中文
相关论文

相关论文: What Are You Doing? A Closer Look at Controllable …

200 篇论文

Talking Head Generation (THG) has emerged as a transformative technology in computer vision, enabling the synthesis of realistic human faces synchronized with image, audio, text, or video inputs. This paper provides a comprehensive review…

计算机视觉与模式识别 · 计算机科学 2026-01-22 Vineet Kumar Rakesh , Soumya Mazumdar , Research Pratim Maity , Sarbajit Pal , Amitabha Das , Tapas Samanta

Dense video captioning aims to identify the events of interest in an input video, and generate descriptive captions for each event. Previous approaches usually follow a two-stage generative process, which first proposes a segment for each…

计算机视觉与模式识别 · 计算机科学 2022-09-19 Wanrong Zhu , Bo Pang , Ashish V. Thapliyal , William Yang Wang , Radu Soricut

The growing capabilities of AI in generating video content have brought forward significant challenges in effectively evaluating these videos. Unlike static images or text, video content involves complex spatial and temporal dynamics which…

计算机视觉与模式识别 · 计算机科学 2026-03-23 Xiao Liu , Xinhao Xiang , Zizhong Li , Yongheng Wang , Zhuoheng Li , Zhuosheng Liu , Weidi Zhang , Weiqi Ye , Jiawei Zhang

Recent image editing models boast next-level intelligent capabilities, facilitating cognition- and creativity-informed image editing. Yet, existing benchmarks provide too narrow a scope for evaluation, failing to holistically assess these…

计算机视觉与模式识别 · 计算机科学 2025-12-09 Kaihang Pan , Weile Chen , Haiyi Qiu , Qifan Yu , Wendong Bu , Zehan Wang , Yun Zhu , Juncheng Li , Siliang Tang

Understanding human actions in visual data is tied to advances in complementary research areas including object recognition, human dynamics, domain adaptation and semantic segmentation. Over the last decade, human action analysis evolved…

计算机视觉与模式识别 · 计算机科学 2017-02-02 Samitha Herath , Mehrtash Harandi , Fatih Porikli

Generative models often use human evaluations to measure the perceived quality of their outputs. Automated metrics are noisy indirect proxies, because they rely on heuristics or pretrained embeddings. However, up until now, direct human…

计算机视觉与模式识别 · 计算机科学 2019-11-04 Sharon Zhou , Mitchell L. Gordon , Ranjay Krishna , Austin Narcomey , Li Fei-Fei , Michael S. Bernstein

We present Movie Gen, a cast of foundation models that generates high-quality, 1080p HD videos with different aspect ratios and synchronized audio. We also show additional capabilities such as precise instruction-based video editing and…

Generic motion understanding from video involves not only tracking objects, but also perceiving how their surfaces deform and move. This information is useful to make inferences about 3D shape, physical properties and object interactions.…

计算机视觉与模式识别 · 计算机科学 2023-04-03 Carl Doersch , Ankush Gupta , Larisa Markeeva , Adrià Recasens , Lucas Smaira , Yusuf Aytar , João Carreira , Andrew Zisserman , Yi Yang

Video description is the automatic generation of natural language sentences that describe the contents of a given video. It has applications in human-robot interaction, helping the visually impaired and video subtitling. The past few years…

计算机视觉与模式识别 · 计算机科学 2020-03-04 Nayyer Aafaq , Ajmal Mian , Wei Liu , Syed Zulqarnain Gilani , Mubarak Shah

We are committed to learning human skill generators at key-step levels. The generation of skills is a challenging endeavor, but its successful implementation could greatly facilitate human skill learning and provide more experience for…

计算机视觉与模式识别 · 计算机科学 2025-02-13 Yilu Wu , Chenhui Zhu , Shuai Wang , Hanlin Wang , Jing Wang , Zhaoxiang Zhang , Limin Wang

How do two individuals differ when performing the same action? In this work, we introduce Video Action Differencing (VidDiff), the novel task of identifying subtle differences between videos of the same action, which has many applications,…

计算机视觉与模式识别 · 计算机科学 2025-03-12 James Burgess , Xiaohan Wang , Yuhui Zhang , Anita Rau , Alejandro Lozano , Lisa Dunlap , Trevor Darrell , Serena Yeung-Levy

Existing multimodal generative models fall short as qualified design copilots, as they often struggle to generate imaginative outputs once instructions are less detailed or lack the ability to maintain consistency with the provided…

计算机视觉与模式识别 · 计算机科学 2025-03-11 Zhipeng Huang , Shaobin Zhuang , Canmiao Fu , Binxin Yang , Ying Zhang , Chong Sun , Zhizheng Zhang , Yali Wang , Chen Li , Zheng-Jun Zha

Generating video stories from text prompts is a complex task. In addition to having high visual quality, videos need to realistically adhere to a sequence of text prompts whilst being consistent throughout the frames. Creating a benchmark…

Text-to-video (T2V) models have shown remarkable performance in generating visually reasonable scenes, while their capability to leverage world knowledge for ensuring semantic consistency and factual accuracy remains largely understudied.…

计算机视觉与模式识别 · 计算机科学 2025-07-25 Yubin Chen , Xuyang Guo , Zhenmei Shi , Zhao Song , Jiahao Zhang

With recent advances in computer vision and graphics, it is now possible to generate videos with extremely realistic synthetic faces, even in real time. Countless applications are possible, some of which raise a legitimate alarm, calling…

计算机视觉与模式识别 · 计算机科学 2018-03-28 Andreas Rössler , Davide Cozzolino , Luisa Verdoliva , Christian Riess , Justus Thies , Matthias Nießner

Recent advances in unified multimodal models (UMMs) have enabled impressive progress in visual comprehension and generation. However, existing datasets and benchmarks focus primarily on single-turn interactions, failing to capture the…

计算机视觉与模式识别 · 计算机科学 2025-11-17 Wei Chow , Jiachun Pan , Yongyuan Liang , Mingze Zhou , Xue Song , Liyu Jia , Saining Zhang , Siliang Tang , Juncheng Li , Fengda Zhang , Weijia Wu , Hanwang Zhang , Tat-Seng Chua

Generating realistic human videos remains a challenging task, with the most effective methods currently relying on a human motion sequence as a control signal. Existing approaches often use existing motion extracted from other videos, which…

计算机视觉与模式识别 · 计算机科学 2024-12-18 Hsin-Ping Huang , Yang Zhou , Jui-Hsien Wang , Difan Liu , Feng Liu , Ming-Hsuan Yang , Zhan Xu

Recent advances in large-scale video world models have enabled increasingly realistic future prediction, raising the prospect of using generated videos as scalable supervision for robot learning. However, for embodied manipulation,…

机器人学 · 计算机科学 2026-05-15 Feng Jiang , Yang Chen , Kyle Xu , Yuchen Liu , Haifeng Wang , Zhenhao Shen , Jasper Lu , Shengze Huang , Yuanfei Wang , Chen Xie , Ruihai Wu

Understanding human visual attention and saliency is an integral part of vision research. In this context, there is an ever-present need for fresh and diverse benchmark datasets, particularly for insight into special use cases like crowded…

计算机视觉与模式识别 · 计算机科学 2019-10-10 Memoona Tahira , Sobas Mehboob , Anis U. Rahman , Omar Arif

Human video generation remains challenging due to the difficulty of jointly modeling human appearance, motion, and camera viewpoint under limited multi-view data. Existing methods often address these factors separately, resulting in limited…

计算机视觉与模式识别 · 计算机科学 2026-04-22 Zhengwentai Sun , Keru Zheng , Chenghong Li , Hongjie Liao , Xihe Yang , Heyuan Li , Yihao Zhi , Shuliang Ning , Shuguang Cui , Xiaoguang Han