The main novelty of the proposed approach is that it allows a robot to learn an end-to-end policy which can adapt to changes in the environment during execution.
The usage of convolutional neural networks (CNNs) for unsupervised image segmentation was investigated in this study.
Specifically, we train a deep convolutional network that can predict collision-free paths based on a map of the environment-- this is then used by a reinforcement learning algorithm to learn to closely follow the path.
Various saliency detection algorithms from color images have been proposed to mimic eye fixation or attentive object detection response of human observers for the same scenes.
Bottom-up and top-down visual cues are two types of information that helps the visual saliency models.
2 code implementations • 20 Jul 2017 • Hirokatsu Kataoka, Soma Shirakabe, Yun He, Shunya Ueta, Teppei Suzuki, Kaori Abe, Asako Kanezaki, Shin'ichiro Morita, Toshiyuki Yabe, Yoshihiro Kanehara, Hiroya Yatsuyanagi, Shinya Maruyama, Ryosuke Takasawa, Masataka Fuchida, Yudai Miyashita, Kazushige Okayasu, Yuta Matsuzaki
The paper gives futuristic challenges disscussed in the cvpaper. challenge.
We propose a Convolutional Neural Network (CNN)-based model "RotationNet," which takes multi-view images of an object as input and jointly estimates its pose and object category.
We present a novel dataset and a novel algorithm for recognizing activities of daily living (ADL) from a first-person wearable camera.