Zobrazeno 1 - 10
of 69
pro vyhledávání: '"Fu-Cheng Yang"'
Autor:
Gustafson, Laura, Rolland, Chloe, Ravi, Nikhila, Duval, Quentin, Adcock, Aaron, Fu, Cheng-Yang, Hall, Melissa, Ross, Candace
Computer vision models have known performance disparities across attributes such as gender and skin tone. This means during tasks such as classification and detection, model performance differs for certain classes based on the demographics of the peo
Externí odkaz:
http://arxiv.org/abs/2309.00035
Publikováno v:
Water Science and Engineering, Vol 7, Iss 4, Pp 363-372 (2014)
The Irtysh River is an international river partially joining the territories of China, Kazakhstan, and Russia. Cascade reservoirs have been constructed in the upper reaches of the river and their effects on the seasonal discharge of the middle and lo
Externí odkaz:
https://doaj.org/article/c45dffff4d0043ffa59394ee742eb222
Autor:
Fu, Tsu-Jui, Yu, Licheng, Zhang, Ning, Fu, Cheng-Yang, Su, Jong-Chyi, Wang, William Yang, Bell, Sean
Generating a video given the first several static frames is challenging as it anticipates reasonable future frames with temporal coherence. Besides video prediction, the ability to rewind from the last frame or infilling between the head and tail is
Externí odkaz:
http://arxiv.org/abs/2211.12824
Autor:
Xu, Mengmeng, Li, Yanghao, Fu, Cheng-Yang, Ghanem, Bernard, Xiang, Tao, Perez-Rua, Juan-Manuel
This paper deals with the problem of localizing objects in image and video datasets from visual exemplars. In particular, we focus on the challenging problem of egocentric visual query localization. We first identify grave implicit biases in current
Externí odkaz:
http://arxiv.org/abs/2211.10528
Autor:
Bolya, Daniel, Fu, Cheng-Yang, Dai, Xiaoliang, Zhang, Peizhao, Feichtenhofer, Christoph, Hoffman, Judy
We introduce Token Merging (ToMe), a simple method to increase the throughput of existing ViT models without needing to train. ToMe gradually combines similar tokens in a transformer using a general and light-weight matching algorithm that is as fast
Externí odkaz:
http://arxiv.org/abs/2210.09461
While transformers have begun to dominate many tasks in vision, applying them to large images is still computationally difficult. A large reason for this is that self-attention scales quadratically with the number of tokens, which in turn, scales qua
Externí odkaz:
http://arxiv.org/abs/2209.07484
Autor:
Xu, Mengmeng, Fu, Cheng-Yang, Li, Yanghao, Ghanem, Bernard, Perez-Rua, Juan-Manuel, Xiang, Tao
The recently released Ego4D dataset and benchmark significantly scales and diversifies the first-person visual perception data. In Ego4D, the Visual Queries 2D Localization task aims to retrieve objects appeared in the past from the recording in the
Externí odkaz:
http://arxiv.org/abs/2208.01949
We consider the targeted image editing problem: blending a region in a source image with a driver image that specifies the desired change. Differently from prior works, we solve this problem by learning a conditional probability distribution of the e
Externí odkaz:
http://arxiv.org/abs/2205.01668
In this work, we present a new operator, called Instance Mask Projection (IMP), which projects a predicted Instance Segmentation as a new feature for semantic segmentation. It also supports back propagation so is trainable end-to-end. Our experiments
Externí odkaz:
http://arxiv.org/abs/1906.06597
Recently two-stage detectors have surged ahead of single-shot detectors in the accuracy-vs-speed trade-off. Nevertheless single-shot detectors are immensely popular in embedded vision applications. This paper brings single-shot detectors up to the sa
Externí odkaz:
http://arxiv.org/abs/1901.03353