Zobrazeno 1 - 10
of 15
pro vyhledávání: '"Hickson, Steven"'
Autor:
Lee, Seung Hyun, Ke, Junjie, Li, Yinxiao, He, Junfeng, Hickson, Steven, Datsenko, Katie, Kim, Sangpil, Yang, Ming-Hsuan, Essa, Irfan, Yang, Feng
The goal of image cropping is to identify visually appealing crops within an image. Conventional methods rely on specialized architectures trained on specific datasets, which struggle to be adapted to new requirements. Recent breakthroughs in large v
Externí odkaz:
http://arxiv.org/abs/2408.07790
We propose 4 insights that help to significantly improve the performance of deep learning models that predict surface normals and semantic labels from a single RGB image. These insights are: (1) denoise the "ground truth" surface normals in the train
Externí odkaz:
http://arxiv.org/abs/1906.06792
We consider the problem of retrieving objects from image data and learning to classify them into meaningful semantic categories with minimal supervision. To that end, we propose a fully differentiable unsupervised deep clustering approach to learn se
Externí odkaz:
http://arxiv.org/abs/1801.08985
We present an efficient and scalable algorithm for segmenting 3D RGBD point clouds by combining depth, color, and temporal information using a multistage, hierarchical graph-based approach. Our algorithm processes a moving window over several point c
Externí odkaz:
http://arxiv.org/abs/1801.08981
Autor:
Castro, Daniel, Hickson, Steven, Sangkloy, Patsorn, Mittal, Bhavishya, Dai, Sean, Hays, James, Essa, Irfan
In recent years, deep neural network approaches have naturally extended to the video domain, in their simplest case by aggregating per-frame classifications as a baseline for action recognition. A majority of the work in this area extends from the im
Externí odkaz:
http://arxiv.org/abs/1801.07388
Most of the approaches for indoor RGBD semantic la- beling focus on using pixels or superpixels to train a classi- fier. In this paper, we implement a higher level segmentation using a hierarchy of superpixels to obtain a better segmen- tation for tr
Externí odkaz:
http://arxiv.org/abs/1708.00946
We propose an algorithm that uses energy mini- mization to estimate the current configuration of a non-rigid object. Our approach utilizes an RGBD image to calculate corresponding SURF features, depth, and boundary informa- tion. We do not use predet
Externí odkaz:
http://arxiv.org/abs/1708.00940
One of the main challenges of social interaction in virtual reality settings is that head-mounted displays occlude a large portion of the face, blocking facial expressions and thereby restricting social engagement cues among users. Hence, auxiliary m
Externí odkaz:
http://arxiv.org/abs/1707.07204
Autor:
Castro, Daniel, Hickson, Steven, Bettadapura, Vinay, Thomaz, Edison, Abowd, Gregory, Christensen, Henrik, Essa, Irfan
Publikováno v:
ISWC '15 Proceedings of the 2015 ACM International Symposium on Wearable Computers - Pages 75-82
We present a method to analyze images taken from a passive egocentric wearable camera along with the contextual information, such as time and day of week, to learn and predict everyday activities of an individual. We collected a dataset of 40,103 ego
Externí odkaz:
http://arxiv.org/abs/1510.01576
Publikováno v:
2015 IEEE Winter Conference on Applications of Computer Vision; 2015, p1068-1075, 8p
