Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Mo, Sicheng"'
Autor:
Zhou, Yunsong, Simon, Michael, Peng, Zhenghao, Mo, Sicheng, Zhu, Hongzi, Guo, Minyi, Zhou, Bolei
Controllable synthetic data generation can substantially lower the annotation cost of training data in autonomous driving research and development. Prior works use diffusion models to generate driving images conditioned on the 3D object layout. Howev
Externí odkaz:
http://arxiv.org/abs/2406.09386
Recent controllable generation approaches such as FreeControl and Diffusion Self-guidance bring fine-grained spatial and appearance control to text-to-image (T2I) diffusion models without training auxiliary modules. However, these methods optimize th
Externí odkaz:
http://arxiv.org/abs/2406.07540
Temporal grounding of text descriptions in videos is a central problem in vision-language learning and video understanding. Existing methods often prioritize accuracy over scalability -- they have been optimized for grounding only a few text queries
Externí odkaz:
http://arxiv.org/abs/2404.02257
Recent approaches such as ControlNet offer users fine-grained spatial control over text-to-image (T2I) diffusion models. However, auxiliary modules have to be trained for each type of spatial condition, model architecture, and checkpoint, putting the
Externí odkaz:
http://arxiv.org/abs/2312.07536
This report describes our submission to the Ego4D Moment Queries Challenge 2022. Our submission builds on ActionFormer, the state-of-the-art backbone for temporal action localization, and a trio of strong video features from SlowFast, Omnivore and Eg
Externí odkaz:
http://arxiv.org/abs/2211.09074
This report describes Badgers@UW-Madison, our submission to the Ego4D Natural Language Queries (NLQ) Challenge. Our solution inherits the point-based event representation from our prior work on temporal action localization, and develops a Transformer
Externí odkaz:
http://arxiv.org/abs/2211.08704
Autor:
Mu, Fangzhou, Mo, Sicheng, Peng, Jiayong, Liu, Xiaochun, Nam, Ji Hyun, Raghavan, Siddeshwar, Velten, Andreas, Li, Yin
Computational approach to imaging around the corner, or non-line-of-sight (NLOS) imaging, is becoming a reality thanks to major advances in imaging hardware and reconstruction algorithms. A recent development towards practical NLOS imaging, Nam et al
Externí odkaz:
http://arxiv.org/abs/2205.01679
Publikováno v:
In Automation in Construction October 2023 154