Pengjiang Qian — accepted AI-conference papers

2024

Joint Pre-Encoding Representation and Structure Embedding for Efficient and Low-Resource Knowledge Graph Completion

Chenyu Qiu, Pengjiang Qian, Chuang Wang, Jian Yao, Li Liu, Fang Wei +1

EMNLP 2024main

Knowledge graph completion (KGC) aims to infer missing or incomplete parts in knowledge graph. The existing models are generally divided into structure-based and description-based models, among description-based models often require longer training and inference times as well as increased memory usa…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗

2023

Structural Reparameterization Lightweight Network for Video Action Recognition

Anlei Zhu, Yinghui Wang, Wei Li, Pengjiang Qian

ICASSP 2023accepted

3D convolution networks play an important role in extracting spatiotemporal features in video action recognition. However, it usually brings a large number of paramters, which results in deployment difficulty in edge devices with limited memory space. Although lightweight 3DCNNs can reduce the mode…

Cited by 0 Source ↗Scholar ↗