Multi-layer multi-instance kernel for video concept detection
Lists
Only you see this
Abstract
In video concept detection, most existing methods have not well studied the intrinsic hierarchical structure of video content. However, unlike flat attribute-value data used in many existing methods, video is essentially a structured media with multi-layer representation. For example, a video can be represented by a hierarchical structure including, from large to small, shot, key-frame, and region. Moreover, it fits the typical Multi-Instance (MI) setting in which the "bag-instance" correspondence is embedded among contiguous layers. We call such multi-layer structure and the "bag-instance" relation embedded in the structure as Multi-Layer Multi-Instance (MLMI) setting in this paper. We formulate video concept detection as an MLMI learning problem in which a rooted tree with MLMI nature embedded is devised to represent a video segment. Furthermore, by fusing the information from different layers, we construct a novel MLMI kernel to measure the similarities between the instances in the same and different layers. In contrast to traditional MI learning, both the Multi-Layer structure and Multi-Instance relations are leveraged simultaneously in the proposed kernel. We applied MLMI kernel to concept detection task on TRECVID 2005 corpus and reported superior performance (+25% in Mean Average Precision) to standard Support Vector Machine based approaches.
BibTeX
@inproceedings{gu2007multi,
author = {Zhiwei Gu and Tao Mei and Xian-Sheng Hua and Jinhui Tang and Xiuqing Wu},
title = {{Multi-layer multi-instance kernel for video concept detection}},
booktitle = {ACM Multimedia},
year = {2007},
doi = {10.1145/1291233.1291309},
}Loading related content...