SZSihui Zhang

Sihui Zhang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Sihui Zhang has a total of 16 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • ‘Disengage AND Integrate’: Personalized Causal Network for Gaze Estimation

    by Yi Tian, Xiyun Wang, Sihui Zhang, Wanru Xu, Yi Jin, Yaping Huang

    Gaze estimation task aims to predict a 3D gaze direction or a 2D gaze point given a face or eye image. To improve generalization of gaze estimation models to unseen new users, existing methods either disentangle personalized information of all subjects from their gaze features, or integrate unrefined personalized information into blended embeddings. Their methodologies are not rigorous whose performance is still unsatisfactory. In this paper, we put forward a comprehensive perspective named ‘Disengage AND Integrate’ to deal with personalized information, which elaborates that for specified users, their irrelevant personalized information should be discarded while relevant one should be considered. Accordingly, a novel Personalized Causal Network (PCNet) for generalizable gaze estimation has been proposed. The PCNet adopts a two-branch framework, which consists of a subject-deconfounded appearance sub-network (SdeANet) and a prototypical personalization sub-network (ProPNet). The SdeANet aims to explore causalities among facial images, gazes, and personalized information and extract a subject-invariant appearance-aware feature of each image by means of causal intervention. The ProPNet aims to characterize customized personalization-aware features of arbitrary users with the help of a prototype-based subject identification task. Furthermore, our whole PCNet is optimized in a hybrid episodic training paradigm, which further improve its adaptability to new users. Experiments on three challenging datasets over within-domain and cross-domain gaze estimation tasks demonstrate the effectiveness of our method.


  • Open Access

    Uncertainty Inspired Early Autism Spectrum Disorder Screening via Contrastive Image-Viewing Paradigm

    by Ying Zhang, Yaping Huang, Jiansong Qi, Sihui Zhang, Mei Tian, Yi Tian, Fanchao Meng, Lin Guan, Tianyi Chang

    Eye-tracking technology is found effective in revealing the specific visual preference of Autism Spectrum Disorder (ASD) which can be characterized by high systemizing and low empathizing abilities. Early diagnosis is vital for ASD’s subsequent treatment. However, existing eye-tracking-based methods suffer from long diagnostic times and low diagnostic accuracy due to the lack of awareness of gaze preference derived from individual differences. Moreover, there is only one publicly available eye-tracking dataset that employs a simple image free-viewing paradigm to collect the gaze patterns of ASD and typically developed (TD) subjects with an average age of 8 years, thus can not effectively support the early diagnosis for preschool children. To tackle the difficulties, in this paper, we first propose an Uncertainty-inspired ASD Screening Network (UASN) that dynamically estimates the contribution of each stimulus viewed by different subjects, and secondly, we design a contrastive image-viewing paradigm and further collect eye movement data from preschool children to reveal the visual behaviors of ASD children accordingly. Specifically, in UASN, we estimate the uncertainty of each stimulus and use it for more efficient model training and a more simplified personalized diagnosis procedure. Besides, by synthesizing two images with the opposite semantic representations and recruiting ASD and TD subjects aged 2-6, we construct a new CI4ASD dataset, which offers a novel contrastive image-viewing paradigm for better diagnosis of ASD in children. Comprehensive experiments are conducted and results have evidenced the effectiveness of the proposed UASN and eye-tracking paradigm.


  • Open Access

    Visual Question Answering Driven Eye Tracking Paradigm for Identifying Children with Autism Spectrum Disorder

    by Jiansong Qi, Yaping Huang, Ying Zhang, Sihui Zhang, Mei Tian, Yi Tian, Fanchao Meng, Lin Guan, Tianyi Chang

    As a non-contact method, eye-tracking data can be used to diagnose people with Autism Spectrum Disorder (ASD) by comparing the differences of eye movements between ASD and healthy people. However, existing works mainly employ a simple free-viewing paradigm or visual search paradigm with restricted or unnatural stimuli to collect the gaze patterns of adults or children with an average age of 6-to-8 years, hindering the early diagnosis and intervention of preschool children with ASD. In this paper, we propose a novel method for identifying children with ASD in three unique features: First, we design a novel eye-tracking paradigm that records Visual Question Answering (VQA) driven gaze patterns in complex natural scenes as a powerful guide for differentiating children with ASD. Second, we contribute a carefully designed dataset, named VQA4ASD, for collecting VQA-driven eye-tracking data from 2-to-6-year-old ASD and healthy children. To the best of our knowledge, this is the first dataset focusing on the early diagnosis of preschool children, which could facilitate the community to understand and explore the visual behaviors of ASD children. Third, we further develop a VQA-guided cooperative ASD screening network (VQA-CASN), in which both task-agnostic and task-specific visual scanpaths are explored simultaneously for ASD screening. Extensive experiments demonstrate that the proposed VQA-CASN achieves competitive performance with the proposed VQA-driven eye-tracking paradigm. The code and dataset is available at: https://github.com/qijiansong/VQA4ASD.


  • Domain-Consistent and Uncertainty-Aware Network for Generalizable Gaze Estimation

    by Sihui Zhang, Yi Tian, Yilei Zhang, Mei Tian, Yaping Huang

    Unsupervised domain adaptive (UDA) gaze estimation aims to predict gaze directions of unlabeled target face or eye images given a set of annotated source images, which has been widely applied in practical applications. However, existing methods still perform poorly due to two major challenges. 1) There exists large personalized differences and style discrepancies between source and target samples, which leads the learned source model easily collapsing to biased results; 2) Data uncertainties inherent in reference samples will affect the generalization ability of their models. To tackle the above challenges, in this paper, we propose a novel Domain-Consistent and Uncertainty-Aware (DCUA) network for generalizable gaze estimation. Our DCUA network employs a two-phase framework where a primary training sub-network (PTNet) and a refined adaptation sub-network (RANet) are trained on the source and target domain, respectively. Firstly, to obtain robust and pure gaze-related features, we propose twain domain consistent constraints, that is, the intra-domain consistent constraint and the inter-domain consistent constraint. These two constraints could eliminate the impact of gaze-irrelevant factors by maintaining consistency between label and feature space. Secondly, to further improve the adaptability of our model, we propose dual uncertainty perception modules, which include an intrinsic uncertainty module and an extrinsic uncertainty module. These modules help DCUA network distinguish inferior reference samples and avoid overfitting to them. Experiments on four cross-domain gaze estimation tasks demonstrate the effectiveness of our method.