Sep 1, 2022 · Our method can effectively extract object-level semantic information from weak user tags, and improve the accuracy of image retrieval.
Sep 1, 2022 · Our method can effectively extract object-level semantic information from weak user tags, and improve the accuracy of image retrieval.
CNN-based hashing methods have greatly boosted the performance of image retrieval, under the strong supervision of large amounts of manually annotated ...
Connected Papers is a visual tool to help researchers and applied scientists find academic papers relevant to their field of work.
In this paper, we for- mulate the problem of semantic image hashing as a weakly- supervised learning problem, utilizing user-generated tags associated with the ...
Missing: objectness | Show results with:objectness
Deep objectness hashing using large weakly tagged photos · Author Picture Fei Xie. Xidian University, AOAIR, Shannxi, China. School of Computer Science ...
Deep objectness hashing using large weakly tagged photos. F Xie, W Zhao, Z Guan, H Wang, Q Duan. Neurocomputing 502, 186-195, 2022. 3, 2022 ; A Hybrid framework ...
Dual-level Semantic Transfer Deep Hashing (DSTDH) constructs an image-concept hypergraph to model the latent high-order semantic correlations of images. Weakly ...
In this paper, we propose an efficient weakly-supervised hashing to solve the large-scale social image retrieval.