Multiple object tracking (MOT) technology has made significant progress in terrestrial applications, but underwater tracking scenarios remain underexplored despite their importance to marine ecology and aquaculture. In this paper, we present Multiple Fish Tracking Dataset 2025 (MFT25), a comprehensive dataset specifically designed for underwater multiple fish tracking, featuring 15 diverse video sequences with 408,578 meticulously annotated bounding boxes across 48,066 frames. Our dataset captures various underwater environments, fish species, and challenging conditions including occlusions, similar appearances, and erratic motion patterns. Additionally, we introduce Scale-aware and Unscented Tracker (SU-T), a specialized tracking framework featuring an Unscented Kalman Filter (UKF) optimized for non-linear swimming patterns of fish and a novel Fish-Intersection-over-Union (FishIoU) matching that accounts for the unique morphological characteristics of aquatic species. Extensive experiments demonstrate that our SU-T baseline achieves state-of-the-art performance on MFT25, with 34.1 HOTA and 44.6 IDF1, while revealing fundamental differences between fish tracking and terrestrial object tracking scenarios.

Virtual Reality and Mixed Reality systems have revolutionized consumer electronics, driving innovations in the metaverse. However, traditional VR headsets lack brain activity integration for feedback and control. This work introduces the first 65nm SoC for in situ mind imagery-based brain machine interface, seamlessly integrated into VR/MR headsets, with reduced energy consumption and AI support. The digital core of the SoC achieves state-of-the-art energy consumption <1μJ/class for computation-intensive CNN operations thanks to a novel teacher-student low-power scheme, general instruction set architecture for general programming and system-level optimizations of the design. The demonstration video for the whole system is provided at https://youtu.be/WuGlcMSSQzY.

The 3D organization of the genome is critical for gene expression regulation, cellular identity, and disease progression. Traditional methods that analyze bulk genomic data often obscure cell-to-cell heterogeneity, limiting the resolution of intrinsic variability within complex biological systems. To overcome this, single-cell 3D genomics has emerged, revealing chromatin architecture at the individual cell level. Advanced experimental approaches enable genome-wide chromatin contact mapping, while computational frameworks reconstruct dynamic chromatin topologies from high-dimensional data. Building on these breakthroughs, recent advances in single-cell 3D genomics have led to transformative progress in epigenetics, linking 3D genome architecture with gene regulation, cellular identity, and disease phenotypes. This review focuses on the breakthroughs in single-cell 3D genomics, demonstrating how integrated experimental, computational, and mechanistic approaches decode chromatin architecture. These insights have deepened the understanding of genome function at the single-cell level and lay the foundation for future advances in precision medicine and topology-guided therapeutic strategies.

Public spectral library that can provide authentic and reliable spectral information has been widely used in various applications, especially in the spectral library based spectral super-resolution. In general, the joint of multisource spectral libraries from different organizations can provide more varied and richer spectral information, but the differences in collection conditions and equipment between multisource spectra may greatly affect their application effectiveness. To cope with this problem, an integration method of multisource spectral libraries via benchmark alignment for spectral super-resolution is proposed. In this method, a pairwise alignment model is designed first, to express the integration procedure of multisource spectral libraries. Second, a statistical intercluster consistency measurement-based benchmark selection strategy for the spectrum pairs crossing two or more spectral libraries is designed, to find out the most suitable spectrum for alignment. Then, a nonnegative background component-based alignment strategy is proposed, to achieve spectral library integration through common background components extracted from the selected benchmark clusters. And finally, a modified spectral super-resolution procedure base on the integrated spectral library is given, to evaluate its effectiveness indirectly. Experimental results with the related spectral super-resolution methods on different datasets demonstrate that, our proposed method can significantly improve the performance of spectral super-resolution in both spatial and spectral domains.

Three-dimensional (3D) polarized radiative transfer becomes increasingly important for remote sensing applications. In this study, we propose a 3D mesoscopic modeling for polarized radiative transfer in atmospheric systems based on the Lattice Boltzmann method (LBM). To accurately capture the complex geometries of 3D inhomogeneous atmospheres, the proposed LB model is constructed on unstructured grids. The accuracy of the proposed unstructured LB model is validated through comparison with benchmark solutions. Furthermore, this study employs the proposed unstructured LB model to investigate the influence of different infrared incident wavelengths and atmospheric characteristics on polarized radiative transfer. The results demonstrate that the unstructured LB model accurately captures the wavelength-dependent variations of the Stokes parameters in both forward and backward scattering processes, highlighting its exceptional capability in handling complex atmospheric structures and multiple optical components that influence polarized light. This model provides a 3D mesoscopic tool for remote sensing, particularly for interpreting polarized signals from inhomogeneous atmospheric systems.

Blind image quality assessment (BIQA) aims to predict perceptual quality without access to reference images. However, discerning both image content and complex distortions within a unified model poses key challenges. To address this, we propose a single-stage BIQA framework termed multi-scale dense description (MSDD). The key innovation is a dense quality description (DQD) module that matches tailored distortion portrayals to each spatial location using a learned aggregation. This forms fine-grained alignments between contents and distortions. The content and distortion fusion (CDF) module then fuses them via a improved squash function. Finally, the multi-scale quality prediction (MSQP) module recursively combines evidence across stages through cross-scale integration. Extensive experiments show that MSDD achieves state-of-the-art performance and robustness on diverse distortions and contents.

Emotional AI or Affective Computing has been projected to grow rapidly in the upcoming years. Despite many existing developments in the application space, there has been a lack of hardware-level exploitation of the user's emotions. In this paper, we propose a deep collaboration between user's affects and the hardware system management on resource-limited edge devices. Based on classification results from efficient affect classifiers on smartphone devices, novel real-time management schemes for memory, and video processing are proposed to improve the energy efficiency of mobile devices. Case studies on H.264 / AVC video playback and Android smartphone usages are provided showing significant power saving of up to 23% and reduction of memory loading of up to 17% using the proposed affect adaptive architecture and system management schemes.

The incorporation of artificial intelligence into the rapidly growing IoT devices demands a high level of built-in intelligence, e.g. machine learning capability at the device level. Affective computing offers a new degree of cognitive intelligence into edge processing IoT devices by inferring human emotion, stress levels for intelligent human assistance. This work explores the design space and runtime optimization opportunity for affective computing at the system-on-chip (SoC) level. A design optimization methodology for the neural network classifier and runtime power management schemes are proposed to achieve high energy efficiency on embedded low power devices. A test chip based on a 65nm CMOS process was used to demonstrate the proposed methodology on emotion and stress classification for affective computing. An average power saving of 45% is achieved with a peak power savings of 60% from the proposed emotion-driven adaptive power management scheme.