Learn 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)
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)
In this technical report, we give an overview our technical developments in the story segmentation task in TRECVID 2004. Among them, we propose an information-theoretic framework, visual cue cluster construction (VC 3), to automatically discover adequate mid-level features. The problem is posed as mutual information maximization, through which optimal cue(More)
 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, parts-based classifier, and tf-idf text classifier.  A_DCON3_3: same as above, except a new input-adaptive fusion method was used.  A_DCON4_4: average fusion of 4 SVM classifiers using(More)
etc.) are the major interest of users. Thus, with the exponentially growing photos, large-scale content-based face image retrieval is an enabling technology for many emerging applications. In this work, we aim to utilize automatically detected human attributes that contain semantic cues of the face photos to improve content-based face retrieval by(More)