中文
相关论文

相关论文: Show Me What and Tell Me How: Video Synthesis via …

200 篇论文

Integrating information from multiple modalities is arguably one of the essential prerequisites for grounding artificial intelligence systems with an understanding of the real world. Recent advances in video transformers that jointly learn…

计算机视觉与模式识别 · 计算机科学 2023-11-15 Dota Tianai Dong , Mariya Toneva

Personalized recommendation stands as a ubiquitous channel for users to explore information or items aligned with their interests. Nevertheless, prevailing recommendation models predominantly rely on unique IDs and categorical features for…

信息检索 · 计算机科学 2024-05-14 Jieming Zhu , Chuhan Wu , Rui Zhang , Zhenhua Dong

Diffusion models have emerged as a powerful generative method for synthesizing high-quality and diverse set of images. In this paper, we propose a video generation method based on diffusion models, where the effects of motion are modeled in…

计算机视觉与模式识别 · 计算机科学 2022-12-02 Kangfu Mei , Vishal M. Patel

Despite the impressive progress of multimodal generative models, video-to-audio generation still suffers from limited performance and limits the flexibility to prioritize sound synthesis for specific objects within the scene. Conversely,…

计算机视觉与模式识别 · 计算机科学 2024-12-30 Yujin Jeong , Yunji Kim , Sanghyuk Chun , Jiyoung Lee

The objective of this study is to generate high-quality speech from silent talking face videos, a task also known as video-to-speech synthesis. A significant challenge in video-to-speech synthesis lies in the substantial modality gap…

音频与语音处理 · 电气工程与系统科学 2025-03-24 Ji-Hoon Kim , Jeongsoo Choi , Jaehun Kim , Chaeyoung Jung , Joon Son Chung

Generating videos of complex human motions such as flips, cartwheels, and martial arts remains challenging for current video diffusion models. Text-only conditioning is temporally ambiguous for fine-grained motion control, while explicit…

计算机视觉与模式识别 · 计算机科学 2026-03-10 Ashkan Taghipour , Morteza Ghahremani , Zinuo Li , Hamid Laga , Farid Boussaid , Mohammed Bennamoun

The existing state-of-the-art method for audio-visual conditioned video prediction uses the latent codes of the audio-visual frames from a multimodal stochastic network and a frame encoder to predict the next visual frame. However, a direct…

计算机视觉与模式识别 · 计算机科学 2023-09-21 Yating Xu , Conghui Hu , Gim Hee Lee

Generating temporally coherent high fidelity video is an important milestone in generative modeling research. We make progress towards this milestone by proposing a diffusion model for video generation that shows very promising initial…

计算机视觉与模式识别 · 计算机科学 2022-06-24 Jonathan Ho , Tim Salimans , Alexey Gritsenko , William Chan , Mohammad Norouzi , David J. Fleet

Video captioning targets interpreting the complex visual contents as text descriptions, which requires the model to fully understand video scenes including objects and their interactions. Prevailing methods adopt off-the-shelf object…

计算机视觉与模式识别 · 计算机科学 2022-09-07 Hao Wang , Guosheng Lin , Steven C. H. Hoi , Chunyan Miao

Multi-modal information is essential to describe what has happened in a video. In this work, we represent videos by various appearance, motion and audio information guided with video topic. By following multi-stage training strategy, our…

计算与语言 · 计算机科学 2019-10-15 Ziqi Zhang , Yaya Shi , Jiutong Wei , Chunfeng Yuan , Bing Li , Weiming Hu

Motion control is crucial for generating expressive and compelling video content; however, most existing video generation models rely mainly on text prompts for control, which struggle to capture the nuances of dynamic actions and temporal…

The recent success of Transformers in the language domain has motivated adapting it to a multimodal setting, where a new visual model is trained in tandem with an already pretrained language model. However, due to the excessive memory…

计算机视觉与模式识别 · 计算机科学 2021-09-23 Sangho Lee , Youngjae Yu , Gunhee Kim , Thomas Breuel , Jan Kautz , Yale Song

Customized text-to-video generation aims to generate text-guided videos with user-given subjects, which has gained increasing attention. However, existing works are primarily limited to single-subject oriented text-to-video generation,…

计算机视觉与模式识别 · 计算机科学 2025-04-15 Hong Chen , Xin Wang , Guanning Zeng , Yipeng Zhang , Yuwei Zhou , Feilin Han , Yaofei Wu , Wenwu Zhu

Existing conditional video prediction approaches train a network from large databases and generalize to previously unseen data. We take the opposite stance, and introduce a model that learns from the first frames of a given video and…

计算机视觉与模式识别 · 计算机科学 2018-12-27 Veronique Prinet

Current movie dubbing technology can produce the desired speech using a reference voice and input video, maintaining perfect synchronization with the visuals while effectively conveying the intended emotions. However, crucial aspects of…

多媒体 · 计算机科学 2025-05-23 Junjie Zheng , Zihao Chen , Chaofan Ding , Yunming Liang , Yihan Fan , Huan Yang , Lei Xie , Xinhan Di

Video generation is one of the most challenging tasks in Machine Learning and Computer Vision fields of study. In this paper, we tackle the text to video generation problem, which is a conditional form of video generation. Humans can…

计算机视觉与模式识别 · 计算机科学 2021-07-30 Amir Mazaheri , Mubarak Shah

True understanding of videos comes from a joint analysis of all its modalities: the video frames, the audio track, and any accompanying text such as closed captions. We present a way to learn a compact multimodal feature representation that…

计算机视觉与模式识别 · 计算机科学 2020-04-07 Vivek Sharma , Makarand Tapaswi , Rainer Stiefelhagen

The one-shot talking-head synthesis task aims to animate a source image to another pose and expression, which is dictated by a driving frame. Recent methods rely on warping the appearance feature extracted from the source, by using motion…

计算机视觉与模式识别 · 计算机科学 2023-05-01 Kangning Liu , Yu-Chuan Su , Wei , Hong , Ruijin Cang , Xuhui Jia

This paper proposes a practical multimodal video summarization task setting and a dataset to train and evaluate the task. The target task involves summarizing a given video into a predefined number of keyframe-caption pairs and displaying…

计算与语言 · 计算机科学 2023-12-05 Keito Kudo , Haruki Nagasawa , Jun Suzuki , Nobuyuki Shimizu

Recently, emotional talking face generation has received considerable attention. However, existing methods only adopt one-hot coding, image, or audio as emotion conditions, thus lacking flexible control in practical applications and failing…

计算机视觉与模式识别 · 计算机科学 2023-06-01 Chao Xu , Junwei Zhu , Jiangning Zhang , Yue Han , Wenqing Chu , Ying Tai , Chengjie Wang , Zhifeng Xie , Yong Liu