Haomei Jia

Dr. Haomei Jia

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
5 January 2025 in Expert Systems with Applications
Verified
Journal Article
Closed access
MZMinglu Zhao
Minglu Zhao
WWWenmin Wang
Wenmin Wang
RZRui Zhang
Rui Zhang
HJHaomei Jia
Haomei Jia
QCQi Chen
Qi Chen

1 January 2025
Verified
Conference Paper
Open access
PDF file
DYDezhi Ye
Dezhi Ye
HJHaomei Jia
Haomei Jia
JHJunwei Hu
Junwei Hu
TBTian Bowen
Tian Bowen
JLJie Liu
Jie Liu
WWWenmin Wang
Wenmin Wang
Dezhi Ye, Haomei Jia, Junwei Hu, Tian Bowen, Jie Liu, Haijin Liang, Jin Ma, Wenmin Wang. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: Industry Track). 2025.

22 August 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
QCQi Chen
Qi Chen
WWWenmin Wang
Wenmin Wang
WZWang Zhibing
Wang Zhibing
HJHaomei Jia
Haomei Jia
MZMinglu Zhao
Minglu Zhao
Medical image segmentation is crucial for disease diagnosis, as precise results aid clinicians in locating lesion regions. However, lesions often have blurred boundaries and complex shapes, challenging traditional methods in capturing clear edges and impacting accurate localization and complete excision. Small lesions are also critical but prone to detail loss during downsampling, reducing segmentation accuracy. To address these issues, we propose a novel adaptive scale thresholding network (AdSTNet) that acts as a post-processing lightweight network for enhancing sensitivity to lesion edges and cores through a dual-threshold adaptive mechanism. The dual-threshold adaptive mechanism is a key architectural component that includes a main threshold map for core localization and an edge threshold map for more precise boundary detection. AdSTNet is compatible with any segmentation network and introduces only a small computational and parameter cost. Additionally, Spatial Attention and Channel Attention (SACA), the Laplacian operator, and the Fusion Enhancement module are introduced to improve feature processing. SACA enhances spatial and channel attention for core localization; the Laplacian operator retains edge details without added complexity; and the Fusion Enhancement module adapts concatenation operation and Convolutional Gated Linear Unit (ConvGLU) to improve feature intensities to improve edge and small lesion segmentation. Experiments show that AdSTNet achieves notable performance gains on ISIC 2018, BUSI, and Kvasir-SEG datasets. Compared with the original U-Net, our method attains mIoU/mDice of 83.40%/90.24% on ISIC, 71.66%/80.32% on BUSI, and 73.08%/81.91% on Kvasir-SEG. Moreover, similar improvements are observed in the rest of the networks.

21 October 2024
Verified
Conference Paper
Open access
DYDezhi Ye
Dezhi Ye
HJHaomei Jia
Haomei Jia
BTBowen Tian
Bowen Tian
JLJie Liu
Jie Liu
HLHaijin Liang
Haijin Liang
WWWenmin Wang
Wenmin Wang
Chinese Spelling Correction is to detect errors in a statement and correct them. Researchers have recently begun to investigate the use of pre-train language models to perform this task. They replace tokens with similar characters based on a confusion set rather than mask tokens when pre-training. A significant limitation of this method is that pre-training with single tokens cannot effectively simulate natural errors, such as full spelling. Furthermore, the confusion set consists of single characters, which lacks the contextual relationship between characters. This leads to a lower quality of generated pseudo-labeled samples. To this end, we contribute a novel approach of constructing confusion corpus, which can automatically generate high-quality spelling errors. The construction of our confusion set is based on user behavior patterns, aiming to identify characters that are easily confused in similar contexts. Then we introduce a Span Confusion Pre-Train(SCPre) strategy for Chinese Spelling Correction. The span confusion strategy replaces characters, words, and phrases in the text according to a large confusion set. Upon the constructed corpus, different models are trained and evaluated for CSC with respect to real-world datasets. Quantitative experiments on datasets show that our approach empirically achieves unprecedented performance.

24 August 2026 in Journal of King Saud University Computer and Information Sciences
Verified
Journal Article
Open access
PDF file
HJHaomei Jia
Haomei Jia
WWWenmin Wang
Wenmin Wang
WHWenfeng Huang
Wenfeng Huang
QCQi Chen
Qi Chen
MZMinglu Zhao
Minglu Zhao
Multimodal Aspect-Based Sentiment Analysis (MABSA) aims to simultaneously extract aspects and predict their sentiment polarities from paired textual and visual content. Existing approaches typically formulate MABSA as either a classification or index generation task, which may limit the accuracy of aspect boundary localization, an essential component of end-to-end aspect-sentiment prediction. To address this issue, we propose TicCondDiffusion, a Tweet-Image-Caption conditioned diffusion model that reformulates MABSA as a denoising process over aspect boundary coordinates for aspect boundary localization and sentiment prediction, where the caption is an image-derived textual description used as auxiliary visual-semantic guidance. TicCondDiffusion consists of two main processes: a noising process and a conditioned denoising process. In the noising process, Gaussian noise is gradually added to ground-truth boundary coordinates over multiple timesteps to generate noisy boundary coordinates. In the denoising process, the denoising module, conditioned on Tweet-Image-Caption representations and timestep embeddings, recovers noisy boundary coordinates for boundary localization while simultaneously predicting the sentiment polarities of the corresponding aspects, with subsequent denoising steps providing further refinement. To effectively exploit multimodal information, TicCondDiffusion incorporates three specialized fusion modules: a Tweet-Image Fusion Module, a Tweet-Caption Fusion Module, and a Tweet Feature Fusion Module. Experimental results on Twitter-2015 and Twitter-2017 demonstrate that TicCondDiffusion achieves competitive performance compared with recent baseline approaches under the end-to-end setting. Experiments on the Political-Twitter dataset further show its adaptability to domains with different topical distributions. Additional analyses further validate the effectiveness and flexibility of the proposed framework. To the best of our knowledge, TicCondDiffusion is the first diffusion-based framework specifically designed for MABSA, offering a new direction for this task (The code is available on https://github.com/MEIMEIMEIMEIMEMEDA/TicCondDiffusion .).

28 April 2026 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
HJHaomei Jia
Haomei Jia
WHWenfeng Huang
Wenfeng Huang
QCQi Chen
Qi Chen
MZMinglu Zhao
Minglu Zhao
Existing Multimodal Aspect-Sentiment Pair Extraction (MASPE) methods primarily focus on aspect-sentiment pairs while only implicitly modeling aspect-object associations. However, they overlook explicit object-level prediction, which is crucial for accurate and interpretable sentiment analysis in realistic multimodal scenarios. To address this gap, we introduce the Multimodal Aspect-Object-Sentiment Triples Extraction (MAOSTE) task, which explicitly predicts aspect-object-sentiment triples while accommodating aspects without visual correspondence. We release the Twitter-MAOSTE and Twitter-MAOSTE-Political datasets, and propose the T5 Enhanced Aspect-Object-Sentiment Extractor (T5-AOSE), which augments the T5 framework by adding multimodal information and sentiment clues. Experiments show that T5-AOSE achieves strong performance on the challenging MAOSTE and MAOE tasks while maintaining competitive results on the traditional MASPE task, confirming its effectiveness and generalizability. The dataset and code are publicly available at Github