2021 IEEE International Conference on Acoustics, Speech and Signal Processing
6-11 June 2021 • Toronto, Ontario, Canada
Extracting Knowledge from Information
| Paper ID | MLSP-38.3 | ||
| Paper Title | DHCN: DEEP HIERARCHICAL CONTEXT NETWORKS FOR IMAGE ANNOTATION | ||
| Authors | Mingyuan Jiu, Zhengzhou University, China; Hichem Sahbi, CNRS Sorbonne University, France | ||
| Session | MLSP-38: Neural Networks for Clustering and Classification | ||
| Location | Gather.Town | ||
| Session Time: | Thursday, 10 June, 16:30 - 17:15 | ||
| Presentation Time: | Thursday, 10 June, 16:30 - 17:15 | ||
| Presentation | Poster | ||
| Topic | Machine Learning for Signal Processing: [MLR-PRCL] Pattern recognition and classification | ||
| IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
| Abstract | Context modeling is one of the most fertile subfields of visual recognition which aims at designing discriminant image representations while incorporating their intrinsic and extrinsic relationships. However, the potential of context modeling is currently under-explored and most of the existing solutions are either context-free or restricted to simple handcrafted geometric relationships. We introduce in this paper DHCN: a novel Deep Hierarchical Context Network that leverages different sources of contexts including geometric and semantic relationships. The proposed method is based on the minimization of an objective function mixing a fidelity term, a context criterion and a regularizer. The solution of this objective function defines the architecture of a bi-level hierarchical context network; the first level of this network captures scene geometry while the second one corresponds to semantic relationships. We solve this representation learning problem by training its underlying deep network whose parameters correspond to the most influencing bi-level contextual relationships and we evaluate its performances on image annotation using the challenging ImageCLEF benchmark. | ||