Topical Video Object Discovery from Key Frames by Modeling Word Co-occurrence Prior

Gangqiang Zhao, Junsong Yuan, Gang Hua
2013 2013 IEEE Conference on Computer Vision and Pattern Recognition  
A topical video object refers to an object that is frequently highlighted in a video. It could be, e.g., the product logo and the leading actor/actress in a TV commercial. We propose a topic model that incorporates a word co-occurrence prior for efficient discovery of topical video objects from a set of key frames. Previous work using topic models, such as Latent Dirichelet Allocation (LDA), for video object discovery often takes a bag-of-visual-words representation, which ignored important
more » ... ccurrence information among the local features. We show that such data driven co-occurrence information from bottom-up can conveniently be incorporated in LDA with a Gaussian Markov prior, which combines top down probabilistic topic modeling with bottom up priors in a unified model. Our experiments on challenging videos demonstrate that the proposed approach can discover different types of topical objects despite variations in scale, view-point, color and lighting changes, or even partial occlusions. The efficacy of the co-occurrence prior is clearly demonstrated when comparing with topic models without such priors.
doi:10.1109/cvpr.2013.210 dblp:conf/cvpr/ZhaoYH13 fatcat:2zxlf4kvrfhgfgfkcfxu4gertu