Selective state models are what you need for animal action recognition
Recognizing animal actions provides valuable insights into animal welfare, yielding crucial information for agricultural, ethological, and neuroscientific research. While video-based action recognition models have been applied to this task, current approaches often rely on computationally intensive...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | Ecological Informatics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1574954124004977 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832595421091856384 |
|---|---|
| author | Edoardo Fazzari Donato Romano Fabrizio Falchi Cesare Stefanini |
| author_facet | Edoardo Fazzari Donato Romano Fabrizio Falchi Cesare Stefanini |
| author_sort | Edoardo Fazzari |
| collection | DOAJ |
| description | Recognizing animal actions provides valuable insights into animal welfare, yielding crucial information for agricultural, ethological, and neuroscientific research. While video-based action recognition models have been applied to this task, current approaches often rely on computationally intensive Transformer layers, limiting their practical application in field settings such as farms and wildlife reserves. This study introduces Mamba-MSQNet, a novel architecture family for multilabel Animal Action Recognition using Selective Space Models. By transforming the state-of-the-art MSQNet model with Mamba blocks, we achieve significant reductions in computational requirements: up to 90% fewer Floating point OPerations and 78% fewer parameters compared to MSQNet. These optimizations not only make the model more efficient but also enable it to outperform Transformer-based counterparts on the Animal Kingdom dataset, achieving a mean Average Precision of 74.6, marking an improvement over previous architectures. This combination of enhanced efficiency and improved performance represents a significant advancement in the field of animal action recognition. The dramatic reduction in computational demands, coupled with a performance boost, opens new possibilities for real-time animal behavior monitoring in resource-constrained environments. This enhanced efficiency could revolutionize how we observe and analyze animal behavior, potentially leading to breakthroughs in animal welfare assessment, behavioral studies, and conservation efforts. |
| format | Article |
| id | doaj-art-bae440bcde364fda86a07361a093930d |
| institution | Kabale University |
| issn | 1574-9541 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Ecological Informatics |
| spelling | doaj-art-bae440bcde364fda86a07361a093930d2025-01-19T06:24:39ZengElsevierEcological Informatics1574-95412025-03-0185102955Selective state models are what you need for animal action recognitionEdoardo Fazzari0Donato Romano1Fabrizio Falchi2Cesare Stefanini3The BioRobotics Institute, Sant’Anna School of Advanced Studies, Viale Rinaldo Piaggio, Pontedera, 56025, Tuscany, Italy; Department of Excellence in Robotics and AI, Sant’Anna School of Advanced Studies, Piazza Martiri della Libertà, Pisa, 56127, Tuscany, Italy; Institute of Information Science and Technologies, National Research Council of Italy, Via G. Moruzzi, Pisa, 56124, Tuscany, Italy; Corresponding author at: The BioRobotics Institute, Sant’Anna School of Advanced Studies, Viale Rinaldo Piaggio, Pontedera, 56025, Tuscany, Italy.The BioRobotics Institute, Sant’Anna School of Advanced Studies, Viale Rinaldo Piaggio, Pontedera, 56025, Tuscany, Italy; Department of Excellence in Robotics and AI, Sant’Anna School of Advanced Studies, Piazza Martiri della Libertà, Pisa, 56127, Tuscany, ItalyThe BioRobotics Institute, Sant’Anna School of Advanced Studies, Viale Rinaldo Piaggio, Pontedera, 56025, Tuscany, Italy; Institute of Information Science and Technologies, National Research Council of Italy, Via G. Moruzzi, Pisa, 56124, Tuscany, ItalyThe BioRobotics Institute, Sant’Anna School of Advanced Studies, Viale Rinaldo Piaggio, Pontedera, 56025, Tuscany, Italy; Department of Excellence in Robotics and AI, Sant’Anna School of Advanced Studies, Piazza Martiri della Libertà, Pisa, 56127, Tuscany, ItalyRecognizing animal actions provides valuable insights into animal welfare, yielding crucial information for agricultural, ethological, and neuroscientific research. While video-based action recognition models have been applied to this task, current approaches often rely on computationally intensive Transformer layers, limiting their practical application in field settings such as farms and wildlife reserves. This study introduces Mamba-MSQNet, a novel architecture family for multilabel Animal Action Recognition using Selective Space Models. By transforming the state-of-the-art MSQNet model with Mamba blocks, we achieve significant reductions in computational requirements: up to 90% fewer Floating point OPerations and 78% fewer parameters compared to MSQNet. These optimizations not only make the model more efficient but also enable it to outperform Transformer-based counterparts on the Animal Kingdom dataset, achieving a mean Average Precision of 74.6, marking an improvement over previous architectures. This combination of enhanced efficiency and improved performance represents a significant advancement in the field of animal action recognition. The dramatic reduction in computational demands, coupled with a performance boost, opens new possibilities for real-time animal behavior monitoring in resource-constrained environments. This enhanced efficiency could revolutionize how we observe and analyze animal behavior, potentially leading to breakthroughs in animal welfare assessment, behavioral studies, and conservation efforts.http://www.sciencedirect.com/science/article/pii/S1574954124004977Animal action recognitionDeep learningSelective state modelsComputer visionMambaMsqnet |
| spellingShingle | Edoardo Fazzari Donato Romano Fabrizio Falchi Cesare Stefanini Selective state models are what you need for animal action recognition Ecological Informatics Animal action recognition Deep learning Selective state models Computer vision Mamba Msqnet |
| title | Selective state models are what you need for animal action recognition |
| title_full | Selective state models are what you need for animal action recognition |
| title_fullStr | Selective state models are what you need for animal action recognition |
| title_full_unstemmed | Selective state models are what you need for animal action recognition |
| title_short | Selective state models are what you need for animal action recognition |
| title_sort | selective state models are what you need for animal action recognition |
| topic | Animal action recognition Deep learning Selective state models Computer vision Mamba Msqnet |
| url | http://www.sciencedirect.com/science/article/pii/S1574954124004977 |
| work_keys_str_mv | AT edoardofazzari selectivestatemodelsarewhatyouneedforanimalactionrecognition AT donatoromano selectivestatemodelsarewhatyouneedforanimalactionrecognition AT fabriziofalchi selectivestatemodelsarewhatyouneedforanimalactionrecognition AT cesarestefanini selectivestatemodelsarewhatyouneedforanimalactionrecognition |