… 30], which preserved the parameters learned by ImageNet [6], but replaced the last fully-connected
layer with two new fully-connected layers to adapt to the new visual recognition tasks. …

… This article thoroughly reviews the applications of DL in the field of visual recognition and
detection for aquatic animals (including not only marine animals, but also animals bred in fresh …

… recognition systems. Second, based on of the aforementioned analysis, we propose a deep
learning-based visual recognition … the concept of Transfer Learning, that achieves better than …

… Therefore, this study proposed a visual recognition model based deep learning to classify
different types of navigation marks. And, the contributions of this study is highlighted as follows…

… audio-visual recognition task as an application of our approach, our framework is flexible
and thus can work with any multimodal dataset, or with any already-existing deep networks that …

… In this paper, we present a high-resolution network for visual recognition problems. There
are three … Her current research interests include computer vision and deep learning. …

… Sparsely connected weights have been widely used in visual recognition algorithms (… For
one, human visual recognition of partially visible objects is more accurate if the occluding ob…

… multi-level deep learning algorithm is developed to learn multiple deep networks and a …
learning tasks automatically. Our multi-level deep learning algorithm can: (a) train multiple deep …

… Then, we propose a deep learning weed recognition and detection system based on 2D
visual input and evaluate it on data collected by our robot. Our system achieves state-of-the-art …

… visual recognition … for visual recognition tasks. Inspired by these papers, researchers from
VPR community start to utilize advanced deep learning techniques to tackle place recognition. …