The study investigates whether Vision Transformer (ViT)-based animal re-identification models learn biologically meaningful concepts. Using a DINOv3 backbone fine‑tuned on Western lowland gorilla images, the authors find that sex and age emerge as linear directions in the model’s representations, generalizing to unseen individuals with high AUROC scores. They demonstrate that the sex direction is causally used by the model, that fine‑tuning relocates these concepts within the network, and that the representations reflect a graded biological axis encoded redundantly across the population.
By Robert Nolting, Alexandra Schild, Moritz Weckbecker, Maximilian Schall, Gerard de Melo
arXiv:2512.07776v2 Announce Type: replace
Abstract: Monitoring critically endangered western lowland gorillas is currently hampered by the immense manual effort required to re-identify individuals fr...
By Maximilian Schall, Felix Leonard Kn\"ofel, Noah Elias K\"onig, Jan Jonas Kubeler, Maximilian von Klinski, Joan Wilhelm Linnemann, Xiaoshi Liu, Iven Jelle Schlegelmilch, Ole Woyciniuk, Alexandra Schild, Dante Wasmuht, Magdalena Bermejo Espinet, German Illera Basas, Gerard de Melo
arXiv:2606. 09353v1 Announce Type: cross Abstract: Individual animal recognition can be useful in the search for lost or stolen pets, the tracking of individuals of endangered species, and the recognition of animals in crowded farms.
By Maria De Marsico, Anil K. Jain, Annalaura Miglino
arXiv:2609.09705v1 Announce Type: new
Abstract: Generalizable animal Re-Identification (ReID) aims to recognize individual animals across species with diverse morphologies and ecological contexts. Un...
By Shuoyi Chen, Yuejia Li, Mang Ye
arXiv:2607. 09443v1 Announce Type: cross Abstract: Long-term animal re-identification (ReID) must remain robust to gradual morphological evolution and seasonal appearance shifts.
By Anil Osman Tur, Tonje Knutsen Sordalen, Kim Tallaksen Halvorsen, Cigdem Beyan
The paper introduces a one-stage end-to-end model for wildlife instance-level recognition that integrates detection and re-identification within a single latent space. It leverages DINOv2 for spatial geometry and MegaDescriptor for re-identification, while enhancing latent queries with prompt re-identification features. Preliminary results show a competitive mean average precision of 30.584% compared to the state-of-the-art two-stage approach of 44.89%, with qualitative evidence of effective bounding and identification of animal identities.
By Mufhumudzi Muthivhi, Jiahao Huo, Terence van Zyl, Fredrik Gustafsson
arXiv:2606. 00548v1 Announce Type: cross Abstract: Concentrated Animal Feeding Operations (CAFOs) play an important role in agricultural production but are also associated with environmental, public health, and disease surveillance concerns.
By Oishee Bintey Hoque, Nibir Chandra Mandal, Mandy L Wilson, Samarth Swarup, Madhav Marathe, Abhijin Adiga
arXiv:2512. 15748v2 Announce Type: replace Abstract: Visual Species Recognition (VSR) is a fundamental task in scientific disciplines that require species-level identification, including ecology, palynology, evolutionary biology, systematics, and phylogenetics.
By Tian Liu, Anwesha Basu, James Caverlee, Shu Kong
arXiv:2606. 15655v1 Announce Type: new Abstract: The need for effective cattle identification technology is now more acutely felt than ever in maintaining biosecurity, food safety, and supply chain efficacy in livestock management.
By Fayazunnesa Chowdhury, Syed Md. Galib, Md Nasim Adnan, Md. Moradul Siddique, Md Robiul Karim, K M Tanvir Anjum
arXiv:2605. 05627v2 Announce Type: replace-cross Abstract: Sustainable forest management relies on precise species composition mapping, yet traditional ground surveys are labour-intensive and geographically constrained.
By Gabriel Jeanson, David-Alexandre Duclos, William Larriv\'ee-Hardy, No\'e Cochet, Mat\v{e}j Boxan, Anthony Desch\^enes, Fran\c{c}ois Pomerleau, Philippe Gigu\`ere
The paper presents a deep learning approach for detecting woody clearing using bitemporal Sentinel‑2 imagery from New South Wales, Australia. By introducing a loss‑scaling coefficient, the authors align the model’s objective with end‑user metrics, boosting precision and recall. They further demonstrate zero‑shot transfer to woody regrowth and segmentation tasks, achieving significant error reductions and high F1 scores through image augmentation and generation techniques.
By Kal Backman, Jared Wood, Adam Roff
arXiv:2607. 17157v1 Announce Type: cross Abstract: Multi-object tracking (MOT) aims to localize multiple objects in videos while preserving their identities over time.
By Yanrong Qin, Xiaoyan Cao, Yao Yao