Sep 20, 2017 � Then a query-adaptive feature fusion method is proposed, which is used jointly with 2-D inverted index under the framework of bag-of-words.
Recently, image representation based on convolutional neural network (CNN) becomes more popular than SIFT based feature, such as Fisher vector (FV).
We extract CNN feature and FV from multi-scale regions, which makes the representation more robust to image noise. Then a query-adaptive feature fusion method�...
Region based Image Retrieval with Query-Adaptive Feature Fusion. Zhang, Guixuan ; Zhang, Shuwu ; Zeng, Zhi ; Guan, Hu ; Wang, Fangxin. 2017. 会议名称, IEEE�...
... Image & Video Labeling and Retrieval. Paper Title: REGION BASED IMAGE RETRIEVAL WITH QUERY-ADAPTIVE FEATURE FUSION. Authors: Guixuan Zhang, Shuwu Zhang, Zhi�...
This paper proposes a multi-feature fusion image retrieval strategy with adaptive features based on information entropy theory.
In this paper, a novel regions-of-attention (ROA) based feature extraction and fusion scheme for efficient image retrieval is suggested.
Feature fusion has been proven effective [35, 36] in im- age search. Typically, it is assumed that the to-be-fused het- erogeneous features work well by�...
It was compared to an online image retrieving system called MMRetrieval and to the proposed system but without using association rules. The obtained results�...
Oct 19, 2024 � Based on this, we propose a multi-scale adaptive feature fusion hash image retrieval method, which mines more detailed information about the�...
Missing: Region | Show results with:Region
