Unsupervised Segmentation of Color-Texture Regions in Images and Video
IEEE Transactions on Pattern Analysis and Machine Intelligence
ICML '02 Proceedings of the Nineteenth International Conference on Machine Learning
Image Categorization by Learning and Reasoning with Regions
The Journal of Machine Learning Research
MILES: Multiple-Instance Learning via Embedded Instance Selection
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Multimedia
MILC2: a multi-layer multi-instance learning approach to video concept detection
MMM'08 Proceedings of the 14th international conference on Advances in multimedia modeling
Enhancing multi-lingual information extraction via cross-media inference and fusion
COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics: Posters
Semi-supervised multi-instance multi-label learning for video annotation task
Proceedings of the 20th ACM international conference on Multimedia
Hi-index | 0.00 |
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.