{"total":138,"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":"2111.10337","title":"Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions","created":"2021-11-19","cited_by_count":226,"area":null},{"id":"2310.10647","title":"A Survey on Video Diffusion Models","created":"2023-10-16","cited_by_count":206,"area":"diffusion"},{"id":"2403.09630","title":"GenAD: Generalized Predictive Model for Autonomous Driving","created":"2024-03-14","cited_by_count":150,"area":"wm"},{"id":"2407.06358","title":"MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions","created":"2024-07-08","cited_by_count":146,"area":null},{"id":"2410.08260","title":"Koala-36M: A Large-scale Video Dataset Improving Consistency between Fine-grained Conditions and Video Content","created":"2024-10-10","cited_by_count":135,"area":null},{"id":"2411.00769","title":"GameGen-X: Interactive Open-world Game Video Generation","created":"2024-11-01","cited_by_count":128,"area":"wm"},{"id":"2406.15704","title":"video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models","created":"2024-06-22","cited_by_count":102,"area":null},{"id":"2303.07284","title":"Align and Attend: Multimodal Summarization with Dual Contrastive Losses","created":"2023-03-13","cited_by_count":65,"area":null},{"id":"2104.00332","title":"UC2: Universal Cross-lingual Cross-modal Vision-and-Language Pre-training","created":"2021-04-01","cited_by_count":64,"area":null},{"id":"2104.12671","title":"Multimodal Clustering Networks for Self-supervised Learning from Unlabeled Videos","created":"2021-04-26","cited_by_count":62,"area":null},{"id":"2106.01045","title":"Cascade versus Direct Speech Translation: Do the Differences Still Make a Difference?","created":"2021-06-02","cited_by_count":54,"area":null},{"id":"2312.02702","title":"Neural Sign Actors: A diffusion model for 3D sign language production from text","created":"2023-12-05","cited_by_count":49,"area":"diffusion"},{"id":"2408.14469","title":"Grounded Multi-Hop VideoQA in Long-Form Egocentric Videos","created":"2024-08-26","cited_by_count":45,"area":null},{"id":"2305.11095","title":"Prompting the Hidden Talent of Web-Scale Speech Models for Zero-Shot Task Generalization","created":"2023-05-18","cited_by_count":43,"area":null},{"id":"2309.15800","title":"Exploring Speech Recognition, Translation, and Understanding with Discrete Speech Units: A Comparative Study","created":"2023-09-27","cited_by_count":42,"area":null},{"id":"2108.13327","title":"N24News: A New Dataset for Multimodal News Classification","created":"2021-08-30","cited_by_count":40,"area":null},{"id":"2203.12515","title":"A Survey on Cross-Lingual Summarization","created":"2022-03-23","cited_by_count":38,"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":"2411.15262","title":"MovieBench: A Hierarchical Movie Level Dataset for Long Video Generation","created":"2024-11-22","cited_by_count":36,"area":"diffusion"},{"id":"2212.10525","title":"SLUE Phase-2: A Benchmark Suite of Diverse Spoken Language Understanding Tasks","created":"2022-12-20","cited_by_count":35,"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":"2109.02401","title":"Vision Guided Generative Pre-trained Language Models for Multimodal Abstractive Summarization","created":"2021-09-06","cited_by_count":32,"area":null},{"id":"2301.06782","title":"A Large-Scale Outdoor Multi-modal Dataset and Benchmark for Novel View Synthesis and Implicit Scene Reconstruction","created":"2023-01-17","cited_by_count":32,"area":null},{"id":"2107.02268","title":"Instant One-Shot Word-Learning for Context-Specific Neural Sequence-to-Sequence Speech Recognition","created":"2021-07-05","cited_by_count":30,"area":null},{"id":"2310.20436","title":"SignAvatars: A Large-scale 3D Sign Language Holistic Motion Dataset and Benchmark","created":"2023-10-31","cited_by_count":29,"area":null},{"id":"2302.00389","title":"Multimodality Representation Learning: A Survey on Evolution, Pretraining and Its Applications","created":"2023-02-01","cited_by_count":27,"area":"lr"},{"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":"2109.05199","title":"A Survey on Multi-modal Summarization","created":"2021-09-11","cited_by_count":26,"area":null},{"id":"2110.06263","title":"Speech Summarization using Restricted Self-Attention","created":"2021-10-12","cited_by_count":23,"area":null},{"id":"2203.09866","title":"Under the Morphosyntactic Lens: A Multifaceted Evaluation of Gender Bias in Speech Translation","created":"2022-03-18","cited_by_count":23,"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":"2310.05863","title":"Fine-grained Audio-Visual Joint Representations for Multimodal Large Language Models","created":"2023-10-09","cited_by_count":21,"area":"mllm"},{"id":"2406.16808","title":"Exploring the Capability of Mamba in Speech Applications","created":"2024-06-24","cited_by_count":20,"area":"ssm"},{"id":"2105.09601","title":"See, Hear, Read: Leveraging Multimodality with Guided Attention for Abstractive Text Summarization","created":"2021-05-20","cited_by_count":18,"area":null},{"id":"2206.04523","title":"Face-Dubbing++: Lip-Synchronous, Voice Preserving Translation of Videos","created":"2022-06-09","cited_by_count":18,"area":null},{"id":"2405.13684","title":"CrossCheckGPT: Universal Hallucination Ranking for Multimodal Foundation Models","created":"2024-05-22","cited_by_count":18,"area":null},{"id":"2104.11710","title":"Beyond Voice Activity Detection: Hybrid Audio Segmentation for Direct Speech Translation","created":"2021-04-23","cited_by_count":17,"area":null},{"id":"2409.02413","title":"Abstractive Text Summarization: State of the Art, Challenges, and Improvements","created":"2024-09-04","cited_by_count":17,"area":null},{"id":"2303.16501","title":"AVFormer: Injecting Vision into Frozen Speech Models for Zero-Shot AV-ASR","created":"2023-03-29","cited_by_count":16,"area":null},{"id":"2103.03233","title":"An Empirical Study of End-to-end Simultaneous Speech Translation Decoding Strategies","created":"2021-03-04","cited_by_count":14,"area":null},{"id":"2212.07672","title":"Summary-Oriented Vision Modeling for Multimodal Abstractive Summarization","created":"2022-12-15","cited_by_count":14,"area":null},{"id":"2410.01036","title":"MOSEL: 950,000 Hours of Speech Data for Open-Source Speech Foundation Model Training on EU Languages","created":"2024-10-01","cited_by_count":14,"area":null},{"id":"2107.11851","title":"Transcript to Video: Efficient Clip Sequencing from Texts","created":"2021-07-25","cited_by_count":13,"area":null},{"id":"2206.07684","title":"AVATAR: Unconstrained Audiovisual Speech Recognition","created":"2022-06-15","cited_by_count":13,"area":null},{"id":"2407.20962","title":"MMTrail: A Multimodal Trailer Video Dataset with Language and Music Descriptions","created":"2024-07-30","cited_by_count":13,"area":null},{"id":"2509.08621","title":"AdsQA: Towards Advertisement Video Understanding","created":"2025-09-10","cited_by_count":13,"area":null},{"id":"2104.04182","title":"FIBER: Fill-in-the-Blanks as a Challenging Video Understanding Evaluation Framework","created":"2021-04-09","cited_by_count":12,"area":null},{"id":"2210.04829","title":"Hierarchical3D Adapters for Long Video-to-text Summarization","created":"2022-10-10","cited_by_count":12,"area":null},{"id":"2302.06560","title":"Large Scale Multi-Lingual Multi-Modal Summarization Dataset","created":"2023-02-13","cited_by_count":12,"area":null},{"id":"2306.04216","title":"MMSum: A Dataset for Multimodal Summarization and Thumbnail Generation of Videos","created":"2023-06-07","cited_by_count":12,"area":null},{"id":"2406.10221","title":"Long Story Short: Story-level Video Understanding from 20K Short Films","created":"2024-06-14","cited_by_count":12,"area":"mllm"},{"id":"2506.07016","title":"MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks","created":"2025-06-08","cited_by_count":12,"area":"mllm"},{"id":"2201.08054","title":"VISA: An Ambiguous Subtitles Dataset for Visual Scene-Aware Machine Translation","created":"2022-01-20","cited_by_count":11,"area":null},{"id":"2303.00978","title":"Leveraging Large Text Corpora for End-to-End Speech Summarization","created":"2023-03-02","cited_by_count":11,"area":null},{"id":"2502.08279","title":"What Is That Talk About? A Video-to-Text Summarization Dataset for Scientific Presentations","created":"2025-02-12","cited_by_count":11,"area":null},{"id":"2305.05496","title":"Exploiting Pseudo Image Captions for Multimodal Summarization","created":"2023-05-09","cited_by_count":10,"area":"mllm"},{"id":"2111.08201","title":"Attention-based Multi-hypothesis Fusion for Speech Summarization","created":"2021-11-16","cited_by_count":9,"area":null},{"id":"2305.18326","title":"BigVideo: A Large-scale Video Subtitle Translation Dataset for Multimodal Machine Translation","created":"2023-05-23","cited_by_count":9,"area":null},{"id":"2312.01053","title":"End-to-End Speech-to-Text Translation: A Survey","created":"2023-12-02","cited_by_count":9,"area":null},{"id":"2501.00958","title":"2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining","created":"2025-01-01","cited_by_count":9,"area":"mllm"},{"id":"2111.04823","title":"Cascaded Multilingual Audio-Visual Learning from Videos","created":"2021-11-08","cited_by_count":8,"area":null},{"id":"2203.14456","title":"3MASSIV: Multilingual, Multimodal and Multi-Aspect dataset of Social Media Short Videos","created":"2022-03-28","cited_by_count":8,"area":null},{"id":"2401.11654","title":"ActionHub: A Large-scale Action Video Description Dataset for Zero-shot Action Recognition","created":"2024-01-22","cited_by_count":8,"area":null},{"id":"2508.07470","title":"AURA: A Fine-Grained Benchmark and Decomposed Metric for Audio-Visual Reasoning","created":"2025-08-10","cited_by_count":8,"area":"lr"},{"id":"2107.06246","title":"Between Flexibility and Consistency: Joint Generation of Captions and Subtitles","created":"2021-07-13","cited_by_count":7,"area":null},{"id":"2210.08992","title":"Language-agnostic Code-Switching in Sequence-To-Sequence Speech Recognition","created":"2022-10-17","cited_by_count":7,"area":null},{"id":"2211.04534","title":"Going for GOAL: A Resource for Grounded Football Commentaries","created":"2022-11-08","cited_by_count":7,"area":null},{"id":"2306.04233","title":"Transfer Learning from Pre-trained Language Models Improves End-to-End Speech Summarization","created":"2023-06-07","cited_by_count":7,"area":null},{"id":"2306.13968","title":"Fusing Multimodal Signals on Hyper-complex Space for Extreme Abstractive Text Summarization (TL;DR) of Scientific Contents","created":"2023-06-24","cited_by_count":7,"area":null},{"id":"2104.00285","title":"CUPID: Adaptive Curation of Pre-training Data for Video-and-Language Representation Learning","created":"2021-04-01","cited_by_count":6,"area":null},{"id":"2107.06546","title":"ZR-2021VG: Zero-Resource Speech Challenge, Visually-Grounded Language Modelling track, 2021 edition","created":"2021-07-14","cited_by_count":6,"area":null},{"id":"2310.03311","title":"Deep Variational Multivariate Information Bottleneck -- A Framework for Variational Losses","created":"2023-10-05","cited_by_count":6,"area":null},{"id":"2405.12669","title":"A Survey on Multi-modal Machine Translation: Tasks, Methods and Challenges","created":"2024-05-21","cited_by_count":6,"area":null},{"id":"2406.05968","title":"Prompting Large Language Models with Audio for General-Purpose Speech Summarization","created":"2024-06-10","cited_by_count":6,"area":"lr"},{"id":"2512.09841","title":"ChronusOmni: Improving Time Awareness of Omni Large Language Models","created":"2025-12-10","cited_by_count":6,"area":null},{"id":"2112.00775","title":"Routing with Self-Attention for Multimodal Capsule Networks","created":"2021-12-01","cited_by_count":5,"area":null},{"id":"2306.09922","title":"Learning to Summarize and Answer Questions about a Virtual Robot's Past Actions","created":"2023-06-16","cited_by_count":5,"area":null},{"id":"2401.06806","title":"AugSumm: towards generalizable speech summarization using synthetic labels from large language model","created":"2024-01-10","cited_by_count":5,"area":null},{"id":"2408.09333","title":"SkyScript-100M: 1,000,000,000 Pairs of Scripts and Shooting Scripts for Short Drama","created":"2024-08-18","cited_by_count":5,"area":null},{"id":"2409.12370","title":"Robust Audiovisual Speech Recognition Models with Mixture-of-Experts","created":"2024-09-19","cited_by_count":5,"area":"moe"},{"id":"2410.03007","title":"FastAdaSP: Multitask-Adapted Efficient Inference for Large Speech Language Model","created":"2024-10-03","cited_by_count":5,"area":"inference"},{"id":"2504.08024","title":"Summarizing Speech: A Comprehensive Survey","created":"2025-04-10","cited_by_count":5,"area":null},{"id":"2504.15066","title":"Chinese-LiPS: A Chinese audio-visual speech recognition dataset with Lip-reading and Presentation Slides","created":"2025-04-21","cited_by_count":5,"area":null},{"id":"2104.14470","title":"Impact of Encoding and Segmentation Strategies on End-to-End Simultaneous Speech Translation","created":"2021-04-29","cited_by_count":4,"area":null},{"id":"2305.14652","title":"Denoising Bottleneck with Mutual Information Maximization for Video Multimodal Fusion","created":"2023-05-24","cited_by_count":4,"area":null},{"id":"2307.08217","title":"BASS: Block-wise Adaptation for Speech Summarization","created":"2023-07-17","cited_by_count":4,"area":null},{"id":"2406.11049","title":"Reconsidering Sentence-Level Sign Language Translation","created":"2024-06-16","cited_by_count":4,"area":null},{"id":"2407.02005","title":"An End-to-End Speech Summarization Using Large Language Model","created":"2024-07-02","cited_by_count":4,"area":null},{"id":"2505.20638","title":"Music Audio-Visual Question Answering Requires Specialized Multimodal Designs","created":"2025-05-27","cited_by_count":4,"area":"mllm"},{"id":"2506.08633","title":"Approaching Dialogue State Tracking via Aligning Speech Encoders and LLMs","created":"2025-06-10","cited_by_count":4,"area":null},{"id":"2104.11560","title":"Weakly-supervised Multi-task Learning for Multimodal Affect Recognition","created":"2021-04-23","cited_by_count":3,"area":null},{"id":"2203.06671","title":"Summarizing a virtual robot's past actions in natural language","created":"2022-03-13","cited_by_count":3,"area":null},{"id":"2210.03625","title":"C2KD: Cross-Lingual Cross-Modal Knowledge Distillation for Multilingual Text-Video Retrieval","created":"2022-10-07","cited_by_count":3,"area":"distill"},{"id":"2302.14030","title":"Multimodal Speech Recognition for Language-Guided Embodied Agents","created":"2023-02-27","cited_by_count":3,"area":null},{"id":"2303.10160","title":"Visual Information Matters for ASR Error Correction","created":"2023-03-16","cited_by_count":3,"area":null},{"id":"2306.00208","title":"Strategies for improving low resource speech to text translation relying on pre-trained ASR models","created":"2023-05-31","cited_by_count":3,"area":null},{"id":"2306.12559","title":"Exploring the Role of Audio in Video Captioning","created":"2023-06-21","cited_by_count":3,"area":null},{"id":"2310.05060","title":"DeVAn: Dense Video Annotation for Video-Language Models","created":"2023-10-08","cited_by_count":3,"area":"mllm"},{"id":"2310.20201","title":"Video-Helpful Multimodal Machine Translation","created":"2023-10-31","cited_by_count":3,"area":null}],"next_cursor":"100"}