Data Set Used
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)
In this paper we describe our participation in the NIST TRECVID-2003 evaluation. We participated in four tasks of the benchmark including shot boundary detection, high-level feature detection, story segmentation, and search. We describe the different runs we submitted for each track and discuss our performance.
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)
—Photos with people (e.g., family, friends, celebrities, 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… (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)
Description of Submitted Runs High-level feature extraction 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… (More)