English
Related papers

Related papers: MAViS: A Multi-Agent Framework for Long-Sequence V…

200 papers

Retrieval-augmented generation from videos requires systems to retrieve relevant audiovisual evidence from large corpora and synthesize it into coherent, attributed text. Current approaches struggle at both ends: retrieval methods fail on…

Diffusion models have demonstrated great success in text-to-video (T2V) generation. However, existing methods may face challenges when handling complex (long) video generation scenarios that involve multiple objects or dynamic changes in…

Computer Vision and Pattern Recognition · Computer Science 2024-10-15 Ye Tian , Ling Yang , Haotian Yang , Yuan Gao , Yufan Deng , Jingmin Chen , Xintao Wang , Zhaochen Yu , Xin Tao , Pengfei Wan , Di Zhang , Bin Cui

Generative models have substantially expanded video generation capabilities, yet practical thought-to-video creation remains a multi-stage, multi-modal, and decision-intensive process. However, existing tools either hide intermediate…

Multimedia · Computer Science 2026-02-10 Zhuoyun Zheng , Yu Dong , Gaorong Liang , Guan Li , Guihua Shan , Shiyu Cheng , Dong Tian , Jianlong Zhou , Jie Liang

Visual presentations are vital for effective communication. Early attempts to automate their creation using deep learning often faced issues such as poorly organized layouts, inaccurate text summarization, and a lack of image understanding,…

Machine Learning · Computer Science 2025-09-03 Xiaojie Xu , Xinli Xu , Sirui Chen , Haoyu Chen , Fan Zhang , Ying-Cong Chen

Referring video object segmentation (RVOS) is a challenging task that requires the model to segment the object in a video given the language description. MeViS is a recently proposed dataset that contains motion expressions of the target…

Computer Vision and Pattern Recognition · Computer Science 2025-04-02 Haobo Yuan , Tao Zhang , Xiangtai Li , Lu Qi , Zilong Huang , Shilin Xu , Jiashi Feng , Ming-Hsuan Yang

Audio-visual generation is rapidly advancing from short clips to minute-long content, while existing evaluation protocols remain largely confined to short-form settings. Existing benchmarks primarily focus on 5--10 second text-conditioned…

Current audio generation conditioned by text or video focuses on aligning audio with text/video modalities. Despite excellent alignment results, these multimodal frameworks still cannot be directly applied to compelling movie storytelling…

Sound · Computer Science 2025-06-03 Zixuan Wang , Chi-Keung Tang , Yu-Wing Tai

Videos express highly structured spatio-temporal patterns of visual data. A video can be thought of as being governed by two factors: (i) temporally invariant (e.g., person identity), or slowly varying (e.g., activity), attribute-induced…

Computer Vision and Pattern Recognition · Computer Science 2018-03-26 Jiawei He , Andreas Lehrmann , Joseph Marino , Greg Mori , Leonid Sigal

Despite recent advancements in text-to-image generation, most existing methods struggle to create images with multiple objects and complex spatial relationships in the 3D world. To tackle this limitation, we introduce a generic AI system,…

Computer Vision and Pattern Recognition · Computer Science 2024-12-17 Yanbo Ding , Shaobin Zhuang , Kunchang Li , Zhengrong Yue , Yu Qiao , Yali Wang

Building a conversational embodied agent to execute real-life tasks has been a long-standing yet quite challenging research goal, as it requires effective human-agent communication, multi-modal understanding, long-range sequential decision…

Artificial Intelligence · Computer Science 2025-09-04 Kaizhi Zheng , Kaiwen Zhou , Jing Gu , Yue Fan , Jialu Wang , Zonglin Di , Xuehai He , Xin Eric Wang

Bridging vision and natural language is a longstanding goal in computer vision and multimedia research. While earlier works focus on generating a single-sentence description for visual content, recent works have studied paragraph…

Multimedia · Computer Science 2020-05-15 Junnan Li , Yongkang Wong , Qi Zhao , Mohan S. Kankanhalli

Automated movie creation requires coordinating multiple characters, modalities, and narrative elements across extended sequences -- a challenge that existing end-to-end approaches struggle to address effectively. We present…

Multimedia · Computer Science 2026-04-28 Tianyidan Xie , Zhentao Huang , Mingjie Wang , Xin Huang , Jun Zhou , Minglun Gong , Zili Yi

Recent advancements in visual generative models have enabled high-quality image and video generation, opening diverse applications. However, evaluating these models often demands sampling hundreds or thousands of images or videos, making…

Computer Vision and Pattern Recognition · Computer Science 2025-08-22 Fan Zhang , Shulin Tian , Ziqi Huang , Yu Qiao , Ziwei Liu

Recently, transformer-based approaches have shown promising results for semi-supervised video object segmentation. However, these approaches typically struggle on long videos due to increased GPU memory demands, as they frequently expand…

Computer Vision and Pattern Recognition · Computer Science 2024-09-27 Abdelrahman Shaker , Syed Talal Wasim , Martin Danelljan , Salman Khan , Ming-Hsuan Yang , Fahad Shahbaz Khan

Time series analysis underpins many real-world applications, yet existing time-series-specific methods and pretrained large-model-based approaches remain limited in integrating intuitive visual reasoning and generalizing across tasks with…

Artificial Intelligence · Computer Science 2026-02-04 Weilin Ruan , Yuxuan Liang

We present AniME, a director-oriented multi-agent system for automated long-form anime production, covering the full workflow from a story to the final video. The director agent keeps a global memory for the whole workflow, and coordinates…

Artificial Intelligence · Computer Science 2025-10-13 Lisai Zhang , Baohan Xu , Siqian Yang , Mingyu Yin , Jing Liu , Chao Xu , Siqi Wang , Yidi Wu , Yuxin Hong , Zihao Zhang , Yanzhang Liang , Yudong Jiang

Existing text-to-video diffusion models rely solely on text-only encoders for their pretraining. This limitation stems from the absence of large-scale multimodal prompt video datasets, resulting in a lack of visual grounding and restricting…

Computer Vision and Pattern Recognition · Computer Science 2024-07-10 Yuwei Fang , Willi Menapace , Aliaksandr Siarohin , Tsai-Shien Chen , Kuan-Chien Wang , Ivan Skorokhodov , Graham Neubig , Sergey Tulyakov

Recent text-to-video (T2V) generation methods have seen significant advancements. However, the majority of these works focus on producing short video clips of a single event (i.e., single-scene videos). Meanwhile, recent large language…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Han Lin , Abhay Zala , Jaemin Cho , Mohit Bansal

Visual storytelling aims to generate a narrative paragraph from a sequence of images automatically. Existing approaches construct text description independently for each image and roughly concatenate them as a story, which leads to the…

Computation and Language · Computer Science 2020-11-02 Ruize Wang , Zhongyu Wei , Ying Cheng , Piji Li , Haijun Shan , Ji Zhang , Qi Zhang , Xuanjing Huang

Providing asynchronous feedback is a critical step in the 3D design workflow. A common approach to providing feedback is to pair textual comments with companion reference images, which helps illustrate the gist of text. Ideally, feedback…

Human-Computer Interaction · Computer Science 2024-09-17 Chen Chen , Cuong Nguyen , Thibault Groueix , Vladimir G. Kim , Nadir Weibel