| 臺大學術典藏 |
2022-04-25T06:44:04Z |
XCos: An explainable cosine metric for face verification task
|
Lin Y.-S;Liu Z.-Y;Chen Y.-A;Wang Y.-S;Chang Y.-L;Hsu W.H.; Lin Y.-S; Liu Z.-Y; Chen Y.-A; Wang Y.-S; Chang Y.-L; Hsu W.H.; WINSTON HSU |
| 臺大學術典藏 |
2021-11-21T23:19:09Z |
Dual-Awareness Attention for Few-Shot Object Detection
|
Chen, Tung I.; Liu, Yueh Cheng; Su, Hung Ting; Chang, Yu Cheng; Lin, Yu Hsiang; Yeh, Jia Fong; WEN-CHIN CHEN; WINSTON HSU |
| 臺大學術典藏 |
2021-09-02T00:08:59Z |
Learn from the past – sequentially one-to-one video deblurring network
|
Liang C.-H;Su H.-T;Hsu W.H.; Liang C.-H; Su H.-T; Hsu W.H.; WINSTON HSU |
| 臺大學術典藏 |
2021-09-02T00:08:59Z |
Indoor depth completion with boundary consistency and self-attention
|
Huang Y.-K;Wu T.-H;Liu Y.-C;Hsu W.H.; Huang Y.-K; Wu T.-H; Liu Y.-C; Hsu W.H.; WINSTON HSU |
| 臺大學術典藏 |
2021-09-02T00:08:59Z |
End-to-End Video Question-Answer Generation with Generator-Pretester Network
|
Su H;Chang C;Shen P;Wang Y;Chang Y;Chang Y;Cheng P;Hsu W.H.; Su H; Chang C; Shen P; Wang Y; Chang Y; Chang Y; Cheng P; Hsu W.H.; WINSTON HSU |
| 臺大學術典藏 |
2021-09-02T00:08:58Z |
Situation and behavior understanding by trope detection on films
|
Chang C.-H;Su H.-T;Hsu J.-H;Wang Y.-S;Chang Y.-C;Liu Z.Y;Chang Y.-L;Cheng W.-F;Wang K.-J;Hsu W.H.; Chang C.-H; Su H.-T; Hsu J.-H; Wang Y.-S; Chang Y.-C; Liu Z.Y; Chang Y.-L; Cheng W.-F; Wang K.-J; Hsu W.H.; WINSTON HSU |
| 臺大學術典藏 |
2021-09-02T00:08:58Z |
Raw Image Deblurring
|
Liang C;Chen Y;Liu Y;Hsu W.; Liang C; Chen Y; Liu Y; Hsu W.; WINSTON HSU |
| 臺大學術典藏 |
2021-09-02T00:08:58Z |
Netizen-Style Commenting on Fashion Photos: Dataset and Diversity Measures
|
Lin W.H;Chen K.-T;Chiang H.Y;Hsu W.; Lin W.H; Chen K.-T; Chiang H.Y; Hsu W.; WINSTON HSU |
| 臺大學術典藏 |
2021-01-19T12:08:38Z |
Raw Image Deblurring
|
Liang, Chih Hung; Chen, Yu An; Liu, Yueh Cheng; WINSTON HSU |
| 臺大學術典藏 |
2020-05-04T08:09:16Z |
Discovery and fusion of salient multimodal features toward news story segmentation.
|
Hsu, Winston H.; Chang, Shih-Fu; Huang, Chih-Wei; Kennedy, Lyndon S.; Lin, Ching-Yung; Iyengar, Giridharan; WINSTON HSU |
| 臺大學術典藏 |
2020-05-04T08:09:16Z |
A statistical framework for fusing mid-level perceptual features in news story segmentation.
|
Hsu, Winston H.; Chang, Shih-Fu; WINSTON HSU |
| 臺大學術典藏 |
2020-05-04T08:09:16Z |
Story boundary detection in large broadcast news video archives: techniques, experience and trends.
|
Chua, Tat-Seng; Chang, Shih-Fu; Chaisorn, Lekha; Hsu, Winston H.; WINSTON HSU |
| 臺大學術典藏 |
2020-05-04T08:09:15Z |
Video search reranking via information bottleneck principle.
|
Chang, Shih-Fu; WINSTON HSU; Kennedy, Lyndon S.; Hsu, Winston H. |
| 臺大學術典藏 |
2020-05-04T08:09:15Z |
News video story segmentation using fusion of multi-level multi-modal features in TRECVID 2003.
|
Hsu, Winston H.; Kennedy, Lyndon S.; Huang, Chih-Wei; Chang, Shih-Fu; Lin, Ching-Yung; Iyengar, Giridharan; WINSTON HSU |
| 臺大學術典藏 |
2020-05-04T08:09:15Z |
Topic Tracking Across Broadcast News Videos with Visual Duplicates and Semantic Concepts.
|
Hsu, Winston H.; Chang, Shih-Fu; WINSTON HSU |
| 臺大學術典藏 |
2020-05-04T08:09:14Z |
SheepDog: group and tag recommendation for flickr photos by automatic search-based learning.
|
Chen, Hong-Ming; Chang, Ming-Hsiu; Chang, Ping-Chieh; Tien, Min-Chun; Hsu, Winston H.; Wu, Ja-Ling; WINSTON HSU |
| 臺大學術典藏 |
2020-05-04T08:09:14Z |
AdImage: video advertising by image matching and ad scheduling optimization.
|
Liao, Wei-Shing; Chen, Kuan-Ting; Hsu, Winston H.; WINSTON HSU |
| 臺大學術典藏 |
2020-05-04T08:09:14Z |
NTU TRECVID-2007 fast rushes summarization system.
|
Pan, Chen-Ming; Chuang, Yung-Yu; Hsu, Winston H.; WINSTON HSU |
| 臺大學術典藏 |
2020-05-04T08:09:14Z |
Video search reranking through random walk over document-level context graph.
|
Hsu, Winston H.; Kennedy, Lyndon S.; Chang, Shih-Fu; WINSTON HSU |
| 臺大學術典藏 |
2020-05-04T08:09:14Z |
Large-Scale Concept Ontology for Multimedia.
|
Naphade, Milind R.; Smith, John R.; Tesic, Jelena; Chang, Shih-Fu; Hsu, Winston H.; Kennedy, Lyndon S.; Hauptmann, Alexander G.; Curtis, Jon; WINSTON HSU |
| 臺大學術典藏 |
2020-05-04T08:09:13Z |
Canonical image selection and efficient image graph construction for large-scale flickr photos.
|
Hsieh, Liang-Chi; Chen, Kuan-Ting; Chiang, Chien-Hsing; Yang, Yi-Hsuan; Wu, Guan-Long; Ferng, Chun-Sung; Hsueh, Hsiu-Wen; Tsai, Angela Charng-Rurng; Hsu, Winston H.; WINSTON HSU; Hsieh, Liang-Chi;Chen, Kuan-Ting;Chiang, Chien-Hsing;Yang, Yi-Hsuan;Wu, Guan-Long;Ferng, Chun-Sung;Hsueh, Hsiu-Wen;Tsai, Angela Charng-Rurng;Hsu, Winston H. |
| 臺大學術典藏 |
2020-05-04T08:09:13Z |
Video search reranking via online ordinal reranking.
|
Yang, Yi-Hsuan; Hsu, Winston H.; WINSTON HSU |
| 臺大學術典藏 |
2020-05-04T08:09:13Z |
Adaptive Learning for Multimodal Fusion in Video Search.
|
Lee, Wen-Yu;Wu, Po Tun;Hsu, Winston H.; Lee, Wen-Yu; Wu, Po Tun; Hsu, Winston H.; WINSTON HSU |
| 臺大學術典藏 |
2020-05-04T08:09:13Z |
ContextSeer: context search and recommendation at query time for shared consumer photos.
|
Yang, Yi-Hsuan; Wu, Po Tun; Lee, Ching-Wei; Lin, Kuan Hung; Hsu, Winston H.; Chen, Homer H.; WINSTON HSU |
| 臺大學術典藏 |
2020-05-04T08:09:12Z |
Boosting object retrieval by estimating pseudo-objects.
|
Lin, Kuan Hung;Chen, Kuan-Ting;Hsu, Winston H.;Lee, Chun Jen;Li, Tien Hsu; Lin, Kuan Hung; Chen, Kuan-Ting; Hsu, Winston H.; Lee, Chun Jen; Li, Tien Hsu; WINSTON HSU |
