Sunggyun Park
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Sunggyun Park has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Donggeun Yoo
KAIST Daejeon South Korea
3 shared publications - In So Kweon
KAIST
3 shared publications - Anthony S. Paek
Lunit Inc Seoul South Korea
2 shared publications - Joon-Young Lee
KAIST 305-701 Daejeon Korea
2 shared publications Chi-Guhn Lee
Mechanical and Industrial Engineering, University of Toronto, Toronto, Canada
1 shared publicationKyoung-Kuk Kim
Industrial and Systems Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea
1 shared publication
Latest Publications
- Open Access
Pixel-Level Domain Transfer
We present an image-conditional image generation model. The model transfers an input domain to a target domain in semantic level, and generates the target image in pixel level. To generate realistic target images, we employ the real/fake-discriminator as in Generative Adversarial Nets, but also introduce a novel domain-discriminator to make the generated image relevant to the input image. We verify our model through a challenging task of generating a piece of clothing from an input image of a dressed person. We present a high quality clothing dataset containing the two domains, and succeed in demonstrating decent results.
Open AccessPixel-Level Domain Transfer
We present an image-conditional image generation model. The model transfers an input domain to a target domain in semantic level, and generates the target image in pixel level. To generate realistic target images, we employ the real/fake-discriminator as in Generative Adversarial Nets, but also introduce a novel domain-discriminator to make the generated image relevant to the input image. We verify our model through a challenging task of generating a piece of clothing from an input image of a dressed person. We present a high quality clothing dataset containing the two domains, and succeed in demonstrating decent results.
- Open Access
AttentionNet: Aggregating Weak Directions for Accurate Object Detection
We present a novel detection method using a deep convolutional neural network (CNN), named AttentionNet. We cast an object detection problem as an iterative classification problem, which is the most suitable form of a CNN. AttentionNet provides quantized weak directions pointing a target object and the ensemble of iterative predictions from AttentionNet converges to an accurate object boundary box. Since AttentionNet is a unified network for object detection, it detects objects without any separated models from the object proposal to the post bounding-box regression. We evaluate AttentionNet by a human detection task and achieve the state-of-the-art performance of 65% (AP) on PASCAL VOC 2007/2012 with an 8-layered architecture only.
Open AccessAttentionNet: Aggregating Weak Directions for Accurate Object Detection
We present a novel detection method using a deep convolutional neural network (CNN), named AttentionNet. We cast an object detection problem as an iterative classification problem, which is the most suitable form of a CNN. AttentionNet provides quantized weak directions pointing a target object and the ensemble of iterative predictions from AttentionNet converges to an accurate object boundary box. Since AttentionNet is a unified network for object detection, it detects objects without any separated models from the object proposal to the post bounding-box regression. We evaluate AttentionNet by a human detection task and achieve the state-of-the-art performance of 65% (AP) on PASCAL VOC 2007/2012 with an 8-layered architecture only.
- 10 August 2015
- Published by Taylor & Francis in International Journal of Production Research
- Vol. 54 (17) , 5283-5302
Dynamic pricing with ‘BOGO’ promotion in revenue management
We consider a dynamic pricing problem when a seller, facing uncertain demands, sells a single product in a finite horizon. The seller actively adopts dynamic pricing and quantity discount schemes. The proposed model is based on the assumption that each customer has random reservation prices and the purchase size depends on the posted price and discount. We particularly focus on the widely adopted promotional schemes ‘buy one get one free’ and ‘50% off’ and study the optimal strategic choices of the seller. Analytical results together with numerical experiments are presented to help us obtain managerial insights. Additional numerical results for a generalised model are provided so as to examine the effectiveness of promotional schemes.
- 10 August 2015
- Published by Taylor & Francis in International Journal of Production Research
- Vol. 54 (17) , 5283-5302
Dynamic pricing with ‘BOGO’ promotion in revenue management
We consider a dynamic pricing problem when a seller, facing uncertain demands, sells a single product in a finite horizon. The seller actively adopts dynamic pricing and quantity discount schemes. The proposed model is based on the assumption that each customer has random reservation prices and the purchase size depends on the posted price and discount. We particularly focus on the widely adopted promotional schemes ‘buy one get one free’ and ‘50% off’ and study the optimal strategic choices of the seller. Analytical results together with numerical experiments are presented to help us obtain managerial insights. Additional numerical results for a generalised model are provided so as to examine the effectiveness of promotional schemes.
- Open Access
Fisher Kernel for Deep Neural Activations
Compared to image representation based on low-level local descriptors, deep neural activations of Convolutional Neural Networks (CNNs) are richer in mid-level representation, but poorer in geometric invariance properties. In this paper, we present a straightforward framework for better image representation by combining the two approaches. To take advantages of both representations, we propose an efficient method to extract a fair amount of multi-scale dense local activations from a pre-trained CNN. We then aggregate the activations by Fisher kernel framework, which has been modified with a simple scale-wise normalization essential to make it suitable for CNN activations. Replacing the direct use of a single activation vector with our representation demonstrates significant performance improvements: +17.76 (Acc.) on MIT Indoor 67 and +7.18 (mAP) on PASCAL VOC 2007. The results suggest that our proposal can be used as a primary image representation for better performances in visual recognition tasks.
Open AccessFisher Kernel for Deep Neural Activations
Compared to image representation based on low-level local descriptors, deep neural activations of Convolutional Neural Networks (CNNs) are richer in mid-level representation, but poorer in geometric invariance properties. In this paper, we present a straightforward framework for better image representation by combining the two approaches. To take advantages of both representations, we propose an efficient method to extract a fair amount of multi-scale dense local activations from a pre-trained CNN. We then aggregate the activations by Fisher kernel framework, which has been modified with a simple scale-wise normalization essential to make it suitable for CNN activations. Replacing the direct use of a single activation vector with our representation demonstrates significant performance improvements: +17.76 (Acc.) on MIT Indoor 67 and +7.18 (mAP) on PASCAL VOC 2007. The results suggest that our proposal can be used as a primary image representation for better performances in visual recognition tasks.