Search Results for author: Patrick Dong

Found 7 papers, 1 papers with code

SuperTML: Two-Dimensional Word Embedding and Transfer Learning Using ImageNet Pretrained CNN Models for the Classifications on Tabular Data

no code implementations28 May 2019 Baohua Sun, Lin Yang, Wenhan Zhang, Michael Lin, Patrick Dong, Charles Young and Jason Dong

The recent work of Super Characters method using two-dimensional word embedding achieved state-of-the-art results in text classification tasks, showcasing the promise of this new approach.

text-classification Text Classification +1

SuperCaptioning: Image Captioning Using Two-dimensional Word Embedding

no code implementations25 May 2019 Baohua Sun, Lin Yang, Michael Lin, Charles Young, Patrick Dong, Wenhan Zhang, Jason Dong

In this paper, we propose the SuperCaptioning method, which borrows the idea of two-dimensional word embedding from Super Characters method, and processes the information of language and vision together in one single CNN model.

General Classification Image Captioning +4

SuperChat: Dialogue Generation by Transfer Learning from Vision to Language using Two-dimensional Word Embedding and Pretrained ImageNet CNN Models

no code implementations7 May 2019 Baohua Sun, Lin Yang, Michael Lin, Charles Young, Jason Dong, Wenhan Zhang, Patrick Dong

The recent work of Super Characters method using two-dimensional word embedding achieved state-of-the-art results in text classification tasks, showcasing the promise of this new approach.

Dialogue Generation General Classification +3

Ultra Power-Efficient CNN Domain Specific Accelerator with 9.3TOPS/Watt for Mobile and Embedded Applications

no code implementations30 Apr 2018 Baohua Sun, Lin Yang, Patrick Dong, Wenhan Zhang, Jason Dong, Charles Young

Furthermore, in order to better support real-world deployment for various application scenarios, especially with low-end mobile and embedded platforms and MCUs (Microcontroller Units), we also designed algorithms to fully utilize the CNN-DSA accelerator efficiently by reducing the dependency on external accelerator computation resources, including implementation of Fully-Connected (FC) layers within the accelerator and compression of extracted features from the CNN-DSA accelerator.

Cannot find the paper you are looking for? You can Submit a new open access paper.