descriptions","created":"2023-04-09","cited_by_count":42,"area":null},{"id":"2303.12060","title":"VideoXum: Cross-modal Visual and Textural Summarization of Videos","created":"2023-03-21","cited_by_count":41,"area":null},{"id":"2406.05615","title":"Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectives","created":"2024-06-09","cited_by_count":37,"area":null},{"id":"2409.17531","title":"SimVG: A Simple Framework for Visual Grounding with Decoupled Multi-modal Fusion","created":"2024-09-26","cited_by_count":36,"area":null},{"id":"2512.03627","title":"MemVerse: Multimodal Memory for Lifelong Learning Agents","created":"2025-12-03","cited_by_count":35,"area":null},{"id":"2512.10945","title":"MeViS: A Multi-Modal Dataset for Referring Motion Expression Video Segmentation","created":"2025-12-11","cited_by_count":35,"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":"2402.02460","title":"Review of multimodal machine learning approaches in healthcare","created":"2024-02-04","cited_by_count":31,"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":"2503.00936","title":"IteRPrimE: Zero-shot Referring Image Segmentation with Iterative Grad-CAM Refinement and Primary Word Emphasis","created":"2025-03-02","cited_by_count":26,"area":null},{"id":"2305.06002","title":"InfoMetIC: An Informative Metric for Reference-free Image Caption Evaluation","created":"2023-05-10","cited_by_count":25,"area":null},{"id":"2407.16658","title":"EgoCVR: An Egocentric Benchmark for Fine-Grained Composed Video Retrieval","created":"2024-07-23","cited_by_count":21,"area":null},{"id":"2501.00513","title":"CaReBench: A Fine-Grained Benchmark for Video Captioning and Retrieval","created":"2024-12-31","cited_by_count":19,"area":null},{"id":"2507.11336","title":"UGC-VideoCaptioner: An Omni UGC Video Detail Caption Model and New Benchmarks","created":"2025-07-15","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":"2401.06395","title":"ModaVerse: Efficiently Transforming Modalities with LLMs","created":"2024-01-12","cited_by_count":18,"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":"2407.15350","title":"WTS: A Pedestrian-Centric Traffic Video Dataset for Fine-grained Spatial-Temporal Understanding","created":"2024-07-22","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":"2311.14199","title":"A Systematic Review of Deep Learning-based Research on Radiology Report Generation","created":"2023-11-23","cited_by_count":14,"area":null},{"id":"2409.06299","title":"Enhancing Long Video Understanding via Hierarchical Event-Based Memory","created":"2024-09-10","cited_by_count":14,"area":null},{"id":"2412.13845","title":"Do Language Models Understand Time?","created":"2024-12-18","cited_by_count":14,"area":null},{"id":"2309.06799","title":"When Geoscience Meets Foundation Models: Towards General Geoscience Artificial Intelligence System","created":"2023-09-13","cited_by_count":13,"area":null},{"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":"2502.13363","title":"Pretrained Image-Text Models are Secretly Video Captioners","created":"2025-02-19","cited_by_count":11,"area":null},{"id":"2405.13911","title":"TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment","created":"2024-05-22","cited_by_count":10,"area":null},{"id":"2504.05541","title":"Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting","created":"2025-04-07","cited_by_count":10,"area":null},{"id":"2504.07836","title":"AerialVG: A Challenging Benchmark for Aerial Visual Grounding by Exploring Positional Relations","created":"2025-04-10","cited_by_count":10,"area":null},{"id":"2308.05822","title":"Encode-Store-Retrieve: Augmenting Human Memory through Language-Encoded Egocentric Perception","created":"2023-08-10","cited_by_count":9,"area":null},{"id":"2410.20034","title":"Sensor2Text: Enabling Natural Language Interactions for Daily Activity Tracking Using Wearable Sensors","created":"2024-10-26","cited_by_count":9,"area":null},{"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":"2307.03153","title":"MultiVENT: Multilingual Videos of Events with Aligned Natural Text","created":"2023-07-06","cited_by_count":7,"area":null},{"id":"2312.06363","title":"MMICT: Boosting Multi-Modal Fine-Tuning with In-Context Examples","created":"2023-12-11","cited_by_count":7,"area":null},{"id":"2411.12593","title":"AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction","created":"2024-11-19","cited_by_count":7,"area":null},{"id":"2504.20185","title":"AI Supply Chains: An Emerging Ecosystem of AI Actors, Products, and Services","created":"2025-04-28","cited_by_count":7,"area":null},{"id":"2511.21331","title":"The More, the Merrier: Contrastive Fusion for Higher-Order Multimodal Alignment","created":"2025-11-26","cited_by_count":7,"area":null},{"id":"2509.02969","title":"VQualA 2025 Challenge on Engagement Prediction for Short Videos: Methods and Results","created":"2025-09-03","cited_by_count":6,"area":null},{"id":"2606.23327","title":"VideoAgent: All-in-One Framework for Video Understanding and Editing","created":"2026-06-22","cited_by_count":6,"area":null},{"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":"2405.00954","title":"X-Oscar: A Progressive Framework for High-quality Text-guided 3D Animatable Avatar Generation","created":"2024-05-02","cited_by_count":5,"area":null},{"id":"2507.00033","title":"Moment Sampling in Video LLMs for Long-Form Video QA","created":"2025-06-18","cited_by_count":5,"area":null},{"id":"2507.04815","title":"From Vision To Language through Graph of Events in Space and Time: An Explainable Self-supervised Approach","created":"2025-07-07","cited_by_count":5,"area":null},{"id":"2309.15857","title":"A Survey on Image-text Multimodal Models","created":"2023-09-23","cited_by_count":4,"area":null},{"id":"2402.09036","title":"Can Text-to-image Model Assist Multi-modal Learning for Visual Recognition with Visual Modality Missing?","created":"2024-02-14","cited_by_count":4,"area":null},{"id":"2410.00289","title":"Delving Deep into Engagement Prediction of Short Videos","created":"2024-09-30","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":"2509.04773","title":"Hybrid-Tower: Fine-grained Pseudo-query Interaction and Generation for Text-to-Video Retrieval","created":"2025-09-05","cited_by_count":4,"area":null},{"id":"2602.09507","title":"Towards Uniformity and Alignment for Multimodal Representation Learning","created":"2026-02-10","cited_by_count":4,"area":null},{"id":"2310.02894","title":"Human-centric Behavior Description in Videos: New Benchmark and Model","created":"2023-10-04","cited_by_count":3,"area":null},{"id":"2401.02052","title":"Encoder-Decoder Based Long Short-Term Memory (LSTM) Model for Video Captioning","created":"2023-10-02","cited_by_count":3,"area":null},{"id":"2406.05496","title":"Generalist Multimodal AI: A Review of Architectures, Challenges and Opportunities","created":"2024-06-08","cited_by_count":3,"area":null},{"id":"2408.11432","title":"T2VIndexer: A Generative Video Indexer for Efficient Text-Video Retrieval","created":"2024-08-21","cited_by_count":3,"area":null},{"id":"2505.13429","title":"Understanding Complexity in VideoQA via Visual Program Generation","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2506.21028","title":"TRIDENT: Tri-Modal Molecular Representation Learning with Taxonomic Annotations and Local Correspondence","created":"2025-06-26","cited_by_count":3,"area":null},{"id":"2305.16621","title":"A Reminder of its Brittleness: Language Reward Shaping May Hinder Learning for Instruction Following Agents","created":"2023-05-26","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":"2412.06413","title":"World-Consistent Data Generation for Vision-and-Language Navigation","created":"2024-12-09","cited_by_count":2,"area":null},{"id":"2501.18269","title":"MAMS: Model-Agnostic Module Selection Framework for Video Captioning","created":"2025-01-30","cited_by_count":2,"area":null},{"id":"2503.06820","title":"Towards Fine-Grained Video Question Answering","created":"2025-03-10","cited_by_count":2,"area":null},{"id":"2507.18552","title":"VideoMind: An Omni-Modal Video Dataset with Intent Grounding for Deep-Cognitive Video Understanding","created":"2025-07-24","cited_by_count":2,"area":null},{"id":"2510.10671","title":"Image-to-Video Transfer Learning based on Image-Language Foundation Models: A Comprehensive Survey","created":"2025-10-12","cited_by_count":2,"area":null},{"id":"2305.19871","title":"There is more to graphs than meets the eye: Learning universal features with self-supervision","created":"2023-05-31","cited_by_count":1,"area":null},{"id":"2312.00115","title":"A Video is Worth 10,000 Words: Training and Benchmarking with Diverse Captions for Better Long Video Retrieval","created":"2023-11-30","cited_by_count":1,"area":null},{"id":"2402.16769","title":"Unifying Latent and Lexicon Representations for Effective Video-Text Retrieval","created":"2024-02-26","cited_by_count":1,"area":null},{"id":"2406.16301","title":"UBiSS: A Unified Framework for Bimodal Semantic Summarization of Videos","created":"2024-06-24","cited_by_count":1,"area":null},{"id":"2411.14688","title":"Whats in a Video: Factorized Autoregressive Decoding for Online Dense Video Captioning","created":"2024-11-22","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":"2609.33800","title":"Binding Multiple Modalities via Multimodal Wasserstein Barycenter","created":"2026-09-27","cited_by_count":1,"area":null},{"id":"2310.12724","title":"Query-aware Long Video Localization and Relation Discrimination for Deep Video Understanding","created":"2023-10-19","cited_by_count":0,"area":null},{"id":"2409.00973","title":"IVGF: The Fusion-Guided Infrared and Visible General Framework","created":"2024-09-02","cited_by_count":0,"area":null},{"id":"2410.22233","title":"ContextIQ: A Multimodal Expert-Based Video Retrieval System for Contextual Advertising","created":"2024-10-29","cited_by_count":0,"area":null},{"id":"2504.02496","title":"Group-based Distinctive Image Captioning with Memory Difference Encoding and Attention","created":"2025-04-03","cited_by_count":0,"area":null},{"id":"2506.09953","title":"Outside Knowledge Conversational Video (OKCV) Dataset -- Dialoguing over Videos","created":"2025-06-11","cited_by_count":0,"area":null},{"id":"2507.11773","title":"Small Data Explainer -- The impact of small data methods in everyday life","created":"2025-07-15","cited_by_count":0,"area":null},{"id":"2510.13665","title":"Axial Neural Networks for Dimension-Free Foundation Models","created":"2025-10-15","cited_by_count":0,"area":null},{"id":"2512.07729","title":"Improving action classification with brain-inspired deep networks","created":"2025-12-08","cited_by_count":0,"area":null},{"id":"2512.17108","title":"Atom: Efficient On-Device Video-Language Pipelines Through Modular Reuse","created":"2025-12-18","cited_by_count":0,"area":null},{"id":"2606.06338","title":"StoryVideoQA: Scaling Deep Video Understanding with a Large-Scale, Multi-Genre and Auto-Generated Dataset","created":"2026-06-04","cited_by_count":0,"area":null}],"next_cursor":"100"}