| 臺大學術典藏 |
2020-05-04T08:09:00Z |
Egocentric activity recognition by leveraging multiple mid-level representations.
|
Hsieh, Peng-Ju; Lin, Yen-Liang; Chen, Yu-Hsiu; Hsu, Winston H.; WINSTON HSU |
| 臺大學術典藏 |
2020-05-04T08:09:00Z |
Scalable object detection by filter compression with regularized sparse coding.
|
Chao, Ting-Hsuan;Lin, Yen-Liang;Kuo, Yin-Hsi;Hsu, Winston H.; Chao, Ting-Hsuan; Lin, Yen-Liang; Kuo, Yin-Hsi; Hsu, Winston H.; WINSTON HSU |
| 臺大學術典藏 |
2020-05-04T08:09:00Z |
Mediated experts for deep convolutional networks.
|
Agethen, Sebastian;Hsu, Winston H.; Agethen, Sebastian; Hsu, Winston H.; WINSTON HSU |
| 臺大學術典藏 |
2020-05-04T08:09:00Z |
Proceedings of the 2016 ACM on International Conference on Multimedia Retrieval, ICMR 2016, New York, New York, USA, June 6-9, 2016
|
WINSTON HSU |
| 臺大學術典藏 |
2020-05-04T08:08:59Z |
Harnessing A.I. for Augmenting Creativity: Application to Movie Trailer Creation.
|
Smith, John R.; Joshi, Dhiraj; Huet, Benoit; Hsu, Winston H.; Cota, Jozef; WINSTON HSU |
| 臺大學術典藏 |
2020-05-04T08:08:59Z |
Super-Identity Convolutional Neural Network for Face Hallucination.
|
Zhang, Kaipeng; Zhang, Zhanpeng; Cheng, Chia-Wen; Hsu, Winston H.; Qiao, Yu; Liu, Wei; Zhang, Tong; WINSTON HSU |
| 臺大學術典藏 |
2020-05-04T08:08:59Z |
Joint Sequence Learning and Cross-Modality Convolution for 3D Biomedical Segmentation.
|
Tseng, Kuan-Lun;Lin, Yen-Liang;Hsu, Winston H.;Huang, Chung-Yang; Tseng, Kuan-Lun; Lin, Yen-Liang; Hsu, Winston H.; Huang, Chung-Yang; WINSTON HSU |
| 臺大學術典藏 |
2020-05-04T08:08:59Z |
Multi-task learning for face identification and attribute estimation.
|
Hsieh, Hui-Lan; Hsu, Winston H.; Chen, Yan-Ying; WINSTON HSU |
| 臺大學術典藏 |
2020-05-04T08:08:59Z |
Drone-Based Object Counting by Spatially Regularized Regional Proposal Network.
|
Hsieh, Meng-Ru; Lin, Yen-Liang; Hsu, Winston H.; WINSTON HSU |
| 臺大學術典藏 |
2020-05-04T08:08:59Z |
Feature Learning with Rank-Based Candidate Selection for Product Search.
|
WINSTON HSU; Hsu, Winston H.; Kuo, Yin-Hsi |
| 臺大學術典藏 |
2020-05-04T08:08:58Z |
Anticipation of Human Actions With Pose-Based Fine-Grained Representations.
|
Agethen, Sebastian;Lee, Hu-Cheng;Hsu, Winston H.; Agethen, Sebastian; Lee, Hu-Cheng; Hsu, Winston H.; WINSTON HSU |
| 臺大學術典藏 |
2020-05-04T08:08:58Z |
Learning from 3D (Point Cloud) Data.
|
Hsu, Winston H.; Hsu, Winston H.; WINSTON HSU |
| 臺大學術典藏 |
2020-05-04T08:08:58Z |
Audio Feature Generation for Missing Modality Problem in Video Action Recognition.
|
Lee, Hu-Cheng;Lin, Chih-Yu;Hsu, Pin-Chun;Hsu, Winston H.; Lee, Hu-Cheng; Lin, Chih-Yu; Hsu, Pin-Chun; Hsu, Winston H.; WINSTON HSU |
| 臺大學術典藏 |
2020-05-04T08:08:58Z |
Saliency Aware: Weakly Supervised Object Localization.
|
Chen, Yun-Chun;Hsu, Winston H.; Chen, Yun-Chun; Hsu, Winston H.; WINSTON HSU |
| 臺大學術典藏 |
2020-05-04T08:08:58Z |
PIVTONS: Pose Invariant Virtual Try-On Shoe with Conditional Image Completion.
|
WINSTON HSU; Hsu, Winston H.; Lee, Hu-Cheng; Zhang, Kaipeng; Lee, Cheng-Han; Chou, Chao-Te |
| 臺大學術典藏 |
2020-05-04T08:08:57Z |
A middleware architecture to improve the efficiency of web-based telemedicine application
|
Lin, C.-C.; Hsu, W.-H.; Chen, J.-H.; Chen, H.-S.; Chen, C.-Y.; Hou, S.-M.; WINSTON HSU |
| 臺大學術典藏 |
2020-05-04T08:08:57Z |
Reranking methods for visual search
|
Hsu, Winston H.; Kennedy, Lyndon S.; Chang, Shih-Fu; WINSTON HSU |
| 臺大學術典藏 |
2020-05-04T08:08:57Z |
A Unified Point-Based Framework for 3D Segmentation.
|
Chiang, HungYueh;Lin, Yen-Liang;Liu, Yueh-Cheng;Hsu, Winston H.; Chiang, HungYueh; Lin, Yen-Liang; Liu, Yueh-Cheng; Hsu, Winston H.; WINSTON HSU |
| 臺大學術典藏 |
2019-07-10T06:02:42Z |
Story boundary detection in large broadcast news video archives - Techniques, experience and trends
|
WINSTON HSU;Chaisorn, Lekha;Chang, Shih Fu;Chua, Tat Seng; Chua, Tat Seng; Chang, Shih Fu; Chaisorn, Lekha; WINSTON HSU |
| 臺大學術典藏 |
2019-07-10T06:02:42Z |
Story boundary detection in large broadcast news video archives - Techniques, experience and trends
|
WINSTON HSU;Chaisorn, Lekha;Chang, Shih Fu;Chua, Tat Seng; Chua, Tat Seng; Chang, Shih Fu; Chaisorn, Lekha; WINSTON HSU |
| 臺大學術典藏 |
2019-07-10T05:51:29Z |
Topic tracking across broadcast news videos with visual duplicates and semantic concepts
|
Chang, Shih Fu;WINSTON HSU; WINSTON HSU; Chang, Shih Fu |
| 臺大學術典藏 |
2019-07-10T05:51:29Z |
Topic tracking across broadcast news videos with visual duplicates and semantic concepts
|
Chang, Shih Fu;WINSTON HSU; WINSTON HSU; Chang, Shih Fu |
| 臺大學術典藏 |
2015-04 |
Enhancing Sparse Voice Annotation for Semantic Retrieval of Personal Photos by Continuous Space Word Representations
|
Yuan-ming Liou;Hung-tsung Lu;Yi-sheng Fu;Winston Hsu;Lin-shan Lee; Yuan-ming Liou; Hung-tsung Lu; Yi-sheng Fu; Winston Hsu; Lin-shan Lee; LIN-SHAN LEE |
| 臺大學術典藏 |
2015-04 |
Enhancing Sparse Voice Annotation for Semantic Retrieval of Personal Photos by Continuous Space Word Representations
|
Yuan-ming Liou;Hung-tsung Lu;Yi-sheng Fu;Winston Hsu;Lin-shan Lee; Yuan-ming Liou; Hung-tsung Lu; Yi-sheng Fu; Winston Hsu; Lin-shan Lee; LIN-SHAN LEE |
| 臺大學術典藏 |
2015 |
Who are the Devils Wearing Prada in New York City?
|
Chen, Kuan-Ting;Chen, Kezhen;Cong, Peizhong;Hsu, Winston H.;Luo, Jiebo; Chen, Kuan-Ting; Chen, Kezhen; Cong, Peizhong; Hsu, Winston H.; Luo, Jiebo; WINSTON HSU |
