Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Khodabandeh, Mehran"'
Domain shift is unavoidable in real-world applications of object detection. For example, in self-driving cars, the target domain consists of unconstrained road environments which cannot all possibly be observed in training data. Similarly, in surveil
Externí odkaz:
http://arxiv.org/abs/1904.02361
Discriminative learning machines often need a large set of labeled samples for training. Active learning (AL) settings assume that the learner has the freedom to ask an oracle to label its desired samples. Traditional AL algorithms heuristically choo
Externí odkaz:
http://arxiv.org/abs/1805.08916
Publikováno v:
The IEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPRW), 2018
The recent successes in applying deep learning techniques to solve standard computer vision problems has aspired researchers to propose new computer vision problems in different domains. As previously established in the field, training data itself pl
Externí odkaz:
http://arxiv.org/abs/1803.11264
We propose a general purpose active learning algorithm for structured prediction, gathering labeled data for training a model that outputs a set of related labels for an image or video. Active learning starts with a limited initial training set, then
Externí odkaz:
http://arxiv.org/abs/1706.02342
Autor:
Khodabandeh, Mehran, Vahdat, Arash, Zhou, Guang-Tong, Hajimirsadeghi, Hossein, Roshtkhari, Mehrsan Javan, Mori, Greg, Se, Stephen
We present a novel approach for discovering human interactions in videos. Activity understanding techniques usually require a large number of labeled examples, which are not available in many practical cases. Here, we focus on recovering semantically
Externí odkaz:
http://arxiv.org/abs/1502.03851
Autor:
Mousavian, Zaynab1 (AUTHOR) zmousavian@ut.ac.ir, Khodabandeh, Mehran2 (AUTHOR), Sharifi-Zarchi, Ali3,4 (AUTHOR), Nadafian, Alireza1 (AUTHOR), Mahmoudi, Alireza1 (AUTHOR)
Publikováno v:
BMC Bioinformatics. 6/29/2021, Vol. 22 Issue 1, p1-14. 14p.
Publikováno v:
2015 14th IAPR International Conference on Machine Vision Applications (MVA); 2015, p535-538, 4p