More complex encoder is not all you need

1 code implementation • 20 Sep 2023 • Weibin Yang, Longwei Xu, Pengwei Wang, Dehua Geng, Yusong Li, Mingyuan Xu, Zhiqi Dong

To address the gap in relevant research, we extend our focus beyond the encoder and introduce neU-Net (i. e., not complex encoder U-Net), which incorporates a novel Sub-pixel Convolution for upsampling to construct a powerful decoder.

Image Segmentation Medical Image Segmentation +2

History-Aware Hierarchical Transformer for Multi-session Open-domain Dialogue System

no code implementations • 2 Feb 2023 • Tong Zhang, Yong liu, Boyang Li, Zhiwei Zeng, Pengwei Wang, Yuan You, Chunyan Miao, Lizhen Cui

HAHT maintains a long-term memory of history conversations and utilizes history information to understand current conversation context and generate well-informed and context-relevant responses.

Latent Space is Feature Space: Regularization Term for GANs Training on Limited Dataset

1 code implementation • 28 Oct 2022 • Pengwei Wang

However, a large amount of data is required, or the model would prone to generate images with similar patterns (mode collapse) and bad quality.

Data Augmentation Image Generation

Bootstrap Latent Representations for Multi-modal Recommendation

2 code implementations • 13 Jul 2022 • Xin Zhou, HongYu Zhou, Yong liu, Zhiwei Zeng, Chunyan Miao, Pengwei Wang, Yuan You, Feijun Jiang

Besides the user-item interaction graph, existing state-of-the-art methods usually use auxiliary graphs (e. g., user-user or item-item relation graph) to augment the learned representations of users and/or items.

Speech2Slot: An End-to-End Knowledge-based Slot Filling from Speech

no code implementations • 10 May 2021 • Pengwei Wang, Xin Ye, Xiaohuan Zhou, Jinghui Xie, Hao Wang

In contrast to conventional pipeline Spoken Language Understanding (SLU) which consists of automatic speech recognition (ASR) and natural language understanding (NLU), end-to-end SLU infers the semantic meaning directly from speech and overcomes the error propagation caused by ASR.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +8

WearMask: Fast In-browser Face Mask Detection with Serverless Edge Computing for COVID-19

1 code implementation • 4 Jan 2021 • Zekun Wang, Pengwei Wang, Peter C. Louis, Lee E. Wheless, Yuankai Huo

The serverless edge-computing design minimizes the extra hardware costs (e. g., specific devices or cloud computing servers).

Blocking Cloud Computing +1

Understanding Semantics from Speech Through Pre-training

no code implementations • 24 Sep 2019 • Pengwei Wang, Liang-Chen Wei, Yong Cao, Jinghui Xie, Yuji Cao, Zaiqing Nie

End-to-end Spoken Language Understanding (SLU) is proposed to infer the semantic meaning directly from audio features without intermediate text representation.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +4

Logic Rules Powered Knowledge Graph Embedding

no code implementations • 9 Mar 2019 • Pengwei Wang, Dejing Dou, Fangzhao Wu, Nisansa de Silva, Lianwen Jin

And then, to put both triples and mined logic rules within the same semantic space, all triples in the knowledge graph are represented as first-order logic.

Knowledge Graph Embedding Link Prediction +1