中文
相关论文

相关论文: RichSpace: Enriching Text-to-Video Prompt Space vi…

200 篇论文

Advancements in Large Language Models (LLMs) inspire various strategies for integrating video modalities. A key approach is Video-LLMs, which incorporate an optimizable interface linking sophisticated video encoders to LLMs. However, due to…

计算机视觉与模式识别 · 计算机科学 2024-10-03 Yuzhang Shang , Bingxin Xu , Weitai Kang , Mu Cai , Yuheng Li , Zehao Wen , Zhen Dong , Kurt Keutzer , Yong Jae Lee , Yan Yan

With the development of video generation models has advanced significantly in recent years, we adopt large-scale image-to-video diffusion models for video frame interpolation. We present a conditional encoder designed to adapt an…

计算机视觉与模式识别 · 计算机科学 2025-02-18 Luoxu Jin , Hiroshi Watanabe

Video interpolation is an important problem in computer vision, which helps overcome the temporal limitation of camera sensors. Existing video interpolation methods usually assume uniform motion between consecutive frames and use linear…

计算机视觉与模式识别 · 计算机科学 2019-11-05 Xiangyu Xu , Li Siyao , Wenxiu Sun , Qian Yin , Ming-Hsuan Yang

In recent years, large text-to-video (T2V) synthesis models have garnered considerable attention for their abilities to generate videos from textual descriptions. However, achieving both high imaging quality and effective motion…

计算机视觉与模式识别 · 计算机科学 2025-07-21 Tongtong Su , Chengyu Wang , Bingyan Liu , Jun Huang , Dongming Lu

Text-driven video generation witnesses rapid progress. However, merely using text prompts is not enough to depict the desired subject appearance that accurately aligns with users' intents, especially for customized content creation. In this…

计算机视觉与模式识别 · 计算机科学 2023-12-04 Yuming Jiang , Tianxing Wu , Shuai Yang , Chenyang Si , Dahua Lin , Yu Qiao , Chen Change Loy , Ziwei Liu

Text-to-image diffusion models have shown impressive capabilities in generating realistic visuals from natural-language prompts, yet they often struggle with accurately binding attributes to corresponding objects, especially in prompts…

计算机视觉与模式识别 · 计算机科学 2025-05-05 Do Huu Dat , Nam Hyeonu , Po-Yuan Mao , Tae-Hyun Oh

Text-driven content creation has evolved to be a transformative technique that revolutionizes creativity. Here we study the task of text-driven human video generation, where a video sequence is synthesized from texts describing the…

计算机视觉与模式识别 · 计算机科学 2023-04-18 Yuming Jiang , Shuai Yang , Tong Liang Koh , Wayne Wu , Chen Change Loy , Ziwei Liu

Text-to-image generation requires large amount of training data to synthesizing high-quality images. For augmenting training data, previous methods rely on data interpolations like cropping, flipping, and mixing up, which fail to introduce…

计算机视觉与模式识别 · 计算机科学 2024-10-03 Senmao Ye , Fei Liu

Text-to-video generation is an emerging field in generative AI, enabling the creation of realistic, semantically accurate videos from text prompts. While current models achieve impressive visual quality and alignment with input text, they…

计算机视觉与模式识别 · 计算机科学 2025-09-23 Luca Zanchetta , Lorenzo Papa , Luca Maiano , Irene Amerini

Visual-semantic embedding aims to learn a joint embedding space where related video and sentence instances are located close to each other. Most existing methods put instances in a single embedding space. However, they struggle to embed…

计算机视觉与模式识别 · 计算机科学 2023-05-31 Huy Manh Nguyen , Tomo Miyazaki , Yoshihiro Sugaya , Shinichiro Omachi

This paper proposes a new strategy for learning powerful cross-modal embeddings for audio-to-video synchronization. Here, we set up the problem as one of cross-modal retrieval, where the objective is to find the most relevant audio segment…

计算机视觉与模式识别 · 计算机科学 2020-11-05 Soo-Whan Chung , Joon Son Chung , Hong-Goo Kang

We introduce an approach for augmenting text-to-video generation models with customized motions, extending their capabilities beyond the motions depicted in the original training data. By leveraging a few video samples demonstrating…

计算机视觉与模式识别 · 计算机科学 2024-12-11 Joanna Materzynska , Josef Sivic , Eli Shechtman , Antonio Torralba , Richard Zhang , Bryan Russell

Text-to-video generation has trailed behind text-to-image generation in terms of quality and diversity, primarily due to the inherent complexities of spatio-temporal modeling and the limited availability of video-text datasets. Recent…

计算机视觉与模式识别 · 计算机科学 2024-10-04 Xiefan Guo , Jinlin Liu , Miaomiao Cui , Liefeng Bo , Di Huang

Recent advancements in video generation have been remarkable, yet many existing methods struggle with issues of consistency and poor text-video alignment. Moreover, the field lacks effective techniques for text-guided video inpainting, a…

计算机视觉与模式识别 · 计算机科学 2024-03-19 Bojia Zi , Shihao Zhao , Xianbiao Qi , Jianan Wang , Yukai Shi , Qianyu Chen , Bin Liang , Kam-Fai Wong , Lei Zhang

We introduce an approach to generating videos based on a series of given language descriptions. Frames of the video are generated sequentially and optimized by guidance from the CLIP image-text encoder; iterating through language…

计算机视觉与模式识别 · 计算机科学 2022-10-25 Peter Schaldenbrand , Zhixuan Liu , Jean Oh

The increasing use of machine learning models has amplified the demand for high-quality, large-scale multimodal datasets. However, the availability of such datasets, especially those combining acoustic, visual and textual data, remains…

多媒体 · 计算机科学 2025-09-09 Jorge E. León , Miguel Carrasco

Video prediction is an extrapolation task that predicts future frames given past frames, and video frame interpolation is an interpolation task that estimates intermediate frames between two frames. We have witnessed the tremendous…

计算机视觉与模式识别 · 计算机科学 2022-06-28 Yue Wu , Qiang Wen , Qifeng Chen

Image-to-Video (I2V) generation aims to synthesize a video clip according to a given image and condition (e.g., text). The key challenge of this task lies in simultaneously generating natural motions while preserving the original appearance…

计算机视觉与模式识别 · 计算机科学 2025-03-04 Jie Tian , Xiaoye Qu , Zhenyi Lu , Wei Wei , Sichen Liu , Yu Cheng

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…

计算机视觉与模式识别 · 计算机科学 2024-07-10 Yuwei Fang , Willi Menapace , Aliaksandr Siarohin , Tsai-Shien Chen , Kuan-Chien Wang , Ivan Skorokhodov , Graham Neubig , Sergey Tulyakov

We propose a method to fuse frozen text-only large language models (LLMs) with pre-trained image encoder and decoder models, by mapping between their embedding spaces. Our model demonstrates a wide suite of multimodal capabilities: image…

计算与语言 · 计算机科学 2023-10-16 Jing Yu Koh , Daniel Fried , Ruslan Salakhutdinov