Self-supervised Learning on Camera Trap Footage Yields a Strong Universal Face Embedder Article Swipe
Vladimir Iashin
,
H.S. Lee
,
Daniel Schofield
,
Andrew Zisserman
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2507.10552
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2507.10552
Camera traps are revolutionising wildlife monitoring by capturing vast amounts of visual data; however, the manual identification of individual animals remains a significant bottleneck. This study introduces a fully self-supervised approach to learning robust chimpanzee face embeddings from unlabeled camera-trap footage. Leveraging the DINOv2 framework, we train Vision Transformers on automatically mined face crops, eliminating the need for identity labels. Our method demonstrates strong open-set re-identification performance, surpassing supervised baselines on challenging benchmarks such as Bossou, despite utilising no labelled data during training. This work underscores the potential of self-supervised learning in biodiversity monitoring and paves the way for scalable, non-invasive population studies.
Related Topics
Concepts
No concepts available.
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2507.10552
- https://arxiv.org/pdf/2507.10552
- OA Status
- green
- OpenAlex ID
- https://openalex.org/W4414742268
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4414742268Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2507.10552Digital Object Identifier
- Title
-
Self-supervised Learning on Camera Trap Footage Yields a Strong Universal Face EmbedderWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-07-14Full publication date if available
- Authors
-
Vladimir Iashin, H.S. Lee, Daniel Schofield, Andrew ZissermanList of authors in order
- Landing page
-
https://arxiv.org/abs/2507.10552Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2507.10552Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2507.10552Direct OA link when available
- Cited by
-
0Total citation count in OpenAlex
Full payload
| id | https://openalex.org/W4414742268 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2507.10552 |
| ids.doi | https://doi.org/10.48550/arxiv.2507.10552 |
| ids.openalex | https://openalex.org/W4414742268 |
| fwci | |
| type | preprint |
| title | Self-supervised Learning on Camera Trap Footage Yields a Strong Universal Face Embedder |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11448 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9962000250816345 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1707 |
| topics[0].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[0].display_name | Face recognition and analysis |
| topics[1].id | https://openalex.org/T10331 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9861999750137329 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1707 |
| topics[1].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[1].display_name | Video Surveillance and Tracking Methods |
| topics[2].id | https://openalex.org/T10057 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9715999960899353 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1707 |
| topics[2].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[2].display_name | Face and Expression Recognition |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2507.10552 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2507.10552 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2507.10552 |
| locations[1].id | doi:10.48550/arxiv.2507.10552 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | cc-by |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | https://openalex.org/licenses/cc-by |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2507.10552 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5008909874 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-8879-587X |
| authorships[0].author.display_name | Vladimir Iashin |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Iashin, Vladimir |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5061180501 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | H.S. Lee |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Lee, Horace |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5101857466 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-9251-8653 |
| authorships[2].author.display_name | Daniel Schofield |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Schofield, Dan |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5057678172 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-8945-8573 |
| authorships[3].author.display_name | Andrew Zisserman |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Zisserman, Andrew |
| authorships[3].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2507.10552 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Self-supervised Learning on Camera Trap Footage Yields a Strong Universal Face Embedder |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11448 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9962000250816345 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1707 |
| primary_topic.subfield.display_name | Computer Vision and Pattern Recognition |
| primary_topic.display_name | Face recognition and analysis |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2507.10552 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2507.10552 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2507.10552 |
| primary_location.id | pmh:oai:arXiv.org:2507.10552 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2507.10552 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2507.10552 |
| publication_date | 2025-07-14 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 21, 27 |
| abstract_inverted_index.as | 74 |
| abstract_inverted_index.by | 6 |
| abstract_inverted_index.in | 91 |
| abstract_inverted_index.no | 78 |
| abstract_inverted_index.of | 10, 17, 88 |
| abstract_inverted_index.on | 49, 70 |
| abstract_inverted_index.to | 31 |
| abstract_inverted_index.we | 45 |
| abstract_inverted_index.Our | 60 |
| abstract_inverted_index.and | 94 |
| abstract_inverted_index.are | 2 |
| abstract_inverted_index.for | 57, 98 |
| abstract_inverted_index.the | 14, 42, 55, 86, 96 |
| abstract_inverted_index.way | 97 |
| abstract_inverted_index.This | 24, 83 |
| abstract_inverted_index.data | 80 |
| abstract_inverted_index.face | 35, 52 |
| abstract_inverted_index.from | 37 |
| abstract_inverted_index.need | 56 |
| abstract_inverted_index.such | 73 |
| abstract_inverted_index.vast | 8 |
| abstract_inverted_index.work | 84 |
| abstract_inverted_index.data; | 12 |
| abstract_inverted_index.fully | 28 |
| abstract_inverted_index.mined | 51 |
| abstract_inverted_index.paves | 95 |
| abstract_inverted_index.study | 25 |
| abstract_inverted_index.train | 46 |
| abstract_inverted_index.traps | 1 |
| abstract_inverted_index.Camera | 0 |
| abstract_inverted_index.DINOv2 | 43 |
| abstract_inverted_index.Vision | 47 |
| abstract_inverted_index.crops, | 53 |
| abstract_inverted_index.during | 81 |
| abstract_inverted_index.manual | 15 |
| abstract_inverted_index.method | 61 |
| abstract_inverted_index.robust | 33 |
| abstract_inverted_index.strong | 63 |
| abstract_inverted_index.visual | 11 |
| abstract_inverted_index.Bossou, | 75 |
| abstract_inverted_index.amounts | 9 |
| abstract_inverted_index.animals | 19 |
| abstract_inverted_index.despite | 76 |
| abstract_inverted_index.labels. | 59 |
| abstract_inverted_index.remains | 20 |
| abstract_inverted_index.approach | 30 |
| abstract_inverted_index.footage. | 40 |
| abstract_inverted_index.however, | 13 |
| abstract_inverted_index.identity | 58 |
| abstract_inverted_index.labelled | 79 |
| abstract_inverted_index.learning | 32, 90 |
| abstract_inverted_index.open-set | 64 |
| abstract_inverted_index.studies. | 102 |
| abstract_inverted_index.wildlife | 4 |
| abstract_inverted_index.baselines | 69 |
| abstract_inverted_index.capturing | 7 |
| abstract_inverted_index.potential | 87 |
| abstract_inverted_index.scalable, | 99 |
| abstract_inverted_index.training. | 82 |
| abstract_inverted_index.unlabeled | 38 |
| abstract_inverted_index.utilising | 77 |
| abstract_inverted_index.Leveraging | 41 |
| abstract_inverted_index.benchmarks | 72 |
| abstract_inverted_index.chimpanzee | 34 |
| abstract_inverted_index.embeddings | 36 |
| abstract_inverted_index.framework, | 44 |
| abstract_inverted_index.individual | 18 |
| abstract_inverted_index.introduces | 26 |
| abstract_inverted_index.monitoring | 5, 93 |
| abstract_inverted_index.population | 101 |
| abstract_inverted_index.supervised | 68 |
| abstract_inverted_index.surpassing | 67 |
| abstract_inverted_index.bottleneck. | 23 |
| abstract_inverted_index.camera-trap | 39 |
| abstract_inverted_index.challenging | 71 |
| abstract_inverted_index.eliminating | 54 |
| abstract_inverted_index.significant | 22 |
| abstract_inverted_index.underscores | 85 |
| abstract_inverted_index.Transformers | 48 |
| abstract_inverted_index.biodiversity | 92 |
| abstract_inverted_index.demonstrates | 62 |
| abstract_inverted_index.non-invasive | 100 |
| abstract_inverted_index.performance, | 66 |
| abstract_inverted_index.automatically | 50 |
| abstract_inverted_index.identification | 16 |
| abstract_inverted_index.revolutionising | 3 |
| abstract_inverted_index.self-supervised | 29, 89 |
| abstract_inverted_index.re-identification | 65 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 4 |
| citation_normalized_percentile |