{"total":121,"rows":[{"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":"2310.01852","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","created":"2023-10-03","cited_by_count":370,"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":"2407.00634","title":"Tarsier: Recipes for Training and Evaluating Large Video Description Models","created":"2024-06-30","cited_by_count":141,"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":"2406.15704","title":"video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models","created":"2024-06-22","cited_by_count":102,"area":null},{"id":"2410.05643","title":"TRACE: Temporal Grounding Video LLM via Causal Event Modeling","created":"2024-10-08","cited_by_count":89,"area":null},{"id":"2411.17040","title":"Multimodal Alignment and Fusion: A Survey","created":"2024-11-26","cited_by_count":74,"area":null},{"id":"2510.15870","title":"OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM","created":"2025-10-17","cited_by_count":59,"area":null},{"id":"2406.10729","title":"A Comprehensive Survey of Foundation Models in Medicine","created":"2024-06-15","cited_by_count":56,"area":null},{"id":"2410.18325","title":"AVHBench: A Cross-Modal Hallucination Benchmark for Audio-Visual Large Language Models","created":"2024-10-23","cited_by_count":56,"area":null},{"id":"2412.11959","title":"Gramian Multimodal Representation Learning and Alignment","created":"2024-12-16","cited_by_count":54,"area":null},{"id":"2411.19772","title":"LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos","created":"2024-11-29","cited_by_count":51,"area":null},{"id":"2311.05709","title":"OmniVec: Learning robust representations with cross modal sharing","created":"2023-11-07","cited_by_count":44,"area":null},{"id":"2405.19334","title":"LLMs Meet Multimodal Generation and Editing: A Survey","created":"2024-05-29","cited_by_count":35,"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":"2311.16081","title":"ViT-Lens: Towards Omni-modal Representations","created":"2023-11-27","cited_by_count":29,"area":null},{"id":"2405.10674","title":"From Sora What We Can See: A Survey of Text-to-Video Generation","created":"2024-05-17","cited_by_count":27,"area":null},{"id":"2505.19650","title":"Modality Curation: Building Universal Embeddings for Advanced Multimodal Information Retrieval","created":"2025-05-26","cited_by_count":26,"area":null},{"id":"2412.11694","title":"From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalities","created":"2024-12-16","cited_by_count":22,"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":"2503.19009","title":"Video-ColBERT: Contextualized Late Interaction for Text-to-Video Retrieval","created":"2025-03-24","cited_by_count":20,"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":"2408.00672","title":"ExpertAF: Expert Actionable Feedback from Video","created":"2024-08-01","cited_by_count":17,"area":null},{"id":"2410.11619","title":"MultiVENT 2.0: A Massive Multilingual Benchmark for Event-Centric Video Retrieval","created":"2024-10-15","cited_by_count":17,"area":null},{"id":"2412.13845","title":"Do Language Models Understand Time?","created":"2024-12-18","cited_by_count":14,"area":null},{"id":"2503.01725","title":"HarmonySet: A Comprehensive Dataset for Understanding Video-Music Semantic Alignment and Temporal Synchronization","created":"2025-03-03","cited_by_count":14,"area":null},{"id":"2407.06491","title":"VideoEval: Comprehensive Benchmark Suite for Low-Cost Evaluation of Video Foundation Model","created":"2024-07-09","cited_by_count":12,"area":null},{"id":"2311.08396","title":"Zero-shot audio captioning with audio-language model guidance and audio context keywords","created":"2023-11-14","cited_by_count":11,"area":null},{"id":"2312.10144","title":"Data-Efficient Multimodal Fusion on a Single GPU","created":"2023-12-15","cited_by_count":11,"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":"2407.12508","title":"MERLIN: Multimodal Embedding Refinement via LLM-based Iterative Navigation for Text-Video Retrieval-Rerank Pipeline","created":"2024-07-17","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":"2412.14056","title":"A Review of Multimodal Explainable Artificial Intelligence: Past, Present and Future","created":"2024-12-18","cited_by_count":9,"area":null},{"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":"2506.06144","title":"CLaMR: Contextualized Late-Interaction for Multimodal Content Retrieval","created":"2025-06-06","cited_by_count":9,"area":null},{"id":"2510.27571","title":"Towards Universal Video Retrieval: Generalizing Video Embedding via Synthesized Multimodal Pyramid Curriculum","created":"2025-10-31","cited_by_count":9,"area":null},{"id":"2503.18422","title":"Breaking the Encoder Barrier for Seamless Video-Language Understanding","created":"2025-03-24","cited_by_count":8,"area":null},{"id":"2505.20873","title":"Fork-Merge Decoding: Enhancing Multimodal Understanding in Audio-Visual Large Language Models","created":"2025-05-27","cited_by_count":8,"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":"2401.01823","title":"Detours for Navigating Instructional Videos","created":"2024-01-03","cited_by_count":7,"area":null},{"id":"2507.18531","title":"IntentVCNet: Bridging Spatio-Temporal Gaps for Intention-Oriented Controllable Video Captioning","created":"2025-07-24","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":"2409.19532","title":"Video DataFlywheel: Resolving the Impossible Data Trinity in Video-Language Understanding","created":"2024-09-29","cited_by_count":6,"area":null},{"id":"2503.09321","title":"DAVE: Diagnostic benchmark for Audio Visual Evaluation","created":"2025-03-12","cited_by_count":6,"area":null},{"id":"2503.14237","title":"Make Your Training Flexible: Towards Deployment-Efficient Video Models","created":"2025-03-18","cited_by_count":6,"area":null},{"id":"2504.06835","title":"LVC: A Lightweight Compression Framework for Enhancing VLMs in Long Video Understanding","created":"2025-04-09","cited_by_count":6,"area":null},{"id":"2506.23138","title":"VisualPrompter: Semantic-Aware Prompt Optimization with Visual Feedback for Text-to-Image Synthesis","created":"2025-06-29","cited_by_count":6,"area":null},{"id":"2508.12149","title":"MOVER: Multimodal Optimal Transport with Volume-based Embedding Regularization","created":"2025-08-16","cited_by_count":6,"area":null},{"id":"2512.09841","title":"ChronusOmni: Improving Time Awareness of Omni Large Language Models","created":"2025-12-10","cited_by_count":6,"area":null},{"id":"2406.02554","title":"Hear Me, See Me, Understand Me: Audio-Visual Autism Behavior Recognition","created":"2024-03-22","cited_by_count":5,"area":null},{"id":"2406.09412","title":"Explore the Limits of Omni-modal Pretraining at Scale","created":"2024-06-13","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":"2601.18525","title":"Closing the Modality Gap Aligns Group-Wise Semantics","created":"2026-01-26","cited_by_count":5,"area":null},{"id":"2605.17423","title":"Soap2Soap: Long Cinematic Video Remaking via Multi-Agent Collaboration","created":"2026-05-17","cited_by_count":5,"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":"2409.15672","title":"Language-based Audio Moment Retrieval","created":"2024-09-24","cited_by_count":4,"area":null},{"id":"2410.12018","title":"LocoMotion: Learning Motion-Focused Video-Language Representations","created":"2024-10-15","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":"2505.20920","title":"HuMoCon: Concept Discovery for Human Motion Understanding","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2506.08887","title":"DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval","created":"2025-06-10","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":"2409.00851","title":"Dissecting Temporal Understanding in Text-to-Audio Retrieval","created":"2024-09-01","cited_by_count":3,"area":null},{"id":"2504.03501","title":"LV-MAE: Learning Long Video Representations through Masked-Embedding Autoencoders","created":"2025-04-04","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":"2508.07312","title":"MobileViCLIP: An Efficient Video-Text Model for Mobile Devices","created":"2025-08-10","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":"2510.18346","title":"AV-Master: Dual-Path Comprehensive Perception Makes Better Audio-Visual Question Answering","created":"2025-10-21","cited_by_count":3,"area":null},{"id":"2511.12034","title":"Calibrated Multimodal Representation Learning with Missing Modalities","created":"2025-11-15","cited_by_count":3,"area":null},{"id":"2605.17360","title":"Omni-DuplexEval: Evaluating Real-time Duplex Omni-modal Interaction","created":"2026-05-17","cited_by_count":3,"area":null},{"id":"2310.11830","title":"CLARA: Multilingual Contrastive Learning for Audio Representation Acquisition","created":"2023-10-18","cited_by_count":2,"area":null},{"id":"2406.06201","title":"2DP-2MRC: 2-Dimensional Pointer-based Machine Reading Comprehension Method for Multimodal Moment Retrieval","created":"2024-06-10","cited_by_count":2,"area":null},{"id":"2408.11641","title":"Estimated Audio-Caption Correspondences Improve Language-Based Audio Retrieval","created":"2024-08-21","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":"2502.12623","title":"DeepResonance: Enhancing Multimodal Music Understanding via Music-centric Multi-way Instruction Tuning","created":"2025-02-18","cited_by_count":2,"area":null},{"id":"2503.18637","title":"Unbiasing through Textual Descriptions: Mitigating Representation Bias in Video Benchmarks","created":"2025-03-24","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":"2601.22508","title":"CoVA: Text-Guided Composed Video Retrieval for Audio-Visual Content","created":"2026-01-30","cited_by_count":2,"area":null},{"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":"2608.09572","title":"Hyperbolic Multimodal Continual Learning","created":"2026-08-10","cited_by_count":2,"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":"2412.01488","title":"TACO: Training-free Sound Prompted Segmentation via Semantically Constrained Audio-visual CO-factorization","created":"2024-12-02","cited_by_count":1,"area":null},{"id":"2502.08234","title":"Learning Human Skill Generators at Key-Step Levels","created":"2025-02-12","cited_by_count":1,"area":null},{"id":"2504.01591","title":"Leveraging Modality Tags for Enhanced Cross-Modal Video Retrieval","created":"2025-04-02","cited_by_count":1,"area":null},{"id":"2505.23952","title":"Leveraging Auxiliary Information in Text-to-Video Retrieval: A Review","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2511.01617","title":"Vote-in-Context: Turning VLMs into Zero-Shot Rank Fusers","created":"2025-11-03","cited_by_count":1,"area":null},{"id":"2602.20046","title":"Closing the gap in multimodal medical representation alignment","created":"2026-02-23","cited_by_count":1,"area":null},{"id":"2603.08202","title":"MM-TS: Multi-Modal Temperature and Margin Schedules for Contrastive Learning with Long-Tail Data","created":"2026-03-09","cited_by_count":1,"area":null},{"id":"2605.26641","title":"OmniRetriever: Any-to-Any Audio-Video-Text Retrieval via Fusion-as-Teacher Distillation","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2606.09641","title":"MAVIS: Multi-Agent Video Retrieval via Structured Video Understanding","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2607.05090","title":"Be Indiscrete: The Benefits of Learning Continuous Spine Degeneration Severity Scores","created":"2026-07-06","cited_by_count":1,"area":null},{"id":"2609.00551","title":"EM^2Mem: Event-Centric Multimodal Memory for Large Language Models","created":"2026-09-01","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}],"next_cursor":"100"}