ACTIVE: Activity Concept Transitions in Video Event Classification
Authors:
- Chen SunCSChen Sun
- Ram NevatiaRNRam Nevatia
- 1 December 2013
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15505499,p. 913-920
Abstract
The goal of high level event classification from videos is to assign a single, high level event label to each query video. Traditional approaches represent each video as a set of low level features and encode it into a fixed length feature vector (e.g. Bag-of-Words), which leave a big gap between low level visual features and high level events. Our paper tries to address this problem by exploiting activity concept transitions in video events (ACTIVE). A video is treated as a sequence of short clips, all of which are observations corresponding to latent activity concept variables in a Hidden Markov Model (HMM). We propose to apply Fisher Kernel techniques so that the concept transitions over time can be encoded into a compact and fixed length feature vector very efficiently. Our approach can utilize concept annotations from independent datasets, and works well even with a very small number of training samples. Experiments on the challenging NIST TRECVID Multimedia Event Detection (MED) dataset shows our approach performs favorably over the state-of-the-art.Keywords
This publication has 17 references indexed in Scilit:
- Large-scale web video event classification by use of Fisher Vectors2013
- Multimodal feature fusion for robust event detection in web videos2012
- Learning latent temporal structure for complex event detection2012
- Recognizing human actions by attributes2011
- Action recognition by dense trajectories2011
- Evaluation of local spatio-temporal features for action recognition2009
- Fisher Kernels on Visual Vocabularies for Image Categorization2007
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- Recognizing human actions: a local SVM approach2004
- A tutorial on hidden Markov models and selected applications in speech recognitionProceedings of the IEEE, 1989