Serwis Infona wykorzystuje pliki cookies (ciasteczka). Są to wartości tekstowe, zapamiętywane przez przeglądarkę na urządzeniu użytkownika. Nasz serwis ma dostęp do tych wartości oraz wykorzystuje je do zapamiętania danych dotyczących użytkownika, takich jak np. ustawienia (typu widok ekranu, wybór języka interfejsu), zapamiętanie zalogowania. Korzystanie z serwisu Infona oznacza zgodę na zapis informacji i ich wykorzystanie dla celów korzytania z serwisu. Więcej informacji można znaleźć w Polityce prywatności oraz Regulaminie serwisu. Zamknięcie tego okienka potwierdza zapoznanie się z informacją o plikach cookies, akceptację polityki prywatności i regulaminu oraz sposobu wykorzystywania plików cookies w serwisie. Możesz zmienić ustawienia obsługi cookies w swojej przeglądarce.
Recently, the community of style transfer is trying to incorporate semantic information into traditional system. This practice achieves better perceptual results by transferring the style between semantically-corresponding regions. Yet, few efforts are invested to address the computation bottleneck of back-propagation. In this paper, we propose a new framework for fast semantic style transfer. Our...
Early power modeling and analysis using electronic system-level methodology enables designers to explore energy saving opportunities more efficiently at a higher abstraction level. However, power modeling for third party IPs are challenging due to the limited observability and unknown architecture details. To model the data dependency for blackbox IPs, several works rely on adopting Hamming distance...
We present RON, an efficient and effective framework for generic object detection. Our motivation is to smartly associate the best of the region-based (e.g., Faster R-CNN) and region-free (e.g., SSD) methodologies. Under fully convolutional architecture, RON mainly focuses on two fundamental problems: (a) multi-scale object localization and (b) negative sample mining. To address (a), we design the...
We propose three regularization techniques to overcome drawbacks of local winner-take-all methods used in deep convolutional networks. Channel-Max inherits the max activation unit from Maxout networks, but otherwise adopts complementary subsets of input and filters with different kernel sizes as better companions to the max function. To balance the training on different pathways, Channel-Drop is employed...
In nowadays, hand gestures can be used as a more natural and convenient way for human computer interaction. The direct interface of hand gestures provides us a new way for communicating with the virtual environment. In this paper, we propose a new hand gesture recognition method using self-organizing map (SOM) with datagloves. The SOM method is a type of machine learning algorithm. It deals with the...
Image semantic retrieval usually involves two steps, namely image annotation and annotation-based retrieval. Although there is a rich literature on image auto-annotation, little focuses on bridging the gap between annotation and retrieval. In fact, the efficiency of an image semantic retrieval system depends not only on the precision of annotation but also the way to use the annotation result in the...
In order to improve the method of training the commander, the aerial instructor, back parachute commander, the guarantee unit and the aerial broadcaster, in this paper, we used Vega, Creator, and RTI implement the Parachute Jump Commanding And Simulation System to simulate the parachute jump commanding process. In this system, firstly, we used Creator build the 3D models that we need in the system;...
Because of its robustness, user friendliness, low cost and high accuracy, palmprint recognition has been widely studied in the past ten years. Various feature extraction and matching schemes have been proposed, among which the Gabor phase and orientation codes are very effective and efficient for palmprint representation and matching. Although these methods are adopted in the online palmprint recognition...
Podaj zakres dat dla filtrowania wyświetlonych wyników. Możesz podać datę początkową, końcową lub obie daty. Daty możesz wpisać ręcznie lub wybrać za pomocą kalendarza.