Object Interaction Recommendation with Multi-Modal Attention-based Hierarchical Graph Neural Network

Recipe recommendation systems play an important role in helping people find recipes that are of their interest and fit their eating habits. Unlike what has been developed for recommending recipes using content-based or collaborative filtering approaches, the relational information among users, recipes, and food items is less explored. In this paper, we leverage the relational information into recipe recommendation and propose a graph learning approach to solve it. In particular, we propose HGAT, a novel hierarchical graph attention network for recipe recommendation. The proposed model can capture user history behavior, recipe content, and relational information through several neural network modules, including type-specific transformation, node-level attention, and relation-level attention. We further introduce a ranking-based objective function to optimize the model. Thorough experiments demonstrate that HGAT outperforms numerous baseline methods.

Get full-text (via PubEx)

Vehicle Trajectory Prediction Using Hierarchical Graph Neural Network for Considering Interaction among Multimodal Maneuvers

Sensors ◽

10.3390/s21165354 ◽

2021 ◽

Vol 21 (16) ◽

pp. 5354

Author(s):

Eunsan Jo ◽

Myoungho Sunwoo ◽

Minchul Lee

Keyword(s):

Neural Network ◽

Autonomous Vehicles ◽

Prediction Performance ◽

Data Driven ◽

Graph Structure ◽

Trajectory Prediction ◽

Hierarchical Graph ◽

Vehicle Trajectory ◽

Using Data ◽

Vehicle Trajectory Prediction

Predicting the trajectories of surrounding vehicles by considering their interactions is an essential ability for the functioning of autonomous vehicles. The subsequent movement of a vehicle is decided based on the multiple maneuvers of surrounding vehicles. Therefore, to predict the trajectories of surrounding vehicles, interactions among multiple maneuvers should be considered. Recent research has taken into account interactions that are difficult to express mathematically using data-driven deep learning methods. However, previous studies have only considered the interactions among observed trajectories due to subsequent maneuvers that are unobservable and numerous maneuver combinations. Thus, to consider the interaction among multiple maneuvers, this paper proposes a hierarchical graph neural network. The proposed hierarchical model approximately predicts the multiple maneuvers of vehicles and considers the interaction among the maneuvers by representing their relationships in a graph structure. The proposed method was evaluated using a publicly available dataset and a real driving dataset. Compared with previous methods, the results of the proposed method exhibited better prediction performance in highly interactive situations.

Get full-text (via PubEx)

Hierarchical Graph Attention based Multi-view Convolutional Neural Network for 3D Object Recognition

IEEE Access ◽

10.1109/access.2021.3059853 ◽

2021 ◽

pp. 1-1

Author(s):

Hui Zeng ◽

Tianmeng Zhao ◽

Ruting Cheng ◽

Fuzhou Wang ◽

Jiwei Liu

Keyword(s):

Neural Network ◽

Object Recognition ◽

Convolutional Neural Network ◽

3D Object Recognition ◽

3D Object ◽

Hierarchical Graph

Get full-text (via PubEx)

Co-Saliency Detection Via Unified Hierarchical Graph Neural Network With Geometric Attention

10.1109/icip42928.2021.9506378 ◽

2021 ◽

Author(s):

Jiaqing Qiao ◽

Shaowei Sun ◽

Mingzhu Xu ◽

Yongqiang Li ◽

Bing Liu

Keyword(s):

Neural Network ◽

Saliency Detection ◽

Hierarchical Graph

Get full-text (via PubEx)