J
Jie Nie
Researcher at Ocean University of China
Publications - 9
Citations - 217
Jie Nie is an academic researcher from Ocean University of China. The author has contributed to research in topics: Feature extraction & Artificial neural network. The author has an hindex of 5, co-authored 9 publications receiving 80 citations.
Papers
More filters
Journal ArticleDOI
Multi-Level Policy and Reward-Based Deep Reinforcement Learning Framework for Image Captioning
TL;DR: A novel multi-level policy and reward RL framework for image captioning that can be easily integrated with RNN-based captioning models, language metrics, or visual-semantic functions for optimization and achieves competitive performances on a variety of evaluation metrics.
Journal ArticleDOI
Multi-View Saliency Guided Deep Neural Network for 3-D Object Retrieval and Classification
TL;DR: The proposed MVSG-DNN can discover the discriminative structure of multi-view sequence without constraints of specific camera settings and can support flexible 3D object retrieval and classification for real applications by avoiding the required camera settings.
Journal ArticleDOI
M-GCN: Multi-Branch Graph Convolution Network for 2D Image-based on 3D Model Retrieval
TL;DR: A novel multi-branch graph convolution network (M-GCN) is proposed to address the 2D image based 3D model retrieval problem and demonstrates the superiority of the proposed method over the state-of-the-art methods.
Journal ArticleDOI
C-GCN: Correlation Based Graph Convolutional Network for Audio-Video Emotion Recognition
TL;DR: This paper proposes a novel correlation-based graph convolutional network (C-GCN) for AER, which can comprehensively consider the correlation of the intra-class and inter-class videos for feature learning and information fusion and introduces the graph model to represent the correlation among the videos.
Journal ArticleDOI
HGAN: Holistic Generative Adversarial Networks for Two-dimensional Image-based Three-dimensional Object Retrieval
TL;DR: A novel Holistic Generative Adversarial Network (HGAN) is proposed to solve the cross-domain feature representation problem and make the feature space of virtual characteristic view more inclined to thefeature space of the real picture.