Yaqian Zhou

Yaqian Zhou

Auto-generated profile, based on publicly available information

Yaqian Zhou

College of Computer and Cyber Security, Hebei Normal University, Shijiazhuang, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
20 April 2022 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
YZYaqian Zhou
Yaqian Zhou
YLYun Li
Yun Li
HZHe-Yu Zhou
He-Yu Zhou
ZCZhiyong Cheng
Zhiyong Cheng
XLXuanya Li
Xuanya Li
ALAnan Liu
Anan Liu
Existing research on the 2D image-based 3D model retrieval task focuses on learning transferable representations directly to narrow the domain discrepancy. However, it is not easy to achieve in practice due to the significant variations across two domains. In addition, some methods design a domain discriminator to distinguish the feature arising from source or target domains for transferable feature representations learning, which will lead to an unexpected deterioration of the feature discriminability. To settle these problems, we propose jointly learning transferable and discriminative representations for 2D image-based 3D model retrieval. Specifically, we extract features from the 2D images and 3D models (described as multiple views) by CNN. Considering the difficulty of directly narrowing the discrepancy of two domains, we are prone to connect 2D image and 3D model domains to an intermediate domain, where the domain gap aims to be eliminated. However, the feature transferability does not denote well discriminability. Based on the batch spectral penalization (BSP) theory, the feature transferability is dominated by feature vectors with higher singular values, while the feature discriminability depends on more eigenvectors with lower singular values to convey rich discriminative structures. Therefore, we penalize the largest singular values so that the feature vectors with lower singular values are appropriately enhanced, thereby strengthening feature discriminability. A series of experiments on two challenging datasets, MI3DOR and MI3DOR-2, indicate that our method can significantly improve performance.

1 August 2021 in Journal of Visual Communication and Image Representation
Verified
Journal Article
Closed access
YZYaqian Zhou
Yaqian Zhou
YLYun Li
Yun Li
HZHe-Yu Zhou
He-Yu Zhou
WLWenhui Li
Wenhui Li

6 August 2023 in Information Fusion
Verified
Journal Article
Closed access
YZYaqian Zhou
Yaqian Zhou
HLHaochun Lu
Haochun Lu
THTong Hao
Tong Hao
XLXuanya Li
Xuanya Li
ALAn-An Liu
An-An Liu

8 May 2023 in Information Processing & Management
Verified
Journal Article
Closed access
YZYaqian Zhou
Yaqian Zhou
YLYu Liu
Yu Liu
JXJun Xiao
Jun Xiao
MLMin Liu
Min Liu
XLXuanya Li
Xuanya Li
ALAn-An Liu
An-An Liu

28 January 2026 in Information Processing & Management
Verified
Journal Article
Closed access
YZYaqian Zhou
Yaqian Zhou
ZFZhenghao Fang
Zhenghao Fang
ZGZhibin Gu
Zhibin Gu
SYSong Yang
Song Yang
YWYan Wang
Yan Wang

26 February 2026 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
YZYaqian Zhou
Yaqian Zhou
RGRuiqiang Guo
Ruiqiang Guo
DSDan Song
Dan Song
JLJiayu Li
Jiayu Li
ALAnan Liu
Anan Liu
2D-3D cross-modal retrieval (2D-3DCMR) aims at retrieving the most matching 3D models by leveraging 2D query images. However, the inherent modal discrepancy makes the 2D-3DCMR task still largely challenging. Besides, the scarcity of 3D labels in real-world applications severely hinders learning discriminative representations. To address these limitations, we present a prompt tuning guided dual distribution alignment (PTG-DDA) framework based on the CLIP model for the 2D-3DCMR task. Specifically, we design a learnable multi-view adaptive representation learning (MARL) module that adaptively integrates 3D features to merge complementary information and filter out redundant information across views, thereby improving the representation capability of 3D models. To mitigate the feature distribution shift between the 2D and 3D data, we design an attention-guided heterogeneous feature alignment (AHFA) module to guide the 2D and 3D inputs attend to feature banks by adopting the attention mechanism, thereby achieving heterogeneous feature alignment. Furthermore, to learn discriminative 3D features, we employ a multi-modal semantic prompt synergy (MSPS) module, which integrates class-related representations into learnable prompts to progressively learn the cross-modal synergy via a prompt synergy adapter, thereby achieving semantic feature alignment. Comprehensive experimental results on popular 2D-3DCMR benchmarks, i.e., MI3DOR and MI3DOR-2, demonstrate the superiority and effectiveness of PTG-DDA.