Abstract In recent years, there has been a significant increase in research focused on Human Activity Analysis (HAA). This field has progressed from basic activity recognition tasks to addressing more challenging ones, such as predicting future human actions based on partially observed videos and even predicting actions before they happen. The evolution of HAA has been driven by recent advancements in attention-based models like Transformers, along with a wide range of applications from security surveillance to advanced monitoring systems, behaviour analysis, and more. A comprehensive review of HAA literature from 2017 to 2025, with a novel taxonomy emphasising activity recognition, prediction, and anticipation, is presented. We critically review and examine recognition methods from trimmed and untrimmed videos, context-aware and trajectory-based prediction, and short-term and long-term anticipation. Through a comprehensive analysis, we review and evaluate key aspects of this domain, including attention-based contextual comprehension, temporal dynamics modelling, and multi-model fusion methods. Furthermore, we critically examine and assess the public datasets utilised in driving this research forward, pinpointing limitations and primary challenges within this domain. Finally, the paper provides a summary of recent developments in HAA and suggests future directions, with the hope that it will serve as a valuable reference for researchers in the field.

Abstract Saliency prediction (SP) estimates human gaze fixation in scenes, guided by visual attention mechanisms. While deep learning approaches have made substantial progress in SP, many overlook the inherent scene information presented in images. Further exploration is needed to generalize SP models across broader scene types and investigate how SP models behave differently across scenes, thereby advancing our understanding of scene knowledge’s impact on SP performance and human visual attention. This study introduces a scene-specific SP framework that incorporates scene labels predicted by a transferred CLIP-based classifier with multi-layer perceptron enhancement, trained on the CAT2000 dataset comprising 20 scene types. The scene classifier achieves high accuracy (averaging 88%) for 20-scene classification, providing reliable labels for subsequent scene-specific SP. In the SP phase, we employ transfer learning with DINet, training separate SP models for each scene type and a general SP model trained on images from all 20 scene types for comparison. Results show that the scene-specific SP framework consistently outperforms the general model across most scenes, with average improvements of 0.36% in AUC, 6.07% in NSS, and 4.66% in CC. Higher NSS and CC gains indicate that the scene-specific models effectively capture more accurate saliency position and distribution information from each specific scene that aligns with human gaze patterns. Moreover, the proposed framework is model-agnostic, ensuring compatibility with various SP models. Our findings highlight the cognitive importance of incorporating prior scene knowledge for precise SP and deepen the understanding of visual attention mechanisms across diverse environments.

Abstract Mental illnesses affect almost 15% of the world’s population, with half of the cases emerging before age 14. Improved methods for predicting mental distress among adolescents, particularly in vulnerable populations, are needed. This study utilized traditional machine learning techniques to predict mental health status at age 17. We assessed the correlates of mental health outcomes in a sample of 632 adolescents with general mental distress (i.e., total difficulties score of 17 or higher) at age 11, who participated in the UK Millennium Cohort Study. Predictors measured at ages 11 and 14 were included in the analysis. Mental health status at age 17 was best predicted using a Balanced Random Forest model (AUC 0.75). Explainability techniques enabled the identification of several critical factors, such as school environment, emotional distress, sleep patterns, patience, and social network at ages 11 or 14, which were able to differentiate participants with poor or good mental health outcomes at age 17. Individuals experiencing persistent mental distress between the ages 11 and 17 were most likely to suffer from unhappiness and academic struggles. Our results point to potentially modifiable factors associated with the progression of mental distress in adolescents at high risk. These factors could pave the way for improved early intervention and preventive strategies for vulnerable young people during adolescence.

Abstract Breast cancer is the most lethal type of cancer among women, one of the causes can be due to the lack of professionals to evaluate the results of medical images in time (Sharafaddini et al. Multimed Tools Appl, 1–112 2024). This problem is even greater in developing countries. In recent years, diagnostic tools based on artificial intelligence techniques have been developed to improve diagnosis time and results. In this work, we present a system that analyzes histopathological images obtained from breast tissue biopsies to design a classification system that distinguishes between benign and malignant tissue. To demonstrate that the proposed work is robust, multiple alternatives and combinations are studied to obtain the best cases. Finally, we compare the proposed approach with previous works. Furthermore, the developed system integrates explainable artificial intelligence techniques to produce a report to the physician, including a heat map with the areas the system has determined to be essential for classification.