| 1 |
Visual word proximity and linguistic for semantic video indexing and near-duplicate retrieval
|
|
|
|
In: http://vireo.cs.cityu.edu.hk/papers/cviu09_jiang.pdf (2009)
|
|
Abstract:
Bag-of-visual-words (BoW) has recently become a popular representation to describe video and image content. Most existing approaches, nevertheless, neglect inter-word relatedness and measure similarity by bin-to-bin comparison of visual words in histograms. In this paper, we explore the linguistic and ontological aspects of visual words for video analysis. Two approaches, soft-weighting and Constraintbased Earth Mover’s Distance (CEMD), are proposed to model different aspects of visual word linguistics and proximity. In soft-weighting, visual words are cleverly weighted such that the linguistic meaning of words is taken into account for bin-to-bin histogram comparison. In CEMD, a cross-bin matching algorithm is formulated such that the ground distance measure considers the linguistic similarity of words. In particular, a BoW ontology which hierarchically specifies the hyponym relationship of words is constructed to assist the reasoning. We demonstrate softweighting and CEMD on two tasks: video semantic indexing and near-duplicate keyframe retrieval. Experimental results indicate that soft-weighting is superior to other popular weighting schemes such as term frequency (TF) weighting in largescale video database. In addition, CEMD shows excellent performance compared to cosine similarity in near-duplicate retrieval.
|
|
Keyword:
Yu-Gang Jiang and Chong-Wah Ngo
|
|
URL: http://vireo.cs.cityu.edu.hk/papers/cviu09_jiang.pdf
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.329.4363
|
|
BASE
|
|
Hide details
|
|
|
|
|
