Shi wei Zou

Dr. Shi wei Zou

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
19 April 2025 in Remote Sensing
Verified
Journal Article
Open access
PDF file
Shi wei ZouShi wei Zou
Shi wei Zou
YWYingmei Wei
Yingmei Wei
YXYuxiang Xie
Yuxiang Xie
XLXidao LUAN
Xidao LUAN
Remote Sensing Image Change Captioning (RSICC) has emerged as a cross-disciplinary technology that automatically generates sentences describing the changes in bi-temporal remote sensing images. While demonstrating significant potential for urban planning, agricultural surveillance, and disaster management, current RSICC methods exhibit two fundamental limitations: (1) vulnerability to pseudo-changes induced by illumination fluctuations and seasonal transitions and (2) an overemphasis on spatial variations with insufficient modeling of temporal dependencies in multi-temporal contexts. To address these challenges, we present the Frequency–Spatial–Temporal Fusion Network (FST-Net), a novel framework that integrates frequency, spatial, and temporal information for RSICC. Specifically, our Frequency–Spatial Fusion module implements adaptive spectral decomposition to disentangle structural changes from high-frequency noise artifacts, effectively suppressing environmental interference. The Spatia–Temporal Modeling module is further developed to employ state-space guided sequential scanning to capture evolutionary patterns of geospatial changes across temporal dimensions. Additionally, a unified dual-task decoder architecture bridges pixel-level change detection with semantic-level change captioning, achieving joint optimization of localization precision and description accuracy. Experiments on the LEVIR-MCI dataset demonstrate that our FSTNet outperforms previous methods by 3.65% on BLEU-4 and 4.08% on CIDEr-D, establishing new performance standards for RSICC.

14 July 2025 in International Journal of Multimedia Information Retrieval
Verified
Journal Article
Closed access
PDF file
Shi wei ZouShi wei Zou
Shi wei Zou
YWYingmei Wei
Yingmei Wei
YXYuxiang Xie
Yuxiang Xie
MLMingrui Lao
Mingrui Lao
XLXidao LUAN
Xidao LUAN

10 February 2025 in Neural Networks
Verified
Journal Article
Closed access
JYJie Yan
Jie Yan
YXYuxiang Xie
Yuxiang Xie
Shi wei ZouShi wei Zou
Shi wei Zou
YWYingmei Wei
Yingmei Wei
XLXidao LUAN
Xidao LUAN

16 January 2026 in International Journal of Multimedia Information Retrieval
Verified
Journal Article
Closed access
PDF file
QLQianqi Lu
Qianqi Lu
YXYuxiang Xie
Yuxiang Xie
JZJing Zhang
Jing Zhang
Shi wei ZouShi wei Zou
Shi wei Zou
YCYan Chen
Yan Chen
XLXidao LUAN
Xidao LUAN

16 September 2025 in arXiv
Verified
Preprint
Open access
PDF file
QLQianqi Lu
Qianqi Lu
YXYuxiang Xie
Yuxiang Xie
JZJing Zhang
Jing Zhang
Shi wei ZouShi wei Zou
Shi wei Zou
YCYan Chen
Yan Chen
XLXidao LUAN
Xidao LUAN
Referring Image Segmentation (RIS) is a task that segments image regions based on language expressions, requiring fine-grained alignment between two modalities. However, existing methods often struggle with multimodal misalignment and language semantic loss, especially in complex scenes containing multiple visually similar objects, where uniquely described targets are frequently mislocalized or incompletely segmented. To tackle these challenges, this paper proposes TFANet, a Three-stage Image-Text Feature Alignment Network that systematically enhances multimodal alignment through a hierarchical framework comprising three stages: Knowledge Plus Stage (KPS), Knowledge Fusion Stage (KFS), and Knowledge Intensification Stage (KIS). In the first stage, we design the Multiscale Linear Cross-Attention Module (MLAM), which facilitates bidirectional semantic exchange between visual features and textual representations across multiple scales. This establishes rich and efficient alignment between image regions and different granularities of linguistic descriptions. Subsequently, the KFS further strengthens feature alignment through the Cross-modal Feature Scanning Module (CFSM), which applies multimodal selective scanning to capture long-range dependencies and construct a unified multimodal representation. This is essential for modeling long-range cross-modal dependencies and enhancing alignment accuracy in complex scenes. Finally, in the KIS, we propose the Word-level Linguistic Feature-guided Semantic Deepening Module (WFDM) to compensate for semantic degradation introduced in earlier stages.

8 September 2025 in arXiv
Verified
Preprint
Open access
PDF file
ZJZhang Jing
Zhang Jing
PNPu Nan
Pu Nan
XXXie Yu Xiang
Xie Yu Xiang
YGYanming Guo
Yanming Guo
LQLu Qianqi
Lu Qianqi
CYChen Yan
Chen Yan
Generalized Category Discovery (GCD) is an emerging and challenging open-world problem that has garnered increasing attention in recent years. Most existing GCD methods focus on discovering categories in static images. However, relying solely on static visual content is often insufficient to reliably discover novel categories. To bridge this gap, we extend the GCD problem to the video domain and introduce a new setting, termed Video-GCD. Thus, effectively integrating multi-perspective information across time is crucial for accurate Video-GCD. To tackle this challenge, we propose a novel Memory-guided Consistency-aware Contrastive Learning (MCCL) framework, which explicitly captures temporal-spatial cues and incorporates them into contrastive learning through a consistency-guided voting mechanism. MCCL consists of two core components: Consistency-Aware Contrastive Learning(CACL) and Memory-Guided Representation Enhancement (MGRE). CACL exploits multiperspective temporal features to estimate consistency scores between unlabeled instances, which are then used to weight the contrastive loss accordingly. MGRE introduces a dual-level memory buffer that maintains both feature-level and logit-level representations, providing global context to enhance intra-class compactness and inter-class separability. This in turn refines the consistency estimation in CACL, forming a mutually reinforcing feedback loop between representation learning and consistency modeling. To facilitate a comprehensive evaluation, we construct a new and challenging Video-GCD benchmark, which includes action recognition and bird classification video datasets. Extensive experiments demonstrate that our method significantly outperforms competitive GCD approaches adapted from image-based settings, highlighting the importance of temporal information for discovering novel categories in videos. The code will be publicly available.