中文
相关论文

相关论文: Frame-wise Conditioning Adaptation for Fine-Tuning…

200 篇论文

In Learned Video Compression (LVC), improving inter prediction, such as enhancing temporal context mining and mitigating accumulated errors, is crucial for boosting rate-distortion performance. Existing LVCs mainly focus on mining the…

图像与视频处理 · 电气工程与系统科学 2025-10-29 Wei Jiang , Junru Li , Kai Zhang , Li Zhang

Diffusion models are generative models with impressive text-to-image synthesis capabilities and have spurred a new wave of creative methods for classical machine learning tasks. However, the best way to harness the perceptual knowledge of…

计算机视觉与模式识别 · 计算机科学 2024-04-02 Neehar Kondapaneni , Markus Marks , Manuel Knott , Rogerio Guimaraes , Pietro Perona

This paper proposes a method for generating images of customized objects specified by users. The method is based on a general framework that bypasses the lengthy optimization required by previous approaches, which often employ a per-object…

计算机视觉与模式识别 · 计算机科学 2023-04-06 Xuhui Jia , Yang Zhao , Kelvin C. K. Chan , Yandong Li , Han Zhang , Boqing Gong , Tingbo Hou , Huisheng Wang , Yu-Chuan Su

Current state-of-the-art methods for video inpainting typically rely on optical flow or attention-based approaches to inpaint masked regions by propagating visual information across frames. While such approaches have led to significant…

Spatial convolutions are extensively used in numerous deep video models. It fundamentally assumes spatio-temporal invariance, i.e., using shared weights for every location in different frames. This work presents Temporally-Adaptive…

计算机视觉与模式识别 · 计算机科学 2023-08-14 Ziyuan Huang , Shiwei Zhang , Liang Pan , Zhiwu Qing , Yingya Zhang , Ziwei Liu , Marcelo H. Ang

The emergence of text-driven motion synthesis technique provides animators with great potential to create efficiently. However, in most cases, textual expressions only contain general and qualitative motion descriptions, while lack fine…

计算机视觉与模式识别 · 计算机科学 2023-12-27 Dong Wei , Xiaoning Sun , Huaijiang Sun , Bin Li , Shengxiang Hu , Weiqing Li , Jianfeng Lu

Text-to-video generation aims to produce a video based on a given prompt. Recently, several commercial video models have been able to generate plausible videos with minimal noise, excellent details, and high aesthetic scores. However, these…

计算机视觉与模式识别 · 计算机科学 2024-01-18 Haoxin Chen , Yong Zhang , Xiaodong Cun , Menghan Xia , Xintao Wang , Chao Weng , Ying Shan

Recent breakthroughs in Vision-Language (V&L) joint research have achieved remarkable results in various text-driven tasks. High-quality Text-to-video (T2V), a task that has been long considered mission-impossible, was proven feasible with…

人工智能 · 计算机科学 2022-11-28 Yuxing Qiu , Feng Gao , Minchen Li , Govind Thattai , Yin Yang , Chenfanfu Jiang

Achieving precise word-level typography control within generated images remains a persistent challenge. To address it, we newly construct a word-level controlled scene text dataset and introduce the Text-Image Alignment (TIA) framework.…

计算机视觉与模式识别 · 计算机科学 2025-06-27 Wenda Shi , Yiren Song , Zihan Rao , Dengming Zhang , Jiaming Liu , Xingxing Zou

The development of text-to-video (T2V), i.e., generating videos with a given text prompt, has been significantly advanced in recent years. However, relying solely on text prompts often results in ambiguous frame composition due to spatial…

计算机视觉与模式识别 · 计算机科学 2023-11-29 Yuwei Guo , Ceyuan Yang , Anyi Rao , Maneesh Agrawala , Dahua Lin , Bo Dai

In this paper, we study the problem of temporal video grounding (TVG), which aims to predict the starting/ending time points of moments described by a text sentence within a long untrimmed video. Benefiting from fine-grained 3D visual…

计算机视觉与模式识别 · 计算机科学 2023-10-05 Yimeng Zhang , Xin Chen , Jinghan Jia , Sijia Liu , Ke Ding

Recent advancements in video understanding within visual large language models (VLLMs) have led to notable progress. However, the complexity of video data and contextual processing limitations still hinder long-video comprehension. A common…

计算机视觉与模式识别 · 计算机科学 2025-04-30 Yanan Guo , Wenhui Dong , Jun Song , Shiding Zhu , Xuan Zhang , Hanqing Yang , Yingbo Wang , Yang Du , Xianing Chen , Bo Zheng

Learning-based Neural Video Codecs (NVCs) have emerged as a compelling alternative to standard video codecs, demonstrating promising performance, and simple and easily maintainable pipelines. However, NVCs often fall short of compression…

图像与视频处理 · 电气工程与系统科学 2024-12-02 Hyunmo Yang , Seungjun Oh , Eunbyung Park

Vision-Language-Action (VLA) models have demonstrated significant potential in the field of embodied intelligence, enabling agents to follow human instructions to complete complex tasks in physical environments. Existing embodied agents are…

机器人学 · 计算机科学 2025-05-27 Junyang Shu , Zhiwei Lin , Yongtao Wang

Temporal consistency is essential for video editing applications. Existing work on layered representation of videos allows propagating edits consistently to each frame. These methods, however, can only edit object appearance rather than…

计算机视觉与模式识别 · 计算机科学 2023-01-31 Yao-Chih Lee , Ji-Ze Genevieve Jang , Yi-Ting Chen , Elizabeth Qiu , Jia-Bin Huang

Fine-tuning large-scale text-to-video diffusion models to add new generative controls, such as those over physical camera parameters (e.g., shutter speed or aperture), typically requires vast, high-fidelity datasets that are difficult to…

计算机视觉与模式识别 · 计算机科学 2026-04-09 Shihan Cheng , Nilesh Kulkarni , David Hyde , Dmitriy Smirnov

Finetuning a pretrained vision model (PVM) is a common technique for learning downstream vision tasks. However, the conventional finetuning process with randomly sampled data points results in diminished training efficiency. To address this…

计算机视觉与模式识别 · 计算机科学 2024-04-16 Rongyu Zhang , Zefan Cai , Huanrui Yang , Zidong Liu , Denis Gudovskiy , Tomoyuki Okuno , Yohei Nakata , Kurt Keutzer , Baobao Chang , Yuan Du , Li Du , Shanghang Zhang

Video-Language Pre-training models have recently significantly improved various multi-modal downstream tasks. Previous dominant works mainly adopt contrastive learning to achieve global feature alignment across modalities. However, the…

计算机视觉与模式识别 · 计算机科学 2023-01-19 Fan Ma , Xiaojie Jin , Heng Wang , Jingjia Huang , Linchao Zhu , Jiashi Feng , Yi Yang

The current text-to-video (T2V) generation has made significant progress in synthesizing realistic general videos, but it is still under-explored in identity-specific human video generation with customized ID images. The key challenge lies…

计算机视觉与模式识别 · 计算机科学 2025-03-18 Hengjia Li , Haonan Qiu , Shiwei Zhang , Xiang Wang , Yujie Wei , Zekun Li , Yingya Zhang , Boxi Wu , Deng Cai

Text-to-image diffusion models can generate diverse content with flexible prompts, which makes them well-suited for customization through fine-tuning with a small amount of user-provided data. However, controllable fine-tuning that prevents…

计算机视觉与模式识别 · 计算机科学 2025-11-19 Ziyao Zeng , Jingcheng Ni , Ruyi Liu , Alex Wong
‹ 上一页 1 8 9 10 下一页 ›