{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T07:16:36Z","timestamp":1788419796845,"version":"build-2803163510"},"reference-count":37,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T00:00:00Z","timestamp":1788393600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Vet. Sci."],"abstract":"<jats:p>Accurate recognition of pig behavior plays a critical role in enhancing animal welfare and management efficiency for precision livestock farming. Nevertheless, existing methods are commonly limited by rigid feature fusion strategies, insufficient preservation of spatial details, and weak interactions across hierarchical features, which severely compromise recognition performance in complex farm scenarios. To address these challenges, we present a novel deep learning architecture termed MMBs_TransNeXt for pig behavior recognition. This model establishes a unified, hierarchical and adaptive feature learning framework. It employs Multi-stage Adaptive Feature Fusion (MAFF) to adaptively integrate semantic and fine-grained information across different network stages. It enhances the representation of subtle behavioral traits through Multi-scale Detail Fusion Convolution (MDFC). Meanwhile, it facilitates effective information communication and interaction among multi-level features via Bidirectional Modulation Feature Fusion (BMFF). Extensive experiments on a real-world pig behavior dataset validate that MMBs_TransNeXt attains state-of-the-art performance with 95.77% accuracy, substantially outperforming representative CNN and Transformer baselines. This work offers a robust technical foundation for intelligent visual monitoring and welfare evaluation in modern precision pig farming systems.<\/jats:p>","DOI":"10.3389\/fvets.2026.1904986","type":"journal-article","created":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T06:43:56Z","timestamp":1788417836000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MMBs_TransNeXt: a hierarchical adaptive feature learning model for pig behavior recognition in precision livestock farming"],"prefix":"10.3389","volume":"13","author":[{"given":"Meng","family":"Han","sequence":"first","affiliation":[{"name":"School of Information Science and Engineering, Shanxi Agricultural University","place":["Jinzhong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wangli","family":"Hao","sequence":"additional","affiliation":[{"name":"Faculty of Software Technologies, Shanxi Agricultural University","place":["Jinzhong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Shu","sequence":"additional","affiliation":[{"name":"Faculty of Software Technologies, Shanxi Agricultural University","place":["Jinzhong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyuan","family":"Hu","sequence":"additional","affiliation":[{"name":"Faculty of Software Technologies, Shanxi Agricultural University","place":["Jinzhong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingqing","family":"Li","sequence":"additional","affiliation":[{"name":"Faculty of Software Technologies, Shanxi Agricultural University","place":["Jinzhong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fuzhong","family":"Li","sequence":"additional","affiliation":[{"name":"Faculty of Software Technologies, Shanxi Agricultural University","place":["Jinzhong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,3]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1639","DOI":"10.3390\/agriculture13081639","article-title":"Describing behavior sequences of fattening pigs using process mining on video data and automated pig behavior recognition","volume":"13","author":"Melfsen","year":"2023","journal-title":"Agriculture"},{"key":"B2","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1016\/j.inpa.2024.10.001","article-title":"Integrating Artificial Intelligence in dairy farm management biometric facial recognition for cows","volume":"12","author":"Mahato","year":"2025","journal-title":"Inf Process Agric"},{"key":"B3","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1016\/j.inpa.2022.04.001","article-title":"Deep learning based classification of sheep behaviour from accelerometer data with imbalance","volume":"10","author":"Turner","year":"2023","journal-title":"Inf Process Agric"},{"key":"B4","doi-asserted-by":"publisher","first-page":"1759542","DOI":"10.1155\/2022\/1759542","article-title":"Efficient detection method of pig-posture behavior based on multiple attention mechanism","volume":"2022","author":"Huang","year":"2022","journal-title":"Comput Intell Neurosci."},{"key":"B5","doi-asserted-by":"publisher","first-page":"2534","DOI":"10.1016\/j.jia.2024.08.014","article-title":"Promote computer vision applications in pig farming scenarios: high-quality dataset, fundamental models, and comparable performance","volume":"25","author":"Li","year":"2024","journal-title":"J Integrat Agric"},{"key":"B6","doi-asserted-by":"publisher","first-page":"3074","DOI":"10.3390\/ani13193074","article-title":"Detection of pig movement and aggression using deep learning approaches","volume":"13","author":"Wei","year":"2023","journal-title":"Animals"},{"key":"B7","doi-asserted-by":"publisher","first-page":"5092","DOI":"10.3390\/s23115092","article-title":"TSML: A new pig behavior recognition method based on two-stream mutual learning network","volume":"23","author":"Hao","year":"2023","journal-title":"Sensors."},{"key":"B8","doi-asserted-by":"publisher","first-page":"3018","DOI":"10.3390\/app15063018","article-title":"Sow and piglet behavior characterization using visual observation, sensor detection, and video recording","volume":"15","author":"Kim JH Ni","year":"2025","journal-title":"Appl Sci"},{"key":"B9","doi-asserted-by":"publisher","first-page":"105146","DOI":"10.1016\/j.applanim.2020.105146","article-title":"A review of video-based pig behavior recognition","volume":"233","author":"Yang","year":"2020","journal-title":"Appl Anim Behav Sci."},{"key":"B10","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1109\/GCCE.2017.8229435","article-title":"Automatic evaluation of cow's body-condition-score using 3D camera","volume-title":"Proceeding of IEEE 6th Global Conference on Consumer Electronics (GCCE 2017)","author":"Imamura","year":"2017"},{"key":"B11","doi-asserted-by":"publisher","first-page":"101300","DOI":"10.1016\/j.atech.2025.101300","article-title":"AI-powered visual E-monitoring system for cattle health and wealth","volume":"12","author":"Moe","year":"2025","journal-title":"Smart Agric Technol"},{"key":"B12","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1016\/j.inpa.2022.10.003","article-title":"novel low-cost visual ear tag based identification system for precision beef cattle livestock farming","volume":"11","author":"Pretto","year":"2024","journal-title":"Inf Process Agric"},{"key":"B13","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1016\/j.inpa.2023.11.002","article-title":"Recognition and statistical method of cows rumination and eating behaviors based on Tensorflowjs","volume":"11","author":"Zhang","year":"2024","journal-title":"Inf Process Agric"},{"key":"B14","doi-asserted-by":"publisher","first-page":"2028","DOI":"10.1016\/j.jia.2024.07.023","article-title":"Multi-scale keypoints detection and motion features extraction in dairy cows using ResNet101-ASPP network","volume":"25","author":"Wu","year":"2024","journal-title":"J Integrat Agric"},{"key":"B15","doi-asserted-by":"publisher","first-page":"2381","DOI":"10.3390\/s20082381","article-title":"spatiotemporal convolutional network for multi-behavior recognition of pigs","volume":"20","author":"Li","year":"2020","journal-title":"Sensors"},{"key":"B16","doi-asserted-by":"publisher","first-page":"3574","DOI":"10.1016\/j.jia.2024.03.071","article-title":"Enhancing the genomic prediction accuracy of swine agricultural economic traits using an expanded one-hot encoding in CNN models","volume":"24","author":"Wang","year":"2024","journal-title":"J Integrat Agric"},{"key":"B17","doi-asserted-by":"publisher","first-page":"108243","DOI":"10.1016\/j.engappai.2024.108243","article-title":"A hybrid attention-guided convnext-gru network for action recognition","volume":"133","author":"An","year":"2024","journal-title":"Eng Appl Artif Intell"},{"key":"B18","doi-asserted-by":"publisher","first-page":"104143","DOI":"10.1016\/j.biosystemseng.2025.104143","article-title":"Deep learning algorithms to identify individual finishing pigs using 3D data","volume":"255","author":"Paudel","year":"2025","journal-title":"Biosyst Eng"},{"key":"B19","doi-asserted-by":"publisher","first-page":"17036","DOI":"10.1038\/s41598-025-01898-z","article-title":"novel yolo lstm approach for enhanced human action recognition in video sequences","volume":"15","author":"Elnady","year":"2025","journal-title":"Sci Rep"},{"key":"B20","doi-asserted-by":"publisher","first-page":"1907","DOI":"10.3390\/agriculture12111907","article-title":"Automated behavior recognition and tracking of group-housed pigs with an improved DeepSORT method","volume":"12","author":"Tu","year":"2022","journal-title":"Agriculture"},{"key":"B21","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1016\/j.inpa.2023.03.004","article-title":"Pig face recognition based on improved YOLOv4 lightweight neural network","volume":"11","author":"Ma","year":"2024","journal-title":"Inf Process Agric"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1316","DOI":"10.3390\/ani14091316","article-title":"An integrated gather-and-distribute mechanism and attention-enhanced deformable convolution model for pig behavior recognition","volume":"14","author":"Mao","year":"2024","journal-title":"Animals"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv"},{"key":"B24","doi-asserted-by":"publisher","first-page":"10012","DOI":"10.1109\/ICCV48922.2021.00986","author":"Liu","year":"2021","journal-title":"Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows."},{"key":"B25","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1016\/j.aiia.2025.03.006","article-title":"Transformer-based audio-visual multimodal fusion for fine-grained recognition of individual sow nursing behaviour","volume":"15","author":"Yang","year":"2025","journal-title":"Artif Intellig Agric"},{"key":"B26","doi-asserted-by":"publisher","first-page":"1159","DOI":"10.3390\/ani15081159","article-title":"lightweight pig aggressive behavior recognition model by effective integration of spatio-temporal features","volume":"15","author":"Pu","year":"2025","journal-title":"Animals"},{"key":"B27","doi-asserted-by":"publisher","first-page":"17773","DOI":"10.1109\/CVPR52733.2024.01683","author":"Shi","year":"2024","journal-title":"TransNeXt: Robust Foveal Visual Perception for Vision Transformers."},{"key":"B28","doi-asserted-by":"publisher","first-page":"106296","DOI":"10.1016\/j.engappai.2023.106296","article-title":"Time series classification based on convolutional network with a gated linear units kernel","volume":"123","author":"Liu","year":"2023","journal-title":"Eng Appl Artif Intell."},{"key":"B29","doi-asserted-by":"publisher","first-page":"110327","DOI":"10.1016\/j.compag.2025.110327","article-title":"Recent advances in pig behavior detection based on information perception technology","volume":"235","author":"Xu","year":"2025","journal-title":"Comp Electron Agricult"},{"key":"B30","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1016\/j.applanim.2019.04.010","article-title":"Increasing the number of wooden beams from two to four increases the exploratory behaviour of finisher pigs","volume":"216","author":"Larsen","year":"2019","journal-title":"Appl Anim Behav Sci"},{"key":"B31","doi-asserted-by":"publisher","first-page":"947","DOI":"10.1007\/s10489-025-06861-z","article-title":"Mdt: A multiscale differencing transformer with sequence feature relationship mining for robust action recognition","volume":"55","author":"Chen","year":"2025","journal-title":"Appl Intellig"},{"key":"B32","doi-asserted-by":"publisher","first-page":"26114","DOI":"10.1109\/CVPR52734.2025.02432","author":"Sun","year":"2025","journal-title":"Semi-Supervised State-Space Model with Dynamic Stacking Filter for Real-World Video Deraining."},{"key":"B33","doi-asserted-by":"publisher","first-page":"106090","DOI":"10.1016\/j.bspc.2024.106090","article-title":"Multi-head self-attention mechanism-based global feature learning model for asd diagnosis","volume":"91","author":"Zhao","year":"2024","journal-title":"Biomed Signal Process Control"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01386","article-title":"EfficientViT: Memory efficient vision transformer with cascaded group attention","author":"Liu","year":"2023","journal-title":"arXiv"},{"key":"B35","doi-asserted-by":"publisher","first-page":"107520","DOI":"10.1016\/j.compag.2022.107520","article-title":"Evaluation of computer vision for detecting agonistic behavior of pigs in a single-space feeding stall through blocked cross-validation strategies","volume":"204","author":"Han","year":"2023","journal-title":"Comput Electron Agric."},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2405.04517","article-title":"xLSTM: Extended long short-term memory","author":"Beck","year":"2024","journal-title":"arXiv"},{"key":"B37","doi-asserted-by":"publisher","first-page":"20071","DOI":"10.1109\/CVPR52734.2025.01869","author":"Yin","year":"2025","journal-title":"5%>100%: Breaking Performance Shackles of Full Fine-Tuning on Visual Recognition Tasks."}],"container-title":["Frontiers in Veterinary Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fvets.2026.1904986\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T06:43:58Z","timestamp":1788417838000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fvets.2026.1904986\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,3]]},"references-count":37,"alternative-id":["10.3389\/fvets.2026.1904986"],"URL":"https:\/\/doi.org\/10.3389\/fvets.2026.1904986","relation":{},"ISSN":["2297-1769"],"issn-type":[{"value":"2297-1769","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,3]]},"article-number":"1904986"}}