J Yang, R Yan, AG Hauptmann - Proceedings of the 15th ACM …, 2007 - dl.acm.org
Many multimedia applications can benefit from techniques for adapting existing classifiers to data with different distributions. One example is cross-domain video concept detection which …
Exploding amounts of multimedia data increasingly require automatic indexing and classification, eg training classifiers to produce high-level features, or semantic concepts …
We propose a multiple source domain adaptation method, referred to as Domain Adaptation Machine (DAM), to learn a robust decision function (referred to as target classifier) for label …
Y Wu, BL Tseng, JR Smith - … and Expo (ICME)(IEEE Cat. No …, 2004 - ieeexplore.ieee.org
In this paper, an ontology-based multi-classification learning algorithm is adopted to detect concepts in the NIST TREC-2003 video retrieval benchmark which defines 133 video …
Video concept learning often requires a large set of training samples. In practice, however, acquiring noise-free training labels with sufficient positive examples is very expensive. A …
We present a compositional model for video event detection. A video is modeled using a collection of both global and segment-level features and kernel functions are employed for …
R Yan, M Naphade - … Vision and Pattern Recognition (CVPR'05 …, 2005 - ieeexplore.ieee.org
For large scale automatic semantic video characterization, it is necessary to learn and model a large number of semantic concepts. But a major obstacle to this is the insufficiency of …
Y Lu, C Lu, CK Tang - Proceedings of the IEEE International …, 2017 - openaccess.thecvf.com
Video object detection is a fundamental tool for many applications. Since direct application of image-based object detection cannot leverage the rich temporal information inherent in …
Automatic semantic concept detection in video is important for effective content-based video retrieval and mining and has gained great attention recently. In this paper, we propose a …