In recent years, with the increasing demand for public safety and the rapid development of
intelligent surveillance networks, person re-identification (Re-ID) has become one of the hot …

Automatic video search based on semantic concept detectors has recently received
significant attention. Since the number of available detectors is much smaller than the size of …

VIREO/DVMM at TRECVID 2009: High-level feature extraction, automatic video search, and
content-based copy detection Page 1 Singapore Management University Institutional Knowledge …

Automatic concept learning from large scale imbalanced data sets is a key issue in video
semantic analysis and retrieval, which means the number of negative examples is far more …

The misalignment of human images caused by bounding box detection errors or partial
occlusions is one of the main challenges in person Re-Identification (Re-ID) tasks. Previous …

By introducing the concept detection results to the retrieval process, concept-based video
retrieval (CBVR) has been successfully used for semantic content-based video retrieval …

Semantic Indexing and Multimedia Event Detection: ECNU at TRECVID 2012 1 Abstract Page
1 Semantic Indexing and Multimedia Event Detection: ECNU at TRECVID 2012 Feng Wang† …

In recent years, the methods of combining global and local features have shown great
potential in image retrieval task, the most recent and impressive work focus on feature fusion …

We present approaches to handle three correlated issues that are critical to this problem:(1)
how to construct an effective feature representation for semantic concept detection,(2) how …

As early as 1935, video archivists aimed to individually describe each shot in each film
acquired by their archive. However, it soon became apparent that it was impossible to …