Abstract Hashing has become a promising technique to be applied to the large-scale visual retrieval tasks. Multi-view data has multiple views, providing more comprehensive information. Existing hashing methods measure the similarity among the data points by the pre-defined graph Laplacian in each view separately, and thus ignore the underlying common structures across different views. In this paper, we propose a novel hashing method, called adaptive multi-graph hashing (AMGH) to address the above issue. AMGH uses the adaptive weights among the data points, and the weights of each view to characterize the common structure of multi-view data. In addition, AMGH further minimizes the quantization errors. We develop an efficient alternating algorithm to solve the formulated optimization problem. The experiments on three large-scale datasets demonstrate the superiority of the proposed method over the existing multi-view hashing methods.
Paper
Full text
WITHDRAWN: Adaptive multi-graph hashing for scalable multimedia retrieval
Semantic Scholar · Computer Science · 2019
Abstract
Abstract Hashing has become a promising technique to be applied to the large-scale visual retrieval tasks. Multi-view data has multiple views, providing more comprehensive information. Existing hashing methods measure the similarity among the data points by the pre-defined graph Laplacian in each view separately, and thus ignore the underlying common structures across different views. In this paper, we propose a novel hashing method, called adaptive multi-graph hashing (AMGH) to address the above issue. AMGH uses the adaptive weights among the data points, and the weights of each view to characterize the common structure of multi-view data. In addition, AMGH further minimizes the quantization errors. We develop an efficient alternating algorithm to solve the formulated optimization problem. The experiments on three large-scale datasets demonstrate the superiority of the proposed method over the existing multi-view hashing methods.