Engagement plays an essential role in the learning process. Recognition of learning engagement in the classroom helps us understand the student’s learning state and optimize the teaching and study processes. Traditional recognition methods such as self-report and teacher observation are time-consuming and obtrusive to satisfy the needs of large-scale classrooms. With the development of big data analysis and artificial intelligence, applying intelligent methods such as deep learning to recognize learning engagement has become the research hotspot in education. In this paper, based on non-invasive classroom videos, first, a multi-cues classroom learning engagement database was constructed. Then, we introduced the power IoU loss function to You Only Look Once version 5 (YOLOv5) to detect the students and obtained a precision of 95.4%. Finally, we designed a bimodal learning engagement recognition method based on ResNet50 and CoAtNet. Our proposed bimodal learning engagement method obtained an accuracy of 93.94% using the KNN classifier. The experimental results confirmed that the proposed method outperforms most state-of-the-art techniques.

Across taxa, females are routinely choosier than males in selecting mates. Several hypotheses have been advanced to explain genetic benefits behind female strategies. The inbreeding avoidance hypothesis suggests that females avoid mating with close relatives, thereby avoiding the matchup of deleterious recessive alleles. Outbreeding avoidance hypothesis suggests that females should not mate with too distantly related individuals so as to avoid the breakup of coadapted gene complexes. Although previous studies have suggested that selection should favor individuals that optimize the balance between inbreeding and outbreeding, detailed research is necessary to document the trade‐off between them and variability in mate choice across a gradient of inbreeding levels among populations. The good genes and the genetic compatibility hypotheses predict that females choose mates according to costly traits and genetic dissimilarity, respectively. Thus, to document inbreeding or outbreeding depressions and assess the contributions of mate choice based upon good genes versus genetic compatibility, we examined egg production, collected body length measurements and genotyped five microsatellite markers in six populations of Asiatic toad (Bufo gargarizans). Our results revealed that the incidence of inbreeding was higher than that expected under the assumption of random mating and relatedness between mated individuals increased when the average inbreeding level increased among populations. Our findings did not support the good genes or the genetic compatibility hypotheses. Although some other processes could have influences on mate choice of Asiatic toad and need to be tested, our results indicated that, in small and isolated toad populations, the limited availability and high cost of obtaining unrelated mates may promote outbreeding avoidance and adaptation to inbreeding to be the critical drives of female mate choice.