dorsal/arxiv
View SchemaSelf-Supervised Animal Identification for Long Videos
| Authors | Xuyang Fang, Sion Hannuna, Edwin Simpson, Neill Campbell |
|---|---|
| Categories | |
| ArXiv ID | 2601.09663vv1 |
| URL | https://arxiv.org/abs/2601.09663 |
| License | http://creativecommons.org/licenses/by/4.0/ |
Abstract
Identifying individual animals in long-duration videos is essential for behavioral ecology, wildlife monitoring, and livestock management. Traditional methods require extensive manual annotation, while existing self-supervised approaches are computationally demanding and ill-suited for long sequences due to memory constraints and temporal error propagation. We introduce a highly efficient, self-supervised method that reframes animal identification as a global clustering task rather than a sequential tracking problem. Our approach assumes a known, fixed number of individuals within a single video -- a common scenario in practice -- and requires only bounding box detections and the total count. By sampling pairs of frames, using a frozen pre-trained backbone, and employing a self-bootstrapping mechanism with the Hungarian algorithm for in-batch pseudo-label assignment, our method learns discriminative features without identity labels. We adapt a Binary Cross Entropy loss from vision-language models, enabling state-of-the-art accuracy ($>$97\%) while consuming less than 1 GB of GPU memory per batch -- an order of magnitude less than standard contrastive methods. Evaluated on challenging real-world datasets (3D-POP pigeons and 8-calves feeding videos), our framework matches or surpasses supervised baselines trained on over 1,000 labeled frames, effectively removing the manual annotation bottleneck. This work enables practical, high-accuracy animal identification on consumer-grade hardware, with broad applicability in resource-constrained research settings. All code written for this paper are \href{https://huggingface.co/datasets/tonyFang04/8-calves}{here}.
{
"annotation_id": "6eaa5391-d9ba-499d-aada-e0859b880c18",
"date_created": "2026-02-17T05:53:20.291000Z",
"date_modified": "2026-02-17T05:53:20.291000Z",
"file_hash": "ad734da86816408f9ec516e2363010ccc7472ae8d4e694f08a81563d5721f4c6",
"private": false,
"record": {
"abstract": "Identifying individual animals in long-duration videos is essential for behavioral ecology, wildlife monitoring, and livestock management. Traditional methods require extensive manual annotation, while existing self-supervised approaches are computationally demanding and ill-suited for long sequences due to memory constraints and temporal error propagation. We introduce a highly efficient, self-supervised method that reframes animal identification as a global clustering task rather than a sequential tracking problem. Our approach assumes a known, fixed number of individuals within a single video -- a common scenario in practice -- and requires only bounding box detections and the total count. By sampling pairs of frames, using a frozen pre-trained backbone, and employing a self-bootstrapping mechanism with the Hungarian algorithm for in-batch pseudo-label assignment, our method learns discriminative features without identity labels. We adapt a Binary Cross Entropy loss from vision-language models, enabling state-of-the-art accuracy ($\u003e$97\\%) while consuming less than 1 GB of GPU memory per batch -- an order of magnitude less than standard contrastive methods. Evaluated on challenging real-world datasets (3D-POP pigeons and 8-calves feeding videos), our framework matches or surpasses supervised baselines trained on over 1,000 labeled frames, effectively removing the manual annotation bottleneck. This work enables practical, high-accuracy animal identification on consumer-grade hardware, with broad applicability in resource-constrained research settings. All code written for this paper are \\href{https://huggingface.co/datasets/tonyFang04/8-calves}{here}.",
"arxiv_id": "2601.09663",
"authors": [
"Xuyang Fang",
"Sion Hannuna",
"Edwin Simpson",
"Neill Campbell"
],
"categories": [
"cs.CV"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"title": "Self-Supervised Animal Identification for Long Videos",
"url": "https://arxiv.org/abs/2601.09663",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "6b9849e0-5245-49c2-ab3f-863a6162849e",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}