The field of computer vision and image processing is rapidly evolving, with a focus on developing innovative solutions for complex tasks such as salient object detection, fine-grained visual classification, and image super-resolution. Recent research has explored the use of joint learning schemes, spatial decomposition, and graph-enhanced contextual and regional perception networks to improve performance and efficiency. Notably, the development of lightweight and scalable models has enabled the application of computer vision techniques to real-world problems, such as poaching hotspot identification and wildlife forensics. Furthermore, the integration of AI-driven pipelines and frequency-guided attention upsampling has shown promising results in image analysis and super-resolution tasks. Overall, the field is moving towards more effective and efficient solutions that can be applied to a wide range of applications. Noteworthy papers include: Beyond Frequency: Seeing Subtle Cues Through the Lens of Spatial Decomposition for Fine-Grained Visual Classification, which proposes a novel method for fine-grained visual classification. GAPNet: A Lightweight Framework for Image and Video Salient Object Detection via Granularity-Aware Paradigm, which presents a lightweight network for salient object detection. Fourier-Guided Attention Upsampling for Image Super-Resolution, which introduces a lightweight upsampling module for single image super-resolution.