This study introduces a approach to cross-age facial recognition, highlighting the crucial role of extracting rich hybrid features and isolating identity characteristics within them. Our proposed method integrates a Feature Aggregation and Selection Module with a Non-linear Identity Feature Separation module. The process begins with the generation of hybrid features through an attention-driven fusion of basic and advanced semantic features. This is followed by the extraction of identity features via Non-linear decoupling, guided by multi-task training. These identity features are then applied to cross-age facial recognition tasks. The effectiveness and adaptability of our approach are demonstrated by its impressive performance on various datasets, including AgeDB-30, CALFW, CACD-VS, and LFW, achieving accuracy rates of 97.10%, 96.22%, 99.61%, and 99.71% respectively. This method represents a significant advancement in the field of facial recognition research, particularly in addressing the challenges of age variation.

This paper introduces a lightweight spectral channel feature transformation network, LDCFormer, designed to address the high computational complexity and excessive parameter count resulting from self-attention and spatial MLP (Multilayer Perceptron) in vision transformers when dealing with long sequences. Initially, the image information is transformed into the frequency domain using a two-dimensional discrete cosine transform (DCT), effectively capturing the image’s frequency domain features. Secondly, considering that different frequency areas represent various types of features, local feature information such as edges and textures are extracted in the high-frequency area, while the image’s global feature information is extracted in the low-frequency area, complemented by channel attention for feature cleansing. Finally, the integration and interaction of global feature information in the image are achieved by introducing the Transformer architecture. LDCFormer employs a zero-learning-parameter 2D LDCFormer operation to extract features directly from the frequency domain, significantly reducing the number of trainable parameters, and utilizes depth-separable LDConv MLP to further accelerate computational speed, achieving the lightweight and efficient characteristics of LDCFormer. Accuracies of 78.8%, 88.9% and 88.6% were attained on three typical datasets. The experimental results demonstrate that LDCFormer maintains high classification performance while reducing the parameter count, achieving a good balance between speed and accuracy.

The Moon-based Earth Radiation Observatory (MERO) has the potential to complement current Earth Radiation Budget (ERB) missions by providing higher temporal resolution data, especially for the Earth polar regions. Regarding the MERO mission design, quantifying its mixed-pixel-induced uncertainty is crucial, which occupies an important part in the MERO inherent systematic errors. However, current knowledge about this MERO mixed-pixel-induced uncertainty is still limited. In this study, we proposed a MERO 2-endmember-mixed-pixel error quantification method and explored such errors in the land-snow, land-waterbody and waterbody-snow mixing scenarios. Results indicate that the land-snow mixing leads to the biggest measurement errors, which are as large as 4.02% and 7.98 % for the Earth top of the atmosphere (TOA) outgoing solar-reflected shortwave radiation (OSR) and outgoing thermally-emitted longwave radiation (OLR) fluxes respectively. The waterbody-snow mixing caused the secondly largest measurement error with TOA OSR maximum of 3.01% and TOA OLR maximum of 7.08 %. The land-waterbody mixing results in the least measurement error with TOA OSR maximum of 0.79% and TOA OLR maximum of 0.41 %.