5 Papers
Hao Pan is an academic researcher from University of Texas at Arlington. The author has contributed to research in topics: Computer science & Natural language processing. The author has an hindex of 2, co-authored 2 publications. Previous affiliations of Hao Pan include Beijing Institute of Petrochemical Technology.
Chat about Author
Papers
Multimodal high-order relational network for vision-and-language tasks
TL;DR: Zhang et al. as mentioned in this paper proposed a multimodal high-order relational network (MORN) to simultaneously capture the intra-modality highorder relations and the sophisticated correlations between visual and textual relations.
7
Semantic-enhanced discriminative embedding learning for cross-modal retrieval
TL;DR: A novel semantic-enhanced discrim inative embedding learning method is proposed to enhance the discriminative ability of the model, which mainly consists of three modules that enable the attention model pay more attention to the relevant parts and reduce the interferences of irrelevant parts by erasing non-attention parts.
1
Semantic-aware multi-branch interaction network for deep multimodal learning
TL;DR: The generalizability and effectiveness of the proposed Semantic-aware Multi-Branch Interaction (SeMBI) network is demonstrated by applying it to three deep multimodal learning tasks, including Visual Question Answering (VQA), Referring Expression Comprehension (REC) and Cross-Modal Retrieval (CMR).
Fast Preconditioning for Accelerated Multi-contrast MRI Reconstruction
Ruoyu Li,Yeqing Li,Ruogu Fang,Shaoting Zhang,Hao Pan,Hao Pan,Junzhou Huang +6 more
- 05 Oct 2015
TL;DR: This study proposes a novel algorithm to accelerate the MC-MRI reconstruction in the framework of compressed sensing as the minimization of the least square data fitting with joint total variation (JTV) regularization term.
An Effective Approach for Robust Lung Cancer Cell Detection
Hao Pan,Zheng Xu,Junzhou Huang +2 more
- 09 Oct 2015
TL;DR: This work proposed an automatic lung cancer cell detection method based on deep convolutional neural network that needs only the weakly annotated images to achieve the image patches as the training set and has achieved promising performance on the lung cancers cell detection in terms of accuracy and efficiency.