Shuai Wang

Shuai Wang

Auto-generated profile, based on publicly available information

Shuai Wang

University of Amsterdam, Amsterdam, Netherlands

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 October 2025
Verified
Conference Paper
Open access
SWShuai Wang
Shuai Wang
INIvona Najdenkoska
Ivona Najdenkoska
HZHongyi Zhu
Hongyi Zhu
SRStevan Rudinac
Stevan Rudinac
MKMonika Kackovic
Monika Kackovic
MWMarcel Worring
Marcel Worring


15 June 2026
Verified
Conference Paper
Open access
PRPiera Riccio
Piera Riccio
SKSelina Khan
Selina Khan
LSLudovica Schaerf
Ludovica Schaerf
SWShuai Wang
Shuai Wang
TLTiancheng Liu
Tiancheng Liu
NNNanne van Noord
Nanne van Noord

11 October 2022 in arXiv
Verified
Preprint
Open access
PDF file
MKMuhammad Khalifa
Muhammad Khalifa
YVYogarshi Vyas
Yogarshi Vyas
SWShuai Wang
Shuai Wang
GHGraham Horwood
Graham Horwood
SMSunil Mallya
Sunil Mallya
MBMiguel Ballesteros
Miguel Ballesteros
We investigate semi-structured document classification in a zero-shot setting. Classification of semi-structured documents is more challenging than that of standard unstructured documents, as positional, layout, and style information play a vital role in interpreting such documents. The standard classification setting where categories are fixed during both training and testing falls short in dynamic environments where new document categories could potentially emerge. We focus exclusively on the zero-shot setting where inference is done on new unseen classes. To address this task, we propose a matching-based approach that relies on a pairwise contrastive objective for both pretraining and fine-tuning. Our results show a significant boost in Macro F$_1$ from the proposed pretraining step in both supervised and unsupervised zero-shot settings.

4 June 2023
Verified
Conference Paper
Open access
ZZZhangzi Zhu
Zhangzi Zhu
SWShuai Wang
Shuai Wang
HQHong Qu
Hong Qu
In the dataset of image captioning, each image is aligned with several descriptions. Despite the fact that the quality of these descriptions varies, existing captioning models treat them equally in the training process. In this paper, we propose a new control signal of sentence quality, which is taken as an additional input to the captioning model. By integrating the control signal information, captioning models are aware of the quality level of the target sentences and handle them differently. Moreover, we propose a novel reinforcement training method specially designed for the control signal of sentence quality: Quality-oriented Self-Annotated Training (Q-SAT). Extensive experiments on MSCOCO dataset show that without extra information from ground truth captions, models controlled by the highest quality level outperform baseline models on accuracy-based evaluation metrics, which validates the effectiveness of our proposed methods.