홍성은 교수

Real-world face recognition using a single sample per person (SSPP) is a challenging task. The problem is exacerbated if the conditions under which the gallery image and the probe set are captured are completely different. To address these issues from the perspective of domain adaptation, we introduce an SSPP domain adaptation network (SSPP-DAN). In the proposed approach, domain adaptation, feature extraction, and classification are performed jointly using a deep architecture with domain-adversa

Object detection in specific views (e.g., top view, road view, and aerial view) suffers from a lack of dataset, which causes class imbalance and difficulties of covering hard examples. In order to handle these issues, we propose a hard chip mining method that makes the ratio of each class balanced and generates hard examples that are efficient for model training. First, we generate multi-scale chips to train object detector. Next, we extract object patches from the dataset to construct an object

Up to now, only limited research has been conducted on crossmodal retrieval of suitable music for a specified video or vice versa. Moreover, much of the existing research relies on metadata such as keywords, tags, or description that must be individually produced and attached posterior. This paper introduces a new content-based, cross-modal retrieval method for video and music that is implemented through deep neural networks. We train the network via inter-modal ranking loss such that videos and

Low-resolution face recognition suffers from domain shift due to the different resolution between a high-resolution gallery and a low-resolution probe set. Conventional methods use the pairwise correlation between high-resolution and low-resolution for the same subject, which requires label information for both gallery and probe sets. However, explicitly labeled low-resolution probe images are seldom available, and labeling them is labor-intensive. In this paper, we propose a novel unsupervised

Real-world face recognition using a single sample per person (SSPP) is a challenging task. The problem is exacerbated if the conditions under which the gallery image and the probe set are captured are completely different. To address these issues from the perspective of domain adaptation, we introduce an SSPP domain adaptation network (SSPP-DAN). In the proposed approach, domain adaptation, feature extraction, and classification are performed jointly using a deep architecture with domain-adversa

Up to now, only limited research has been conducted on cross-modal retrieval of suitable music for a specified video or vice versa. Moreover, much of the existing research relies on metadata such as keywords, tags, or associated description that must be individually produced and attached posterior. This paper introduces a new content-based, cross-modal retrieval method for video and music that is implemented through deep neural networks. We train the network via inter-modal ranking loss such tha

In this Letter, the authors introduce attention‐guided domain adaptation networks for face recognition under the unsupervised setting. Recently, there has been a dramatic increase in demand for real‐world face recognition problems under severe domain shifts. Adversarial learning of the domain adaptation network has shown promising results for this problem. However, this approach has limitations in manually setting the adaptation factor that controls the trade‐off between feature discriminability

Preview this article: Ein empirische Untersuchung zu Kongruenzverben in der Koreanischen Gebärdensprache [An empirical investigation of agreement verbs in Korean Sign Language] (University of Hamburg, 2008), Page 1 of 1 < Previous page | Next page > /docserver/preview/fulltext/sll.12.2.08hon-1.gif