视频大模型

Panacea: Panoramic and Controllable Video Generation for Autonomous Driving

Yuqing Wen, Yucheng Zhao, Yingfei Liu, Fan Jia, Yanhui Wang, Chong Luo, Chi Zhang, Tiancai Wang, Xiaoyan Sun, Xiangyu Zhang

专题命中 视频生成 ：video generation(title)；分类 cs.CV

Comments Project page: https://panacea-ad.github.io/

High-Fidelity and Freely Controllable Talking Head Video Generation

Yue Gao, Yuan Zhou, Jinglu Wang, Xiao Li, Xiang Ming, Yan Lu

专题命中 视频生成 ：video generation(title)；分类 cs.CV

Comments CVPR 2023

3D-Aware Video Generation

Sherwin Bahmani, Jeong Joon Park, Despoina Paschalidou, Hao Tang, Gordon Wetzstein, Leonidas Guibas, Luc Van Gool, Radu Timofte

专题命中 视频生成 ：video generation(title)；分类 cs.CV

Comments TMLR 2023; Project page: https://sherwinbahmani.github.io/3dvidgen

Facial Expression Video Generation Based-On Spatio-temporal Convolutional GAN: FEV-GAN

Hamza Bouzid, Lahoucine Ballihi

专题命中 视频生成 ：video generation(title)；分类 cs.CV

Comments 13 pages, 8 figures, accepted in ISWA journal

Journal ref Intelligent Systems with Applications. 19 (2022)

Multi-object Video Generation from Single Frame Layouts

Yang Wu, Zhibin Liu, Hefeng Wu, Liang Lin

专题命中 视频生成 ：video generation(title)；分类 cs.CV

Comments 6 pages limit

Conditional Image-to-Video Generation with Latent Flow Diffusion Models

Haomiao Ni, Changhao Shi, Kai Li, Sharon X. Huang, Martin Renqiang Min

专题命中 视频生成 ：video generation(title)；分类 cs.CV

Comments CVPR 2023

D'ARTAGNAN: Counterfactual Video Generation

Hadrien Reynaud, Athanasios Vlontzos, Mischa Dombrowski, Ciarán Lee, Arian Beqiri, Paul Leeson, Bernhard Kainz

专题命中 视频生成 ：video generation(title)；分类 cs.CV

Comments Accepted for MICCAI 2022

RoME: Role-aware Mixture-of-Expert Transformer for Text-to-Video Retrieval

Burak Satar, Hongyuan Zhu, Hanwang Zhang, Joo Hwee Lim

专题命中 视频生成 ：text-to-video(title)；分类 cs.CV

Comments Preprint, under review in TCSVT Journal

Controllable Video Generation through Global and Local Motion Dynamics

Aram Davtyan, Paolo Favaro

专题命中 视频生成 ：video generation(title)；分类 cs.CV

VirtualConductor: Music-driven Conducting Video Generation System

Delong Chen, Fan Liu, Zewen Li, Feng Xu

专题命中 视频生成 ：video generation(title)；分类 cs.CV

Comments Accepted by IEEE International Conference on Multimedia and Expo (ICME) 2021, demo track. Best demo

NWT: Towards natural audio-to-video generation with representation learning

Rayhane Mama, Marc S. Tyndel, Hashiam Kadhim, Cole Clifford, Ragavan Thurairatnam

专题命中 视频生成 ：video generation(title)；分类 cs.CV

Efficient training for future video generation based on hierarchical disentangled representation of latent variables

Naoya Fushishita, Antonio Tejero-de-Pablos, Yusuke Mukuta, Tatsuya Harada

专题命中 视频生成 ：video generation(title)；分类 cs.CV

Long-Term Human Video Generation of Multiple Futures Using Poses

Naoya Fushishita, Antonio Tejero-de-Pablos, Yusuke Mukuta, Tatsuya Harada

专题命中 视频生成 ：video generation(title)；分类 cs.CV

Unsupervised object-centric video generation and decomposition in 3D

Paul Henderson, Christoph H. Lampert

专题命中 视频生成 ：video generation(title)；分类 cs.CV

Comments Appeared at NeurIPS 2020. Project page: http://pmh47.net/o3v/

Can Everybody Sign Now? Exploring Sign Language Video Generation from 2D Poses

Lucas Ventura, Amanda Duarte, Xavier Giro-i-Nieto

专题命中 视频生成 ：video generation(title)；分类 cs.CV

Comments Video here: https://youtu.be/4ve1sGzWl2g

VideoFlow: A Conditional Flow-Based Model for Stochastic Video Generation

Manoj Kumar, Mohammad Babaeizadeh, Dumitru Erhan, Chelsea Finn, Sergey Levine, Laurent Dinh, Durk Kingma

专题命中 视频生成 ：video generation(title)；分类 cs.CV

Comments ICLR 2020 Camera-Ready. Previous title: VideoFlow: A Flow-Based Generative Model for Video

DwNet: Dense warp-based network for pose-guided human video generation

Polina Zablotskaia, Aliaksandr Siarohin, Bo Zhao, Leonid Sigal

专题命中 视频生成 ：video generation(title)；分类 cs.CV

Comments Accepted to BMVC 2019

Adversarial Video Generation on Complex Datasets

Aidan Clark, Jeff Donahue, Karen Simonyan

专题命中 视频生成 ：video generation(title)；分类 cs.CV

Automatic Realistic Music Video Generation from Segments of Youtube Videos

Sarah Gross, Xingxing Wei, Jun Zhu

专题命中 视频生成 ：video generation(title)；分类 cs.MM

Face Video Generation from a Single Image and Landmarks

Kritaphat Songsri-in, Stefanos Zafeiriou

专题命中 视频生成 ：video generation(title)；分类 cs.CV

Unsupervised Bi-directional Flow-based Video Generation from one Snapshot

Lu Sheng, Junting Pan, Jiaming Guo, Jing Shao, Xiaogang Wang, Chen Change Loy

专题命中 视频生成 ：video generation(title)；分类 cs.CV

Comments 11 pages, 12 figures. Technical report for a project in progress

Learning to navigate image manifolds induced by generative adversarial networks for unsupervised video generation

Isabela Albuquerque, João Monteiro, Tiago H. Falk

专题命中 视频生成 ：video generation(title)；分类 cs.CV

Pose Guided Human Video Generation

Ceyuan Yang, Zhe Wang, Xinge Zhu, Chen Huang, Jianping Shi, Dahua Lin

专题命中 视频生成 ：video generation(title)；分类 cs.CV

Comments Accepted to ECCV 2018

Learning to Forecast and Refine Residual Motion for Image-to-Video Generation

Long Zhao, Xi Peng, Yu Tian, Mubbasir Kapadia, Dimitris Metaxas

专题命中 视频生成 ：video generation(title)；分类 cs.CV

Comments 17 pages, 8 figures, 4 tables, accepted by ECCV 2018

Video Generation From Text

Yitong Li, Martin Renqiang Min, Dinghan Shen, David Carlson, Lawrence Carin

专题命中 视频生成 ：video generation(title)；分类 cs.MM

Closed-Loop Triplet Synergistic Generation for Long-Form Video

闭环三元组协同生成用于长视频

Xinlei Yin, Xiulian Peng, Xiao Li, Zhiwei Xiong, Yan Lu

机构 * University of Science and Technology of China（中国科学技术大学） ； Microsoft Research Asia（微软亚洲研究院） 纠错

专题命中 视频生成 ：video generation(abstract)；long video(abstract)；分类 cs.CV、cs.MM

AI总结 提出CoTriSyGen框架，通过闭环视觉-文本-记忆协同过程，结合分析器进行镜头内和镜头间修正，解决长视频生成中的身份漂移和不一致问题。

Do Models Share Safety Representations? Cross-Model Steering for Safe Visual Generation

模型是否共享安全表示？面向安全视觉生成的跨模型引导

Tobia Poppi, Silvia Cappelletti, Sara Sarto, Florian Schiffers, Garin Kessler, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara

机构 * University of Modena and Reggio Emilia（摩德纳和雷吉奥艾米利亚大学） ； University of Pisa（比萨大学） ； Amazon Prime Video（亚马逊prime视频） 纠错

专题命中 视频生成 ：video generation(abstract)；text-to-video(abstract)；分类 cs.CV、cs.MM

AI总结 本文提出首个跨模型安全引导框架，通过源语言模型估计安全方向并迁移至目标生成器，无需目标侧不安全数据即可实现安全控制，且不牺牲生成质量。

Comments Project page: https://aimagelab.github.io/cross-model-safety-representations/

EAD-Net: Emotion-Aware Talking Head Generation with Spatial Refinement and Temporal Coherence

EAD-Net：具有空间细化和时间一致性的情感感知说话头生成

Yahui Li, Yinfeng Yu, Liejun Wang, Shengjie Shen

机构 * School of Computer Science and Technology, Xinjiang University（新疆大学计算机科学与技术学院） 纠错

专题命中 视频生成 ：video generation(abstract)；long video(abstract)；分类 cs.CV、eess.IV

AI总结 EAD-Net通过引入同步网络监督和时空方向注意力机制，提升情感感知说话头生成的唇同步精度和时间一致性，同时利用大语言模型增强情感语义控制。

Comments Main paper (10 pages). Accepted for publication by ICMR(International Conference on Multimedia Retrieval) 2026

AToken: A Unified Tokenizer for Vision

Jiasen Lu, Liangchen Song, Mingze Xu, Byeongjoo Ahn, Yanjun Wang, Chen Chen, Afshin Dehghan, Yinfei Yang

专题命中 视频生成 ：video generation(abstract)；text-to-video(abstract)；分类 cs.CV、cs.MM

Comments 30 pages, 14 figures

GiVE: Guiding Visual Encoder to Perceive Overlooked Information

Junjie Li, Jianghong Ma, Xiaofeng Zhang, Yuhang Li, Jianyang Shi

专题命中 视频生成 ：video generation(abstract)；text-to-video(abstract)；分类 cs.CV、cs.MM

Comments This paper was accepted by ICME 2025