中文
相关论文

相关论文: MM-Narrator: Narrating Long-form Videos with Multi…

200 篇论文

Traditional video summarization methods generate fixed video representations regardless of user interest. Therefore such methods limit users' expectations in content search and exploration scenarios. Multi-modal video summarization is one…

计算机视觉与模式识别 · 计算机科学 2021-04-27 Jia-Hong Huang , Luka Murn , Marta Mrak , Marcel Worring

Recent advances in text-to-audio (TTA) generation excel at synthesizing short audio clips but struggle with long-form narrative audio, which requires temporal coherence and compositional reasoning. To address this gap, we propose…

计算机视觉与模式识别 · 计算机科学 2025-10-06 Yuxin Guo , Teng Wang , Yuying Ge , Shijie Ma , Yixiao Ge , Wei Zou , Ying Shan

Large language models (LMs) are typically adapted to improve performance on new contexts (\eg text prompts that define new tasks or domains) through fine-tuning or prompting. However, there is an accuracy compute tradeoff -- fine-tuning…

机器学习 · 计算机科学 2024-11-12 Tong Chen , Hao Fang , Patrick Xia , Xiaodong Liu , Benjamin Van Durme , Luke Zettlemoyer , Jianfeng Gao , Hao Cheng

Audio Descriptions (AD) are essential for making visual content accessible to individuals with visual impairments. Recent works have shown a promising step towards automating AD, but they have been limited to describing high-quality movie…

多媒体 · 计算机科学 2025-11-13 Lipisha Chaudhary , Trisha Mittal , Subhadra Gopalakrishnan , Ifeoma Nwogu , Jaclyn Pytlarz

Large Multimodal Models (LMMs) have demonstrated exceptional performance in video captioning tasks, particularly for short videos. However, as the length of the video increases, generating long, detailed captions becomes a significant…

计算机视觉与模式识别 · 计算机科学 2025-03-04 Hongchen Wei , Zhihong Tan , Yaosi Hu , Chang Wen Chen , Zhenzhong Chen

Audio Descriptions (ADs) convey essential on-screen information, allowing visually impaired audiences to follow videos. To be effective, ADs must form a coherent sequence that helps listeners to visualise the unfolding scene, rather than…

计算机视觉与模式识别 · 计算机科学 2025-10-30 Eshika Khandelwal , Junyu Xie , Tengda Han , Max Bain , Arsha Nagrani , Andrew Zisserman , Gül Varol , Makarand Tapaswi

This paper presents Audio-Visual LLM, a Multimodal Large Language Model that takes both visual and auditory inputs for holistic video understanding. A key design is the modality-augmented training, which involves the integration of…

计算机视觉与模式识别 · 计算机科学 2023-12-15 Fangxun Shu , Lei Zhang , Hao Jiang , Cihang Xie

Large Language Models(LLMs) have revolutionized text generation and multimodal perception,but their capabilities in 3D content generation remain underexplored. Existing methods compromise by producing either low-resolution meshes or coarse…

计算机视觉与模式识别 · 计算机科学 2026-05-18 Junming Huang , Chi Wang , Letian Li , Guangkai Xu , Donglin Huang , Hao Chen , Qiang Dai , Weiwei Xu

This paper addresses the critical and underexplored challenge of long video understanding with low computational budgets. We propose LongVideo-R1, an active, reasoning-equipped multimodal large language model (MLLM) agent designed for…

计算机视觉与模式识别 · 计算机科学 2026-04-16 Jihao Qiu , Lingxi Xie , Xinyue Huo , Qi Tian , Qixiang Ye

With the explosive growth of digital entertainment, automated video summarization has become indispensable for applications such as content indexing, personalized recommendation, and efficient media archiving. Automatic synopsis generation…

计算机视觉与模式识别 · 计算机科学 2026-03-16 Yizhi Li , Xiaohan Chen , Miao Jiang , Wentao Tang , Gaoang Wang

We introduce Audio-Agent, a multimodal framework for audio generation, editing and composition based on text or video inputs. Conventional approaches for text-to-audio (TTA) tasks often make single-pass inferences from text descriptions.…

声音 · 计算机科学 2025-01-15 Zixuan Wang , Chi-Keung Tang , Yu-Wing Tai

Video storytelling is engaging multimedia content that utilizes video and its accompanying narration to attract the audience, where a key challenge is creating narrations for recorded visual scenes. Previous studies on dense video…

多媒体 · 计算机科学 2024-12-31 Dingyi Yang , Chunru Zhan , Ziheng Wang , Biao Wang , Tiezheng Ge , Bo Zheng , Qin Jin

Visual storytelling is an emerging field that combines images and narratives to create engaging and contextually rich stories. Despite its potential, generating coherent and emotionally resonant visual stories remains challenging due to the…

计算机视觉与模式识别 · 计算机科学 2024-07-04 Xiaochuan Lin , Xiangyong Chen

Large Multimodal Models (LMMs) have demonstrated impressive performance in short video understanding tasks but face great challenges when applied to long video understanding. In contrast, Large Language Models (LLMs) exhibit outstanding…

计算机视觉与模式识别 · 计算机科学 2024-10-03 Hongchen Wei , Zhenzhong Chen

Instructional videos are a common source for learning text-video or even multimodal representations by leveraging subtitles extracted with automatic speech recognition systems (ASR) from the audio signal in the videos. However, in contrast…

计算机视觉与模式识别 · 计算机科学 2024-09-10 Nina Shvetsova , Anna Kukleva , Xudong Hong , Christian Rupprecht , Bernt Schiele , Hilde Kuehne

We propose VideoPerceiver, a novel video multimodal large language model (VMLLM) that enhances fine-grained perception in video understanding, addressing VMLLMs' limited ability to reason about brief actions in short clips or rare transient…

计算机视觉与模式识别 · 计算机科学 2025-11-25 Fufangchen Zhao , Liao Zhang , Daiqi Shi , Yuanjun Gao , Chen Ye , Yang Cai , Jian Gao , Danfeng Yan

This paper introduces MiniGPT4-Video, a multimodal Large Language Model (LLM) designed specifically for video understanding. The model is capable of processing both temporal visual and textual data, making it adept at understanding the…

计算机视觉与模式识别 · 计算机科学 2024-04-05 Kirolos Ataallah , Xiaoqian Shen , Eslam Abdelrahman , Essam Sleiman , Deyao Zhu , Jian Ding , Mohamed Elhoseiny

Current Text-to-audio (TTA) models mainly use coarse text descriptions as inputs to generate audio, which hinders models from generating audio with fine-grained control of content and style. Some studies try to improve the granularity by…

音频与语音处理 · 电气工程与系统科学 2025-04-01 Yuanyuan Wang , Hangting Chen , Dongchao Yang , Zhiyong Wu , Xixin Wu

Recent video and language pretraining frameworks lack the ability to generate sentences. We present Multimodal Video Generative Pretraining (MV-GPT), a new pretraining framework for learning from unlabelled videos which can be effectively…

计算机视觉与模式识别 · 计算机科学 2022-05-11 Paul Hongsuck Seo , Arsha Nagrani , Anurag Arnab , Cordelia Schmid

Despite an exciting new wave of multimodal machine learning models, current approaches still struggle to interpret the complex contextual relationships between the different modalities present in videos. Going beyond existing methods that…

计算机视觉与模式识别 · 计算机科学 2023-09-20 Laura Hanu , Anita L. Verő , James Thewlis