中文
相关论文

相关论文: Rebalancing Reference Frame Dominance to Improve M…

200 篇论文

Recent progress in Large Multi-modal Models (LMMs) has enabled effective vision-language reasoning, yet the ability to understand video content remains constrained by suboptimal frame selection strategies. Existing approaches often rely on…

计算机视觉与模式识别 · 计算机科学 2025-06-03 Hosu Lee , Junho Kim , Hyunjun Kim , Yong Man Ro

Despite the rapid progress of video generation models, the role of data in influencing motion is poorly understood. We present Motive (MOTIon attribution for Video gEneration), a motion-centric, gradient-based data attribution framework…

计算机视觉与模式识别 · 计算机科学 2026-01-14 Xindi Wu , Despoina Paschalidou , Jun Gao , Antonio Torralba , Laura Leal-Taixé , Olga Russakovsky , Sanja Fidler , Jonathan Lorraine

We introduce Talk2Move, a reinforcement learning (RL) based diffusion framework for text-instructed spatial transformation of objects within scenes. Spatially manipulating objects in a scene through natural language poses a challenge for…

计算机视觉与模式识别 · 计算机科学 2026-01-09 Jing Tan , Zhaoyang Zhang , Yantao Shen , Jiarui Cai , Shuo Yang , Jiajun Wu , Wei Xia , Zhuowen Tu , Stefano Soatto

With the prosper of video diffusion models, down-stream applications like video editing have been significantly promoted without consuming much computational cost. One particular challenge in this task lies at the motion transfer process…

计算机视觉与模式识别 · 计算机科学 2025-06-16 Ge Wang , Songlin Fan , Hangxu Liu , Quanjian Song , Hewei Wang , Jinfeng Xu

Recent text-to-video (T2V) models have demonstrated strong capabilities in producing high-quality, dynamic videos. To improve the visual controllability, recent works have considered fine-tuning pre-trained T2V models to support…

计算机视觉与模式识别 · 计算机科学 2026-02-25 June Suk Choi , Kyungmin Lee , Sihyun Yu , Yisol Choi , Jinwoo Shin , Kimin Lee

Training-free diffusion models have achieved remarkable progress in generating multi-subject consistent images within open-domain scenarios. The key idea of these methods is to incorporate reference subject information within the attention…

计算机视觉与模式识别 · 计算机科学 2025-03-11 Huiguo He , Qiuyue Wang , Yuan Zhou , Yuxuan Cai , Hongyang Chao , Jian Yin , Huan Yang

Extracting and predicting object structure and dynamics from videos without supervision is a major challenge in machine learning. To address this challenge, we adopt a keypoint-based image representation and learn a stochastic dynamics…

计算机视觉与模式识别 · 计算机科学 2020-03-03 Matthias Minderer , Chen Sun , Ruben Villegas , Forrester Cole , Kevin Murphy , Honglak Lee

Motion expression video segmentation is designed to segment objects in accordance with the input motion expressions. In contrast to the conventional Referring Video Object Segmentation (RVOS), it places emphasis on motion as well as…

计算机视觉与模式识别 · 计算机科学 2025-04-08 Hao Fang , Runmin Cong , Xiankai Lu , Zhiyang Chen , Wei Zhang

There is a rapidly growing interest in controlling consistency across multiple generated images using diffusion models. Among various methods, recent works have found that simply manipulating attention modules by concatenating features from…

计算机视觉与模式识别 · 计算机科学 2024-05-29 Jiaojiao Fan , Haotian Xue , Qinsheng Zhang , Yongxin Chen

Video Frame Interpolation (VFI) aims to synthesize intermediate frames between existing frames to enhance visual smoothness and quality. Beyond the conventional methods based on the reconstruction loss, recent works have employed generative…

计算机视觉与模式识别 · 计算机科学 2024-12-20 Jaihyun Lew , Jooyoung Choi , Chaehun Shin , Dahuin Jung , Sungroh Yoon

Video compression aims to reconstruct seamless frames by encoding the motion and residual information from existing frames. Previous neural video compression methods necessitate distinct codecs for three types of frames (I-frame, P-frame…

图像与视频处理 · 电气工程与系统科学 2024-06-04 Meiqin Liu , Chenming Xu , Yukai Gu , Chao Yao , Yao Zhao

Diffusion models have achieved remarkable progress on image-to-video (I2V) generation, while their noise-to-data generation process is inherently mismatched with this task, which may lead to suboptimal synthesis quality. In this work, we…

计算机视觉与模式识别 · 计算机科学 2025-06-17 Yuji Wang , Zehua Chen , Xiaoyu Chen , Yixiang Wei , Jun Zhu , Jianfei Chen

Image-to-video (I2V) generation aims to use the initial frame (alongside a text prompt) to create a video sequence. A grand challenge in I2V generation is to maintain visual consistency throughout the video: existing methods often struggle…

计算机视觉与模式识别 · 计算机科学 2024-07-02 Weiming Ren , Huan Yang , Ge Zhang , Cong Wei , Xinrun Du , Wenhao Huang , Wenhu Chen

The autoregressive video diffusion model has recently gained considerable research interest due to its causal modeling and iterative denoising. In this work, we identify that the multi-head self-attention in these models under-utilizes…

计算机视觉与模式识别 · 计算机科学 2026-01-29 Hang Guo , Zhaoyang Jia , Jiahao Li , Bin Li , Yuanhao Cai , Jiangshan Wang , Yawei Li , Yan Lu

We present a lightweight video motion retargeting approach TransMoMo that is capable of transferring motion of a person in a source video realistically to another video of a target person. Without using any paired data for supervision, the…

计算机视觉与模式识别 · 计算机科学 2020-04-02 Zhuoqian Yang , Wentao Zhu , Wayne Wu , Chen Qian , Qiang Zhou , Bolei Zhou , Chen Change Loy

Robust perception and dynamics modeling are fundamental to real-world robotic policy learning. Recent methods employ video diffusion models (VDMs) to enhance robotic policies, improving their understanding and modeling of the physical…

机器人学 · 计算机科学 2026-03-25 Yueru Jia , Jiaming Liu , Shengbang Liu , Rui Zhou , Wanhe Yu , Yuyang Yan , Xiaowei Chi , Yandong Guo , Boxin Shi , Shanghang Zhang

Video Diffusion Models (VDMs) can generate high-quality videos, but often struggle with producing temporally coherent motion. Optical flow supervision is a promising approach to address this, with prior works commonly employing…

计算机视觉与模式识别 · 计算机科学 2025-04-22 Kuanting Wu , Kei Ota , Asako Kanezaki

Recent advances in text-to-image (T2I) diffusion models have enabled impressive image generation capabilities guided by text prompts. However, extending these techniques to video generation remains challenging, with existing text-to-video…

计算机视觉与模式识别 · 计算机科学 2024-08-13 Weifeng Chen , Yatai Ji , Jie Wu , Hefeng Wu , Pan Xie , Jiashi Li , Xin Xia , Xuefeng Xiao , Liang Lin

We present IMAS, a method that segments the primary objects in videos without manual annotation in training or inference. Previous methods in unsupervised video object segmentation (UVOS) have demonstrated the effectiveness of motion as…

计算机视觉与模式识别 · 计算机科学 2022-12-20 Long Lian , Zhirong Wu , Stella X. Yu

Understanding human motion from video is essential for a range of applications, including pose estimation, mesh recovery and action recognition. While state-of-the-art methods predominantly rely on transformer-based architectures, these…

计算机视觉与模式识别 · 计算机科学 2024-04-18 Arnab Kumar Mondal , Stefano Alletto , Denis Tome