Winston H. Hsu

Learn More
Multimedia search over distributed sources often result in recurrent images or videos which are manifested beyond the textual modality. To exploit such contextual patterns and keep the simplicity of the keyword-based search, we propose novel reranking methods to leverage the recurrent patterns to improve the initial text search results. The approach,(More)
We propose a novel and generic video/image reranking algorithm, IB reranking, which reorders results from text-only searches by discovering the salient visual patterns of relevant and irrelevant shots from the approximate relevance provided by text results. The IB reranking method, based on a rigorous Information Bottleneck (IB) principle, finds the optimal(More)
Recently, promising results have been shown on face recognition researches. However, face recognition and retrieval across age is still challenging. Unlike prior methods using complex models with strong parametric assumptions to model the aging process, we use a data-driven method to address this problem. We propose a novel coding framework called Cross-Age(More)
 A_CL1_1: choose the best-performing classifier for each concept from all the following runs and an event detection method.  A_CL2_2: (visual-based) choose the best-performing visual-based classifier for each concept from runs A_CL4_4, A_CL5_5, and A_CL6_6.  A_CL3_3: (visual-text) weighted average fusion of visual-based classifier A_CL4_4 with a text(More)
Leveraging community-contributed data (e.g., blogs, GPS logs, and geo-tagged photos) for travel recommendation is one of the active researches since there are rich contexts and trip activities in such explosively growing data. In this work, we focus on personalized travel recommendation by leveraging the freely available community-contributed photos. We(More)
3D object modeling and fine-grained classification are often treated as separate tasks. We propose to optimize 3D model fitting and fine-grained classification jointly. Detailed 3D object representations encode more information (e.g., precise part locations and viewpoint) than traditional 2D-based approaches, and can therefore improve fine-grained(More)
This paper introduces an approach for face cognizance throughout age and in addition a dataset containing variations of age in the wild. We use a data-driven system to deal with the go-age face realization challenge, known as cross-age reference coding (CARC). By using leveraging a colossal-scale snapshot dataset freely available on the web as a reference(More)
Oct. 28 2005 Descriptions of Submitted Runs High-Level feature extraction  A_DCON1_1: Choose the best-performing classifier from the following runs for each concept.  A_DCON2_2: linear weighted fusion of 4 SVM classifiers using color/texture, partsbased classifier, and tf-idf text classifier.  A_DCON3_3: same as above, except a new input-adaptive fusion(More)