Huaiwen Zhang

Huaiwen Zhang

Auto-generated profile, based on publicly available information

Huaiwen Zhang

Inner Mongolia University, Hohhot, China

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
12 March 2021 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
HZHuaiwen Zhang
Huaiwen Zhang
SQShengsheng Qian
Shengsheng Qian
QFQuan Fang
Quan Fang
CXChangsheng Xu
Changsheng Xu
With the rapid development of social media platforms and the increasing scale of the social media data, the rumor detection task has become vitally important since the authenticity of posts cannot be guaranteed. To date, Many approaches have been proposed to facilitate the rumor detection process by utilizing the multi-task learning mechanism, which aims to improve the performance of rumor detection task by leveraging the useful information in the stance detection task. However, most of the existing approaches suffer from three limitations: (1) only focus on the textual content and ignore the multi-modal information which is key component contained in social media data; (2) ignore the difference of feature space between the stance detection task and rumor detection task, resulting in the unsatisfactory usage of stance information; (3) largely neglect the semantic information hidden in the fine-grained stance labels. Therefore, in this paper, we design a Multi-modal Meta Multi-Task Learning (MM-MTL) framework for social media rumor detection. To make use of multiple modalities, we design a multi-modal post embedding layer which considers both textual and visual content. To overcome the feature-sharing problem of the stance detection task and rumor detection task, we propose a meta knowledge-sharing scheme to share some higher meta network-layers and capture the meta knowledge behind the multi-modal post. To better utilize the semantic information hidden in the fine-grained stance labels, we employ the attention mechanism to estimate the weight of each reply. Extensive experiments on two Twitter benchmark datasets demonstrate that our proposed method achieves state-of-the-art performance.

7 December 2020 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
HZHuaiwen Zhang
Huaiwen Zhang
SQShengsheng Qian
Shengsheng Qian
QFQuan Fang
Quan Fang
CXChangsheng Xu
Changsheng Xu
With the rapid development of social media and the increasing scale of social media data, the rumor detection on social media platforms has become vitally crucial. The key challenges for rumor detection on social media platforms are how to identify rumors deeply entangled with the specific content and how to detect rumors for the emerging social media events without labeled data. Unfortunately, most of the existing approaches can hardly handle these challenges since they tend to learn event-specific features and cannot transfer the learned features to newly emerged events. To tackle the above challenges, we propose a novel Multimodal Disentangled Domain Adaption (MDDA) method which can derive event-invariant features and thus benefit the detection of rumors on emerging social media events. The model consists of two components: the multimodal disentangled representation learning and the unsupervised domain adaptation. The multimodal disentangled representation learning is responsible for disentangling the multimedia posts into the content features and the rumor style features, and removing the content-specific features from post representation. The unsupervised domain adaptation aims to filter out the event-specific features and keep shared rumor style features among events. Based on the final event-invariant rumor style features, we train a robust social media rumor detector that can transfer knowledge from source events to the target events, which can perform well on the newly emerged events. Extensive experiments on two Twitter benchmark datasets demonstrate that our rumor detection model outperforms state-of-the-art methods.

23 January 2023 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
HZHuaiwen Zhang
Huaiwen Zhang
YYYang Yang
Yang Yang
FQFan Qi
Fan Qi
SQShengsheng Qian
Shengsheng Qian
CXChangsheng Xu
Changsheng Xu
Video-text retrieval is a fundamental task in managing the emerging massive amounts of video data. The main challenge focuses on learning a common representation space for videos and queries where the similarity measurement can reflect the semantic closeness. However, existing video-text retrieval models may suffer from the following noise in the common space learning procedure: First, the video-text correspondences in positive pairs may not be exact matches. The crowdsourcing annotation for existing datasets leads to inevitable tagging noise for non-expert annotators. Second, the learning of video-text representation is based on the negative samples randomly sampled. Instances that are semantically similar to the query may be incorrectly categorized as negative samples. To alleviate the adverse impact of these noisy pairs, we propose a novel robust video-text retrieval method that protects the model from noisy positive and negative pairs by identifying and calibrating noisy pairs with their uncertainty score. In particular, we propose a noisy pair identifier, which divides the training dataset into noisy and clean subsets based on the estimated uncertainty of each pair. Then, with the help of uncertainties, we calibrate the two types of noisy pairs with an adaptive margin triplet loss and a weighted triplet loss function, respectively. To verify the effectiveness of our methods, we conduct extensive experiments on three widely used datasets. Experimental results show that the proposed robust video-text retrieval methods successfully identify and calibrate the noisy pairs and improve retrieval performance.

5 February 2024 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
FQFan Qi
Fan Qi
HZHuaiwen Zhang
Huaiwen Zhang
XYXiaoshan Yang
Xiaoshan Yang
CXChangsheng Xu
Changsheng Xu
Multi-modal Emotion Recognition (MER) aims to identify various human emotions from heterogeneous modalities. With the development of emotional theories, there are more and more novel and fine-grained concepts to describe human emotional feelings. Real-world recognition systems often encounter unseen emotion labels. To address this challenge, we propose a versatile zero-shot MER framework to refine emotion label embeddings for capturing inter-label relationships and improving discrimination between labels. We integrate prior knowledge into a novel affective graph space that generates tailored label embeddings capturing inter-label relationships. To obtain multimodal representations, we disentangle the features of each modality into egocentric and altruistic components using adversarial learning. These components are then hierarchically fused using a hybrid co-attention mechanism. Furthermore, an emotion-guided decoder exploits label-modal dependencies to generate adaptive multimodal representations guided by emotion embeddings. We conduct extensive experiments with different multimodal combinations, including visual-acoustic and visual-textual inputs, on four datasets in both single-label and multi-label zero-shot settings. Results demonstrate the superiority of our proposed framework over state-of-the-art methods.

1 January 2025
Verified
Conference Paper
Open access
PDF file
SHShuguo Hu
Shuguo Hu
JHJun Hu
Jun Hu
HZHuaiwen Zhang
Huaiwen Zhang
Shuguo Hu, Jun Hu, Huaiwen Zhang. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

3 April 2025 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
HZHuaiwen Zhang
Huaiwen Zhang
TWTianci Wu
Tianci Wu
YWYinwei Wei
Yinwei Wei
Personalized text-to-image generation aims to synthesize images tailored to individual user preferences. Existing methods primarily generate customized content using a few reference images, which often struggle to mine user preferences from historical records, and thus fail to synthesize truly personalized content. In addition, it is difficult to directly incorporate the extracted feature of user preferences into the feature space of the generation model, since there exists a considerable gap between them. In this paper, we propose a novel multi-view personalized text-to-image generation method based on the diffusion model, named MVP-Diffusion, which learns instance- and user-level preferences from historical records and integrates them into the generation model. For instance-level user preference modeling, we employ a chain-of-thought prompting strategy to deduce preference keywords and integrate them into input prompts with the aid of a large language model. For user-level preference modeling, we construct a learnable embedding for each user to capture more comprehensive preferences by analyzing their historical records. An adaptive user preference fusion module is proposed to inject user preferences into the generation model via a set of learnable parameters. Experimental results demonstrate that the proposed method significantly enhances the personalization of the generated images compared to the other personalized text-to-image generation methods.