With declining populations in the wild, captive rescue and breeding have become one of the most important ways to protect pangolins from extinction. At present, the success rate of artificial breeding is low, due to the insufficient understanding of the breeding behavior characteristics of pangolins. The automatic recognition method based on machine vision not only monitors for 24 h but also reduces the stress response of pangolins. This paper aimed to establish a temporal relation and attention mechanism network (Pangolin breeding attention and transfer network, PBATn) to monitor and recognize pangolin behaviors, including breeding and daily behavior. There were 11,476 videos including breeding behavior and daily behavior that were divided into training, validation, and test sets. For the training set and validation set, the PBATn network model had an accuracy of 98.95% and 96.11%, and a loss function value of 0.1531 and 0.1852. The model is suitable for a 2.40 m × 2.20 m (length × width) pangolin cage area, with a nest box measuring 40 cm × 30 cm × 30 cm (length × width × height) positioned either on the left or right side inside the cage. A spherical night-vision monitoring camera was installed on the cage wall at a height of 2.50 m above the ground. For the test set, the mean Average Precision (mAP), average accuracy, average recall, average specificity, and average F1 score were found to be higher than SlowFast, X3D, TANet, TSN, etc., with values of 97.50%, 99.17%, 97.55%, 99.53%, and 97.48%, respectively. The recognition accuracies of PBATn were 94.00% and 98.50% for the chasing and mounting breeding behaviors, respectively. The results showed that PBATn outperformed the baseline methods in all aspects. This study shows that the deep learning system can accurately observe pangolin breeding behavior and it will be useful for analyzing the behavior of these animals.

Global warming is deeply influencing various ecological processes, especially regarding the phenological synchronization pattern between species, but more cases around the world are needed to reveal it. We report how the forest leaf phenology and ungulate molting respond differently to climate change, and investigate whether it will result in a potential phenology mismatch. Here, we explored how climate change might alter phenological synchronization between forest leaf phenology and Siberian roe deer (Capreolus pygargus) molting in northeast China based on a camera-trapping dataset of seven consecutive years, analyzing forest leaf phenology in combination with records of Siberian roe deer molting over the same period by means of wavelet analysis. We found that the start of the growing season of forest leaf phenology was advanced, while the end of the growing season was delayed, so that the length of the growing season was prolonged. Meanwhile, the start and the end of the molting of Siberian roe deer were both advanced in spring, but in autumn, the start of molting was delayed while the end of molting was advanced. The results of wavelet analysis also suggested the time lag of synchronization fluctuated slightly from year to year between forest leaf phenology and Siberian roe deer molting, with a potential phenology mismatch in spring, indicating the effect of global warming on SRD to forest leaf phenology. Overall, our study provides new insight into the synchronization between forest leaf phenology and ungulate molting, and demonstrates feasible approaches to data collection and analysis using camera-trapping data to explore global warming issues.