The transition from adolescence to college is a significant developmental stage marked by challenges such as high academic pressure, changes in living environments, and social support systems. These challenges can lead to increased rates of depression among college students. This study investigates the relationships between family functioning, emotional intelligence, loneliness, social support, and depressive symptoms in Chinese college students. A cross-sectional design was employed, with data collected via questionnaires from undergraduate students at Xi’an Jiaotong University. Variables such as family functioning, emotional intelligence, loneliness, social support, and depressive symptoms were assessed. Statistical analyses, including correlation and hierarchical regression, were conducted to explore these relationships. The study found a diverse distribution of depressive symptoms among students, with significant gender differences indicating higher depression rates in females. No significant differences were observed across academic disciplines, grades, or between only children and non-only children. Family functioning, emotional intelligence, and social support were negatively correlated with depressive symptoms, while loneliness was positively correlated. Hierarchical regression analysis confirmed that social support significantly moderated the relationship between family functioning and depressive symptoms. Mediation analysis showed that emotional intelligence and loneliness mediated this relationship. The findings highlight the complex interplay between family dynamics, emotional capabilities, social connectedness, and mental health. Enhancing family functioning, emotional intelligence, and social support can effectively reduce depressive symptoms among college students. These results underscore the need for holistic interventions that address multiple aspects of students’ social and emotional lives.

This review focuses on the prevalence of depression and its associated risk factors among Chinese undergraduates, particularly examining the impacts of the COVID-19 pandemic on their mental health. The aim is to deepen the understanding of depression's prevalence and risk factors within this group, providing a robust reference for future studies and interventions. A comprehensive search and review were conducted on 1,198 documents from CNKI, Web of Science, Scopus, and other relevant databases. The selection process involved deduplication, preliminary evaluation, and a thorough full-text review, culminating in 75 documents that adhered to rigorous analytical standards, including the detailed reporting of depression data, the use of standardized depression scale assessments, and focusing on ordinary Chinese undergraduates. The analysis identified 70 risk factors for depression, confirming that the prevalence of depression among these students is influenced by a complex interplay of sociodemographic, psychological, health status, and personal lifestyle factors. The review also highlights several methodological flaws in previous studies, such as simplified research methods and outdated references. The study underscores the need for future research to consider the impact of different cultural backgrounds on depression, to employ longitudinal studies to establish causal relationships, and to use theoretical frameworks to conduct more systematic and detailed analyses. These steps will enhance the understanding and development of effective interventions for improving the mental health of Chinese undergraduates in a post-pandemic context.

Multimodal multi-object tracking has emerged as a crucial task in autonomous driving, aiming to perceive and track dynamic objects through the integration of visual, auditory, and linguistic cues. However, this task faces two major challenges: insufficient multimodal fusion, particularly the loss of frequency-domain information during spatial-only processing, and weak temporal semantic consistency, which often leads to tracking drift across frames. To address these issues, previous studies have explored spatial–frequency fusion networks and contrastive learning frameworks that align heterogeneous features across modalities. While these methods have achieved notable progress, they still suffer from limited adaptability to complex multimodal interactions and unstable long-term dependencies. To overcome these limitations, we propose SynTrack, a synergistic multimodal tracking framework that unifies frequency-domain fusion and contrastive temporal learning. SynTrack introduces two key components: a Multi-scale Cross-modal Frequency Fusion Module (MCFM) to enhance cross-modal representation through dual-domain attention, and a Multimodal Contrastive Tracking Learning (MCTL) strategy to enforce temporal coherence and semantic alignment across modalities. Extensive experiments on newly curated multimodal and text-guided benchmarks demonstrate that SynTrack achieves superior tracking accuracy, stability, and generalization under diverse environmental conditions, validating its effectiveness and scalability for real-world autonomous driving scenarios.