aiqbench analysis
This study demonstrates a viable multimodal deep-learning framework that fuses CNN-based visual analysis with osteometric data for classifying avian skeletal remains in zooarchaeology. By integrating segmentation tools like SAM2 and EfficientNet_V2_S, the model achieves 86% accuracy on bone-type identification while providing probabilistic insights into more complex family-level taxonomic classification. The work establishes a methodological baseline for scalable AI-assisted analysis of archaeological collections without relying solely on visual features or manual measurements.
Multimodal fusion of visual and morphometric features for avian bone classification
arXiv:2607.26743v1 Announce Type: cross Abstract: Artificial intelligence has shown considerable potential for archaeological applications, yet its use in zooarchaeology remains limited, particularly for the identification of avian skeletal remains. This study presents a proof-of-concept multimodal framework that integrates convolutional neural network-based image analysis with osteometric measurements for the classification of bird bones. Using a dataset of more than 10,000 images from multiple museum and research collections, two classification tasks were investigated: skeletal element identification and family-level taxonomic classification. Prior to classification, images were automatically segmented using a two-stage pipeline combining BiRefNet and SAM2. Visual features extracted with a pre-trained EfficientNet_V2_S backbone were fused with standardized morphometric data through a feature-level multimodal architecture. The model achieved 86% accuracy on the test set for bone-type classification, demonstrating reliable recognition of skeletal elements. Family-level classification proved more challenging, reaching 51% top-1 accuracy but 75% top-3 accuracy, indicating that correct taxa were frequently included among the most probable predictions. These results demonstrate the feasibility of combining visual and morphometric information within a unified deep-learning framework and establish a methodological baseline for future AI-assisted zooarchaeological identification. The approach contributes to ongoing efforts to develop scalable, interpretable, and archaeologically meaningful tools for the study of avian remains.
Abstract:Artificial intelligence has shown considerable potential for archaeological applications, yet its use in zooarchaeology remains limited, particularly for the identification of avian skeletal remains. This study presents a proof-of-concept multimodal framework that integrates convolutional neural network-based image analysis with osteometric measurements for the classification of bird bones. Using a dataset of more than 10,000 images from multiple museum and research collections, two classification tasks were investigated: skeletal element identification and family-level taxonomic classification. Prior to classification, images were automatically segmented using a two-stage pipeline combining BiRefNet and SAM2. Visual features extracted with a pre-trained EfficientNet_V2_S backbone were fused with standardized morphometric data through a feature-level multimodal architecture. The model achieved 86% accuracy on the test set for bone-type classification, demonstrating reliable recognition of skeletal elements. Family-level classification proved more challenging, reaching 51% top-1 accuracy but 75% top-3 accuracy, indicating that correct taxa were frequently included among the most probable predictions. These results demonstrate the feasibility of combining visual and morphometric information within a unified deep-learning framework and establish a methodological baseline for future AI-assisted zooarchaeological identification. The approach contributes to ongoing efforts to develop scalable, interpretable, and archaeologically meaningful tools for the study of avian remains.
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
arXiv:2607.26743 [cs.CV]
(or arXiv:2607.26743v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2607.26743 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 296 words
Related coverage
Before Fusion, Ask What to Keep: Contextual Calibration of Multimodal Signals
arXiv · Jun 3, 2026
Chinese Academy of Sciences’ PQFA Cuts Multimodal Model Parameters by 10×
Quantum Zeitgeist · Jul 30, 2026
Toward Interpretable Multimodal Fusion: Heat Conduction Modeling for Hyperspectral and LiDAR Joint Classification
arXiv · Sep 12, 2026
MUPA$^{2}$E: Multimodal Unified Perception with Asymmetric Attention for Emotion Assessment
arXiv · Aug 18, 2026