{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T10:34:21Z","timestamp":1773916461993,"version":"3.50.1"},"reference-count":43,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T00:00:00Z","timestamp":1773705600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100007825","name":"National Forestry and Grassland Administration","doi-asserted-by":"publisher","award":["CGF2024001"],"award-info":[{"award-number":["CGF2024001"]}],"id":[{"id":"10.13039\/501100007825","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["32470541"],"award-info":[{"award-number":["32470541"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U2571211"],"award-info":[{"award-number":["U2571211"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["32270551"],"award-info":[{"award-number":["32270551"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U21A20193"],"award-info":[{"award-number":["U21A20193"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"The program of China Scholarship Council","award":["202306040162"],"award-info":[{"award-number":["202306040162"]}]},{"DOI":"10.13039\/501100007825","name":"National Forestry and Grassland Administration","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100007825","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Animals"],"abstract":"<jats:p>As global demands for nature reserve management intensify, intelligent monitoring has become a pivotal trend. Integrating artificial intelligence with infrared camera traps enables automated analysis of endangered species behavior, providing timely insights for conservation. However, complex habitats often degrade the performance of existing detection technologies. Focusing on the giant panda\u2014a flagship conservation species\u2014we constructed a novel dataset from long-term field monitoring videos and developed an improved PandaSlowFast network. Our model employs channel attention to enhance temporal features, uses small-kernel depth-wise convolutions and dilated convolutions to expand receptive fields for spatial feature extraction, and introduces the Adaptive SwisH activation function to improve adaptability and training stability. The results show that PandaSlowFast achieves 85.38% mean average precision (mAP), outperforming existing methods. An FP16-quantized version maintains comparable accuracy (85.16% mAP) while running at 3.2 frames per second on a Raspberry Pi 4, demonstrating practical deployability for on-site monitoring. This work provides technical support for intelligent panda behavior analysis and offers a transferable methodology for monitoring other rare species, contributing to biodiversity conservation.<\/jats:p>","DOI":"10.3390\/ani16060943","type":"journal-article","created":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T16:20:14Z","timestamp":1773764414000},"page":"943","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Wildlife Monitoring: An Advanced AI Approach for Accurate Giant Panda Behavior Detection and Conservation Insights"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0848-0892","authenticated-orcid":false,"given":"Jin","family":"Hou","sequence":"first","affiliation":[{"name":"Key Laboratory of Southwest China Wildlife Resources Conservation (Ministry of Education), China West Normal University, Nanchong 637002, China"},{"name":"College of Life Sciences, Beijing Normal University, Beijing 100875, China"},{"name":"Nicholas School of Environment, Duke University, Durham, NC 27705, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chaoyu","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Northwest A&F University, Yangling 712100, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dan","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Northwest A&F University, Yangling 712100, China"},{"name":"M3-BIORES-Measure, Model & Manage Bioresponses, KU Leuven, Kasteelpark Arenberg 30, B-3001 Leuven, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7530-5672","authenticated-orcid":false,"given":"Vanessa","family":"Hull","sequence":"additional","affiliation":[{"name":"Department of Wildlife Ecology and Conservation, University of Florida, Gainesville, FL 32611, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4923-0207","authenticated-orcid":false,"given":"Yutong","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Southwest China Wildlife Resources Conservation (Ministry of Education), China West Normal University, Nanchong 637002, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinyi","family":"Zhao","sequence":"additional","affiliation":[{"name":"Key Laboratory of Southwest China Wildlife Resources Conservation (Ministry of Education), China West Normal University, Nanchong 637002, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingchun","family":"Tan","sequence":"additional","affiliation":[{"name":"Wolong National Nature Reserve, Wenchuan 623006, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaogang","family":"Shi","sequence":"additional","affiliation":[{"name":"Wolong National Nature Reserve, Wenchuan 623006, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuehong","family":"Cheng","sequence":"additional","affiliation":[{"name":"Wolong National Nature Reserve, Wenchuan 623006, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuo","family":"Tang","sequence":"additional","affiliation":[{"name":"Wolong National Nature Reserve, Wenchuan 623006, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Desheng","family":"Li","sequence":"additional","affiliation":[{"name":"China Conservation and Research Centre for the Giant Panda, Key Laboratory of State Forestry and Grassland Administration on the Giant Panda, Chengdu 610057, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7751-0936","authenticated-orcid":false,"given":"Jifeng","family":"Ning","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Northwest A&F University, Yangling 712100, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jindong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Southwest China Wildlife Resources Conservation (Ministry of Education), China West Normal University, Nanchong 637002, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,17]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"744","DOI":"10.1111\/cobi.12654","article-title":"A systematic survey of the integration of animal behavior into conservation","volume":"30","author":"Blumstein","year":"2016","journal-title":"Conserv. Biol."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"665","DOI":"10.1093\/beheco\/aru183","article-title":"Behavioral responses to changing environments","volume":"26","author":"Wong","year":"2015","journal-title":"Behav. Ecol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"482","DOI":"10.1038\/nature09210","article-title":"Coupled dynamics of body mass and population growth in response to environmental change","volume":"466","author":"Ozgul","year":"2010","journal-title":"Nature"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1002\/rse2.48","article-title":"A review of camera trapping for conservation behavior research","volume":"3","author":"Caravaggi","year":"2017","journal-title":"Remote Sens. Ecol. Conserv."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1038","DOI":"10.1093\/biosci\/biab073","article-title":"A comprehensive overview of technologies for species and habitat monitoring and conservation","volume":"71","author":"Magrath","year":"2021","journal-title":"BioScience"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"792","DOI":"10.1038\/s41467-022-27980-y","article-title":"Perspectives in machine learning for wildlife conservation","volume":"13","author":"Tuia","year":"2022","journal-title":"Nat. Commun."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Chen, S., Sun, P., Xie, E., Ge, C., Wu, J., Ma, L., Shen, J., and Luo, P. (2021, January 10\u201317). Watch Only Once: An End-to-End Video Action Detection Framework. Proceedings of the IEEE International Conference on Computer Vision, Montreal, QC, Canada.","DOI":"10.1109\/ICCV48922.2021.00807"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C. (2020, January 13\u201319). X3D: Expanding architectures for efficient video recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"8137","DOI":"10.1038\/s41598-019-44565-w","article-title":"Insights and approaches using deep learning to classify wildlife","volume":"9","author":"Miao","year":"2019","journal-title":"Sci. Rep."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"108414","DOI":"10.1016\/j.biocon.2020.108414","article-title":"Identification of animal individuals using deep learning: A case study of giant panda","volume":"242","author":"Hou","year":"2020","journal-title":"Biol. Conserv."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"2350066","DOI":"10.1142\/S0219691323500662","article-title":"A Survey on Deep Learning-based Spatio-temporal Action Detection","volume":"22","author":"Wang","year":"2024","journal-title":"Int. J. Wavelets Multiresolut. Inf. Process."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Wang, P., Wu, Q., and Shen, C. (2023). A Survey on Deep Learning-based Spatio-temporal Action Detection. arXiv.","DOI":"10.1142\/S0219691323500662"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1497","DOI":"10.1111\/cobi.12582","article-title":"Progress in the ecology and conservation of giant pandas","volume":"29","author":"Wei","year":"2015","journal-title":"Conserv. Biol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"4480","DOI":"10.1111\/gcb.16805","article-title":"Giant pandas are losing their edge: Population trend and distribution dynamic drivers of the giant panda","volume":"29","author":"Li","year":"2023","journal-title":"Global Change Biol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/j.biocon.2017.02.014","article-title":"Divergent responses of sympatric species to livestock encroachment at fine spatiotemporal scales","volume":"209","author":"Zhang","year":"2017","journal-title":"Biol. Conserv."},{"key":"ref_16","unstructured":"Guo, H.R. (2019). Research and Application of Giant Panda Action Recognition. [Doctoral Dissertation, University of Electronic Science and Technology of China]. (In Chinese)."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"102797","DOI":"10.1016\/j.ecoinf.2024.102797","article-title":"A joint time and spatial attention-based transformer approach for recognizing the behaviors of wild giant pandas","volume":"83","author":"Liu","year":"2024","journal-title":"Ecol. Inform."},{"key":"ref_18","unstructured":"Wei, X.Y. (2022). Improved Slow-Fast Network for Panda Action Recognition. [Doctoral Dissertation, University of Electronic Science and Technology of China]. (In Chinese)."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Sun, C., Shrivastava, A., Vondrick, C., Murphy, K., Sukthankar, R., and Schmid, C. (2018, January 8\u201314). Actor-centric relation network. Proceedings of the European Conference on Computer Vision, Munich, Germany.","DOI":"10.1007\/978-3-030-01252-6_20"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Wu, C.Y., Feichtenhofer, C., Fan, H., He, K., Krahenbuhl, P., and Girshick, R. (2019, January 15\u201320). Long-term feature banks for detailed video understanding. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00037"},{"key":"ref_21","first-page":"e01431","article-title":"Scent communication behavior by giant pandas","volume":"25","author":"Hou","year":"2021","journal-title":"Glob. Ecol. Conserv."},{"key":"ref_22","unstructured":"Sichuan Forestry Department (2015). The Fourth Survey Report on Giant Panda of Sichuan, Sichuan Science and Technology Press. (In Chinese)."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"892","DOI":"10.26599\/TST.2024.9010079","article-title":"Long-short memory bank for long-tailed video recognition","volume":"31","author":"Fu","year":"2026","journal-title":"Tsinghua Sci. Technol."},{"key":"ref_24","unstructured":"Zhang, H.M., Wang, P.Y., Zhang, G.Q., Li, D.S., Wei, R.P., Tang, C.X., Zhou, X.P., Huang, Y., and Chen, L.Q. (2003). Study on Reproduction of Giant Panda, China Forestry Press. (In Chinese)."},{"key":"ref_25","unstructured":"Zhou, X.P., Wang, P.Y., Zhang, H.M., Wei, R.P., Zhang, G.Q., Li, D.S., Huang, Y., and Swaisgood, R. (2005). Behavior Studies and Its Methods of Captive Giant Pandas, Sichuan Science and Technology Press. (In Chinese)."},{"key":"ref_26","first-page":"446","article-title":"Behavior coding and ethogram of the free-ranging giant pandas (Ailuropoda melanoleuca)","volume":"40","author":"Hou","year":"2020","journal-title":"Acta Theriol. Sin."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"4592","DOI":"10.1109\/TCSVT.2024.3514820","article-title":"Toward long video understanding via fine-detailed video story generation","volume":"35","author":"You","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_28","unstructured":"Zaremba, W., Sutskever, I., and Vinyals, O. (2014). Recurrent Neural Network Regularization. arXiv."},{"key":"ref_29","unstructured":"Finn, C., Goodfellow, I., and Levine, S. (2016, January 5\u201310). Unsupervised learning for physical interaction through video prediction. Proceedings of the 30th Conference on Neural Information Processing Systems, Barcelona, Spain."},{"key":"ref_30","unstructured":"Locatello, F., Bauer, S., Lucic, M., Raetsch, G., Gelly, S., Scholkopf, B., and Bachem, O. (2019, January 9\u201315). Challenging common assumptions in the unsupervised learning of disentangled representations. Proceedings of the International Conference on Machine Learning, Long Beach, CA, USA."},{"key":"ref_31","unstructured":"Castrejon, L., Ballas, N., and Courville, A. (November, January 27). Improved conditional VRNNs for video prediction. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Republic of Korea."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Chen, L., Tong, Z., Song, Y., Wu, G., and Wang, L. (2023, January 2\u20133). Efficient Video Action Detection with Token Dropout and Context Refinement. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Paris, France.","DOI":"10.1109\/ICCV51070.2023.00953"},{"key":"ref_33","unstructured":"Kyungsu, L., Jaeseung, Y., Haeyun, L., and Jae, Y.H. (December, January 28). Stochastic Adaptive Activation Function. Proceedings of the Advances in Neural Information Processing Systems, New Orleans, LA, USA."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1016\/j.matcom.2015.11.005","article-title":"On the approximation of the step function by some sigmoid functions","volume":"133","author":"Iliev","year":"2017","journal-title":"Math. Comput. Simulat."},{"key":"ref_35","unstructured":"Liu, X., Li, W., Song, Y., and Wang, L. (2024). Coarse-to-Fine Hypergraph Network for Spatiotemporal Action Detection. arXiv."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"1168","DOI":"10.1109\/TCSVT.2022.3207174","article-title":"Consistent intra-video contrastive learning with asynchronous long-term memory bank","volume":"33","author":"Chen","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_37","unstructured":"Tong, Z., Song, Y., Wang, J., and Wang, L. (December,, January 28). VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training. Proceedings of the Advances in Neural Information Processing Systems, New Orleans, LA, USA."},{"key":"ref_38","first-page":"490","article-title":"Improved YOLOv5s-Based Pose Recognition of Giant Pandas","volume":"42","author":"Yang","year":"2023","journal-title":"Sichuan J. Zool."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"110051","DOI":"10.1016\/j.isci.2024.110051","article-title":"Characterizing the metabolome and microbiome at giant panda scent marking sites during the mating season","volume":"27","author":"Jin","year":"2024","journal-title":"iScience"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"786","DOI":"10.1111\/cobi.13513","article-title":"Human\u2013wildlife coexistence in a changing world","volume":"34","author":"Kiffner","year":"2020","journal-title":"Conserv. Biol."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"23326","DOI":"10.17520\/biods.2023326","article-title":"Construction of Sino BON mammal diversity monitoring network (Sino BON-Mammal): A 10-year review and future outlook","volume":"31","author":"Xiao","year":"2023","journal-title":"Biodiv. Sci."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. U-Net: Convolutional networks for biomedical image segmentation. Medical Image Computing and Computer-Assisted Intervention, Munich, Germany, 2015, Springer International Publishing.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_43","unstructured":"Howard, A., Sandler, M., Chu, G., Chen, L.C., Chen, B., Tan, M., Wang, W., Zhu, Y., Pang, R., and Vasudevan, V. (November, January 27). Searching for MobileNetV3. Proceedings of the International Conference on Computer Vision, Seoul, Republic of Korea."}],"container-title":["Animals"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2076-2615\/16\/6\/943\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T05:17:03Z","timestamp":1773897423000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2076-2615\/16\/6\/943"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,17]]},"references-count":43,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["ani16060943"],"URL":"https:\/\/doi.org\/10.3390\/ani16060943","relation":{},"ISSN":["2076-2615"],"issn-type":[{"value":"2076-2615","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,17]]}}}