DHCN: Deep Hierarchical Context Networks For Image Annotation

Abstract

Context modeling is one of the most fertile sub-fields 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.

A Time-Sensitive Graph Neural Network for Session-Based New Item Recommendation

“…We compare our method with seven state-of-the-art methods, including SR-GNN [23], SR-GNN-ATT, GC-SAN [64], GCE-GNN [65], DHCN [66], COTREC [67], and NirGNN [24]. Table 2 shows the details of baselines.…”

Lightweight Graph Convolutional Networks with Topologically Consistent Magnitude Pruning

“…Several methods have been proposed in the literature in order to design lightweight yet effective deep convolutional networks [51]- [56], [102]. Some of them build efficient networks from scratch while others pretrain heavy networks prior to reduce their time and memory footprint using distillation [57], [58], [60], [61], [63], [65] and pruning [66], [68], [69].…”