pith. machine review for the scientific record. sign in

arxiv: 2604.20626 · v1 · submitted 2026-04-22 · 🧬 q-bio.PE · cs.AI

Recognition: unknown

Centering Ecological Goals in Automated Identification of Individual Animals

Arjun Subramonian, Charles Stewart, Daniela Hedwig, Daniel Rubenstein, Ekaterina Nepovinnykh, Justin Kitzes, Kostas Papafitsoros, Lasha Otarashvili, Lukas Picek, Luk\'a\v{s} Adam, Michael B. Brown, Sam Lapp, Sara Beery, Silvia Zuffi, Subhransu Maji, Tanya Berger-Wolf, Tilo Burghardt, Timm Haucke, Vojtech Cermak

Pith reviewed 2026-05-09 22:34 UTC · model grok-4.3

classification 🧬 q-bio.PE cs.AI
keywords individual animal identificationecological monitoringautomated recognitionconservationAI in ecologydata workflowspopulation estimation
0
0 comments X

The pith

Automated animal identification in ecology is limited more by mismatched development practices than by algorithm performance.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper argues that while automated methods for recognizing individual animals from images or sounds have improved, they see little use in actual ecological and conservation work. The reason lies in a fundamental mismatch: methods are created and tested using standard machine learning approaches focused on benchmark accuracy, whereas ecological data involves specific collection methods, review processes, and decisions where certain errors carry more weight than others. A sympathetic reader would care because this suggests that simply making models more accurate will not solve the problem; instead, the tools must be designed around the real questions ecologists ask about populations, movements, and behaviors.

Core claim

Recognizing individual animals over time is central to many ecological and conservation questions, including estimating abundance, survival, movement, and social structure. Recent advances in automated identification from images and even acoustic data suggest that this process could be greatly accelerated, yet their promise has not translated well into ecological practice. The main barrier is not the performance of the automated methods themselves, but a mismatch between how those methods are typically developed and evaluated, and how ecological data is actually collected, processed, reviewed, and used. Future progress will depend less on algorithmic gains alone than on recognizing that the

What carries the argument

The mismatch between how automated identification methods are typically developed and evaluated using general performance metrics and the actual workflows of ecological data collection, processing, review, and application in answering specific questions.

If this is right

  • Future automated identification systems must incorporate evaluation criteria based on ecological utility rather than solely on technical accuracy.
  • Development should account for the specific data constraints and decision contexts in conservation biology.
  • Transparency in how models handle errors will be essential for trust in ecological applications.
  • Centering the particular questions being asked will guide what level of performance is sufficient.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Integrating ecological expertise early in model design could reveal new technical challenges not apparent in standard benchmarks.
  • Similar mismatches may exist in other applications of AI to field sciences.
  • Adopting this approach might require new types of collaborative datasets that include metadata on data provenance and error costs.

Load-bearing premise

The mismatch between development practices and ecological workflows is the primary reason automated methods have not been adopted more widely.

What would settle it

A demonstration that current automated identification methods achieve high adoption in ecological studies when their accuracy is improved, without changes to how they are developed or evaluated, would falsify the claim.

read the original abstract

Recognizing individual animals over time is central to many ecological and conservation questions, including estimating abundance, survival, movement, and social structure. Recent advances in automated identification from images and even acoustic data suggest that this process could be greatly accelerated, yet their promise has not translated well into ecological practice. We argue that the main barrier is not the performance of the automated methods themselves, but a mismatch between how those methods are typically developed and evaluated, and how ecological data is actually collected, processed, reviewed, and used. Future progress, therefore, will depend less on algorithmic gains alone than on recognizing that the usefulness of automated identification is grounded in ecological context: it depends on what question is being asked, what data are available, and what kinds of mistakes matter. Only by centering these questions can we move toward automated identification of individuals that is not only accurate but also ecologically useful, transparent, and trustworthy.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 1 minor

Summary. The paper argues that recent advances in automated identification of individual animals from images and acoustic data have not translated well into ecological practice. The central claim is that the main barrier is not insufficient performance of the methods, but a mismatch between how the methods are typically developed and evaluated versus how ecological data is actually collected, processed, reviewed, and used. It concludes that future progress requires centering ecological goals, questions, data availability, and the consequences of different kinds of errors to produce identification tools that are useful, transparent, and trustworthy.

Significance. If the core argument holds and is supported by evidence, the manuscript could usefully redirect priorities in both ecology and computer vision toward more context-aware development of automated tools, increasing their practical adoption in conservation and population studies. It correctly notes that ecological utility depends on more than raw accuracy metrics. However, the absence of quantitative support or case studies for ranking mismatch as the dominant barrier limits the strength of this call to action.

major comments (2)
  1. [Abstract] Abstract: The claim that 'the main barrier is not the performance of the automated methods themselves, but a mismatch...' is load-bearing for the entire thesis yet rests on unshown examples with no quantitative benchmarks, adoption statistics, or comparative analysis showing that mismatch outweighs other factors such as data scarcity, annotation costs, or model limits on variable wild imagery.
  2. [Main text] Main argument (throughout): The text assumes current automated methods already achieve 'ecologically usable accuracy on representative imagery/acoustics' but provides no specific performance metrics, datasets, or counter-examples to support this premise, leaving the ranking of mismatch as the primary barrier without falsifiable grounding.
minor comments (1)
  1. [Abstract] Abstract: A single concrete example of the described mismatch (e.g., a specific ecological workflow versus a typical ML evaluation protocol) would strengthen accessibility without lengthening the piece.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their thoughtful and constructive comments, which highlight important considerations for strengthening the evidential basis of our perspective. We respond to each major comment below, indicating where we agree that revisions would improve the manuscript.

read point-by-point responses

  1. Referee: [Abstract] Abstract: The claim that 'the main barrier is not the performance of the automated methods themselves, but a mismatch...' is load-bearing for the entire thesis yet rests on unshown examples with no quantitative benchmarks, adoption statistics, or comparative analysis showing that mismatch outweighs other factors such as data scarcity, annotation costs, or model limits on variable wild imagery.

    Authors: The manuscript is a perspective article that draws on patterns documented across the published literature on automated identification rather than presenting new empirical rankings of barriers. We cite cases in which high benchmark performance has not led to routine ecological use due to mismatches in data collection protocols, error cost structures, and workflow integration. We agree that the argument would benefit from more explicit citations to such examples and can revise the abstract and introduction to reference specific studies illustrating these points, while preserving the perspective format. revision: partial

  2. Referee: [Main text] Main argument (throughout): The text assumes current automated methods already achieve 'ecologically usable accuracy on representative imagery/acoustics' but provides no specific performance metrics, datasets, or counter-examples to support this premise, leaving the ranking of mismatch as the primary barrier without falsifiable grounding.

    Authors: We do not claim that every current method has reached ecologically usable accuracy on representative data. The core observation is that reported performance gains in the literature have not produced proportional increases in ecological adoption. We will revise the main text to include concrete citations to studies reporting high accuracies on standard image and acoustic datasets, paired with discussion of documented limitations in real-world application. This provides the requested grounding through existing literature without converting the piece into a data-driven meta-analysis. revision: yes

Circularity Check

0 steps flagged

No circularity: position paper with no derivations or self-referential modeling

full rationale

The manuscript is a normative critique arguing that the primary barrier to adoption of automated individual animal identification is a mismatch between typical ML development practices and real ecological workflows. It contains no equations, no fitted parameters, no predictive models, and no derivation chain. The central claim is supported by qualitative discussion of data collection realities rather than any self-citation load-bearing theorem or ansatz. No step reduces to its own inputs by construction. This is the expected outcome for an opinion/position paper without mathematical content.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

No free parameters, formal axioms, or invented entities; the work is a non-technical position paper.

pith-pipeline@v0.9.0 · 5540 in / 968 out tokens · 82285 ms · 2026-05-09T22:34:51.396836+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

77 extracted references · 6 canonical work pages

  1. [1]

    In: Proceedings of the IEEE/CVF winter conference on applications of computer vision, pp 7146–7156

    Adam L, ˇCerm´ ak V, Papafitsoros K, et al (2024) Seaturtleid2022: A long-span dataset for reliable sea turtle re-identification. In: Proceedings of the IEEE/CVF winter conference on applications of computer vision, pp 7146–7156

    2024

  2. [2]

    In: 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), IEEE, pp 2090–2100

    Adam L, ˇCerm´ ak V, Papafitsoros K, et al (2025) Wildlifereid-10k: Wildlife re- identification dataset with 10k individual animals. In: 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), IEEE, pp 2090–2100

    2025

  3. [3]

    Ecological Informatics 89:103158

    Adam L, Papafitsoros K, Jean C, et al (2025) Exploiting facial side similarities to improve ai-driven sea turtle photo-identification systems. Ecological Informatics 89:103158

    2025

  4. [4]

    Marine Ecology Progress Series 552:241–253

    Andreotti S, Rutzen M, van der Walt S, et al (2016) An integrated mark-recapture and genetic approach to estimate the population size of white sharks in south africa. Marine Ecology Progress Series 552:241–253

    2016

  5. [5]

    Journal of Applied Ecology 42(6):999–1011

    Arzoumanian Z, Holmberg J, Norman B (2005) An astronomical pattern-matching algo- rithm for computer-aided identification of whale sharks rhincodon typus. Journal of Applied Ecology 42(6):999–1011

    2005

  6. [6]

    IUCN/SSC Marine Turtle Specialist Group Publication

    Balazs GH (1999) Factors to consider in the tagging of sea turtles. IUCN/SSC Marine Turtle Specialist Group Publication

    1999

  7. [7]

    In: Proceedings of the European Conference on Computer Vision (ECCV), pp 456–473, https://doi

    Beery S, Van Horn G, Perona P (2018) Recognition in terra incognita. In: Proceedings of the European Conference on Computer Vision (ECCV), pp 456–473, https://doi. org/10.1007/978-3-030-01270-0 28

    work page doi:10.1007/978-3-030-01270-0 2018

  8. [8]

    Grevy’s Zebra Trust, Nairobi, Kenya, Tech Rep

    Berger-Wolf T, Crall J, Holberg J, et al (2016) The great grevy’s rally: The need, methods, findings, implications and next steps. Grevy’s Zebra Trust, Nairobi, Kenya, Tech Rep

    2016

  9. [9]

    arXiv preprint arXiv:171008880

    Berger-Wolf TY, Rubenstein DI, Stewart CV, et al (2017) Wildbook: Crowdsourcing, computer vision, and data science for conservation. arXiv preprint arXiv:171008880

    2017

  10. [10]

    Methods in Ecology and Evolution 9(4):946–955

    Bodey TW, Cleasby IR, Bell F, et al (2018) A phylogenetically controlled meta-analysis of biologging device effects on birds: Deleterious effects and a call for more standardized reporting of study data. Methods in Ecology and Evolution 9(4):946–955

    2018

  11. [11]

    Methods in Ecology and Evolution 3(5):813–822

    Bolger DT, Morrison TA, Vance B, et al (2012) A computer-assisted system for photographic mark–recapture analysis. Methods in Ecology and Evolution 3(5):813–822

    2012

  12. [12]

    Journal of Animal Ecology 90(1):212–221

    Bond ML, K¨ onig B, Lee DE, et al (2021) Proximity to humans affects local social structure in a giraffe metapopulation. Journal of Animal Ecology 90(1):212–221

    2021

  13. [13]

    Frontiers in Ecology and Evolution 7:524

    Brown MB, Bolger DT (2020) Male-biased partial migration in a giraffe population. Frontiers in Ecology and Evolution 7:524

    2020

  14. [14]

    Global Ecology and Conservation 19:e00612

    Brown MB, Bolger DT, Fennessy J (2019) All the eggs in one basket: A countrywide assessment of current and historical giraffe population distribution in uganda. Global Ecology and Conservation 19:e00612

    2019

  15. [15]

    Conservation Science and Practice 15 7(10):e70127

    Brown MB, Kasozi H, Aruho R, et al (2025) Assessing the success of conserva- tion translocation establishment: Post-translocation demography of nubian giraffe (giraffa camelopardalis camelopardalis) in uganda. Conservation Science and Practice 15 7(10):e70127

    2025

  16. [16]

    Methods in Ecology and Evolution 16(6):1061–1074

    Brun J, Lyon NJ, Chen A, et al (2025) Enabling data-driven collaborative and reproducible environmental synthesis science. Methods in Ecology and Evolution 16(6):1061–1074

    2025

  17. [17]

    Journal of Experimental Marine Biology and Ecology 476:15–21

    Carpentier AS, Jean C, Barret M, et al (2016) Stability of facial scale patterns on green sea turtles chelonia mydas over time: a validation for the use of a photo-identification method. Journal of Experimental Marine Biology and Ecology 476:15–21

    2016

  18. [18]

    In: European Conference on Computer Vision, Springer, pp 18–36

    Cermak V, Picek L, Adam L, et al (2024) Wildfusion: Individual animal identifica- tion with calibrated similarity fusion. In: European Conference on Computer Vision, Springer, pp 18–36

    2024

  19. [19]

    In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp 5953–5963

    ˇCerm´ ak V, Picek L, Adam L, et al (2024) Wildlifedatasets: An open-source toolkit for animal re-identification. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp 5953–5963

    2024

  20. [20]

    Happywhale, Santa Cruz, CA, USA, Rep SC/67b/PH 2

    Cheeseman T, Johnson T, Southerland K, et al (2017) Happywhale: Globalizing marine mammal photo identification via a citizen science web platform. Happywhale, Santa Cruz, CA, USA, Rep SC/67b/PH 2

    2017

  21. [21]

    Global Ecology and Conservation 24:e01294

    Choo YR, Kudavidanage EP, Amarasinghe TR, et al (2020) Best practices for report- ing individual identification using camera trap photographs. Global Ecology and Conservation 24:e01294

    2020

  22. [22]

    Trends in ecology & evolution 25(10):562–573

    Clutton-Brock T, Sheldon BC (2010) Individuals and populations: the role of long- term, individual-based studies of animals in ecology and evolutionary biology. Trends in ecology & evolution 25(10):562–573

    2010

  23. [23]

    In: 2013 IEEE workshop on applications of computer vision (WACV), IEEE, pp 230–237

    Crall JP, Stewart CV, Berger-Wolf TY, et al (2013) Hotspotter—patterned species instance recognition. In: 2013 IEEE workshop on applications of computer vision (WACV), IEEE, pp 230–237

    2013

  24. [24]

    Marine Ecology 39(1):e12489

    Dujon AM, Schofield G, Lester RE, et al (2018) Complex movement patterns by foraging loggerhead sea turtles outside the breeding season identified using argos-linked fastloc- global positioning system. Marine Ecology 39(1):e12489

    2018

  25. [25]

    Remote Sensing in Ecology and Conservation 7(3):341–354

    Dujon AM, Ierodiaconou D, Geeson JJ, et al (2021) Machine learning to detect marine animals in uav imagery: effect of morphology, spacing, behaviour and habitat. Remote Sensing in Ecology and Conservation 7(3):341–354

    2021

  26. [26]

    Scientific Reports 11(1):9236

    Dul’a M, Bojda M, Chabanne DB, et al (2021) Multi-seasonal systematic camera- trapping reveals fluctuating densities and high turnover rates of carpathian lynx on the western edge of its native range. Scientific Reports 11(1):9236

    2021

  27. [27]

    Journal of Experimental Marine Biology and Ecology 535:151490

    Dunbar SG, Anger EC, Parham JR, et al (2021) Hotspotter: Using a computer-driven photo-id application to identify sea turtles. Journal of Experimental Marine Biology and Ecology 535:151490

    2021

  28. [28]

    Endangered Species Research 59:1–12 16

    Fong CL, Li TH, Hoh D, et al (2026) Long-term wild recovery and resilience of green turtles chelonia mydas to various anthropogenic injuries. Endangered Species Research 59:1–12 16

    2026

  29. [29]

    (2008) The timing of the conscious intention to move.Eur J Neurosci.28(11): 2344–2351https://doi.org/10.1111/j

    Foster JB (1966) The giraffe of Nairobi National Park: home range, sex ratios, the herd, and food. East African Wildlife Journal 4:139–148. https://doi.org/10.1111/j. 1365-2028.1966.tb00889.x

    work page doi:10.1111/j 1966

  30. [30]

    arXiv preprint arXiv:260304314

    Grolleau W, Chaouch A, Sabourin A, et al (2026) Moo: A multi-view oriented observations dataset for viewpoint analysis in cattle re-identification. arXiv preprint arXiv:260304314

    2026

  31. [31]

    African Journal of Ecology 53(2):147–155

    Halloran KM, Murdoch JD, Becker MS (2015) Applying computer-aided photo- identification to messy datasets: a case study of t hornicroft’s giraffe (g iraffa camelopardalis thornicrofti). African Journal of Ecology 53(2):147–155

    2015

  32. [32]

    Frontiers in Marine Science 10:1217683

    Hancock JM, Choma J, Mainye L, et al (2023) Using photo-id to document and monitor the prevalence of fibropapilloma tumours in a foraging aggregation of green turtles. Frontiers in Marine Science 10:1217683

    2023

  33. [33]

    Report of the International Whaling Commission 12:57–61

    Hiby L, Lovell P (1990) Computer aided matching of natural markings: a prototype system for grey seals. Report of the International Whaling Commission 12:57–61

    1990

  34. [34]

    Bioacoustics 32(5):506–531

    Hoefer S, McKnight DT, Allen-Ankins S, et al (2023) Passive acoustic monitoring in terrestrial vertebrates: a review. Bioacoustics 32(5):506–531

    2023

  35. [35]

    PLoS One 18(4):e0283973

    Hudgins JA, Hudgins EJ, K¨ ohnk S, et al (2023) A brighter future? stable and growing sea turtle populations in the republic of maldives. PLoS One 18(4):e0283973

    2023

  36. [36]

    ACM Transactions on Computer-Human Interaction 30(5):1–29

    Inkpen K, Chappidi S, Mallari K, et al (2023) Advancing human-ai complementarity: The impact of user expertise and algorithmic tuning on joint decision making. ACM Transactions on Computer-Human Interaction 30(5):1–29

    2023

  37. [37]

    Jain AK (2005) Biometric recognition: how do i know who you are? In: International Conference on Image Analysis and Processing, Springer, pp 19–26

    2005

  38. [38]

    Frontiers in Ecology and the Environment 22(1):e2599

    Jari´ c I, Normande IC, Arbieu U, et al (2024) Flagship individuals in biodiversity conservation. Frontiers in Ecology and the Environment 22(1):e2599

    2024

  39. [39]

    Mammalian Biology 102(3):545–549

    Karczmarski L, Chan SC, Rubenstein DI, et al (2022) Individual identification and photographic techniques in mammalian ecological and behavioural research—part 1: Methods and concepts. Mammalian Biology 102(3):545–549

    2022

  40. [40]

    https://doi.org/10.1016/j

    Knight E, Rhinehart T, de Zwaan DR, et al (2024) Individual identification in acoustic recordings. Trends in Ecology & Evolution 39(10):947–960. https://doi.org/10.1016/j. tree.2024.05.007, URL https://doi.org/10.1016/j.tree.2024.05.007

    work page doi:10.1016/j 2024

  41. [41]

    Trends in ecology & evolution 28(7):432–441

    K¨ uhl HS, Burghardt T (2013) Animal biometrics: quantifying and detecting phenotypic appearance. Trends in ecology & evolution 28(7):432–441

    2013

  42. [42]

    In: Proceedings of the 1st ACM international conference on multimedia retrieval, pp 1–8

    Lahiri M, Tantipathananandh C, Warungu R, et al (2011) Biometric animal databases from field photographs: identification of individual zebra in the wild. In: Proceedings of the 1st ACM international conference on multimedia retrieval, pp 1–8

    2011

  43. [43]

    Department of Conservation Technical Series A 28:5–32

    Lettink M, Armstrong DP (2003) An introduction to using mark-recapture analysis for monitoring threatened species. Department of Conservation Technical Series A 28:5–32

    2003

  44. [44]

    Journal of Ornithology 152(Suppl 2):355–370 17

    Lindberg MS (2012) A review of designs for capture–mark–recapture studies in discrete time. Journal of Ornithology 152(Suppl 2):355–370 17

    2012

  45. [45]

    Indian Ocean Turtle Newsletter 38:2–7

    Montagna M, Atalawi A, Algohane A, et al (2023) Combined photo identification and flipper tagging of green turtles identify connections between egyptian red sea feeding areas and a key nesting area in saudi arabia. Indian Ocean Turtle Newsletter 38:2–7

    2023

  46. [46]

    Muller Z, Bercovitch F, Brand R, et al (2018)Giraffa camelopardalis(amended ver- sion of 2016 assessment). Tech. rep., https://doi.org/10.2305/IUCN.UK.20163.RLTS. T9194A136266699.en

    work page doi:10.2305/iucn.uk.20163.rlts 2018

  47. [47]

    In: Proceedings of the 2024 ACM conference on fairness, accountability, and transparency, pp 1875–1884

    Orr W, Kang EB (2024) Ai as a sport: On the competitive epistemologies of bench- marking. In: Proceedings of the 2024 ACM conference on fairness, accountability, and transparency, pp 1875–1884

    2024

  48. [48]

    arXiv preprint arXiv:241205602

    Otarashvili L, Subramanian T, Holmberg J, et al (2024) Multispecies animal re-id using a large community-curated dataset. arXiv preprint arXiv:241205602

    2024

  49. [49]

    Ecology 89(2):542–554

    Ovaskainen O, Rekola H, Meyke E, et al (2008) Bayesian methods for analyzing move- ments in heterogeneous landscapes from mark–recapture data. Ecology 89(2):542–554

    2008

  50. [50]

    In: VISAPP (1), pp 403–410

    Palmer L, Burghardt T (2015) Contextual saliency for nonrigid landmark registration and recognition of natural patterns. In: VISAPP (1), pp 403–410

    2015

  51. [51]

    Animal Conservation 24(4):568–579

    Papafitsoros K, Panagopoulou A, Schofield G (2021) Social media reveals consis- tently disproportionate tourism pressure on a threatened marine vertebrate. Animal Conservation 24(4):568–579

    2021

  52. [52]

    In: European Conference on Computer Vision, Springer, pp 185–202

    Perez G, Sheldon D, Van Horn G, et al (2024) Human-in-the-loop visual re-id for population size estimation. In: European Conference on Computer Vision, Springer, pp 185–202

    2024

  53. [53]

    the tag loss problem

    Pfaller JB, Williams KL, Frick MG, et al (2019) Genetic determination of tag loss dynamics in nesting loggerhead turtles: a new chapter in “the tag loss problem”. Marine Biology 166(7):97

    2019

  54. [54]

    In: DAGM German Conference on Pattern Recognition, Springer, pp 241–257

    Picek L, Neumann L, Matas J (2024) Animal identification with independent foreground and background modeling. In: DAGM German Conference on Pattern Recognition, Springer, pp 241–257

    2024

  55. [55]

    Scientific Data

    Picek L, Straka J, Jirik M, et al (2026) Czechlynx: A dataset for individual identification and pose estimation of the eurasian lynx. Scientific Data

    2026

  56. [56]

    Computer Science Review 38:100289

    Ravoor PC, Sudarshan T (2020) Deep learning methods for multi-species animal re- identification and tracking–a survey. Computer Science Review 38:100289

    2020

  57. [57]

    Current Biology 35(7):1631–1640

    Recalde NM, Estand´ ıa A, Keen SC, et al (2025) The demographic drivers of cultural evolution in bird song. Current Biology 35(7):1631–1640

    2025

  58. [58]

    Animal Behaviour 83(5):1279–1283

    Rivera-Gutierrez HF, Pinxten R, Eens M (2012) Tuning and fading voices in songbirds: age-dependent changes in two acoustic traits across the life span. Animal Behaviour 83(5):1279–1283

    2012

  59. [59]

    Current Biology

    Rosenberg B, Zhou M, Wolf N, et al (2026) Individual identification of brown bears using pose-aware metric learning. Current Biology

    2026

  60. [60]

    https://doi

    Rubenstein D, Low Mackey B, Davidson ZD, et al (2016) Equus grevyi. https://doi. org/10.2305/IUCN.UK.2016-3.RLTS.T7950A89624491.en, URL https://dx.doi.org/10. 2305/IUCN.UK.2016-3.RLTS.T7950A89624491.en, assessment ID: e.T7950A89624491 18

    work page doi:10.2305/iucn.uk.2016-3.rlts.t7950a89624491.en 2016

  61. [61]

    Methods in Ecology and Evolution 10(4):461–470

    Schneider S, Taylor GW, Linquist S, et al (2019) Past, present and future approaches using computer vision for animal re-identification from camera trap data. Methods in Ecology and Evolution 10(4):461–470

    2019

  62. [62]

    Journal of experimental marine biology and ecology 360(2):103–108

    Schofield G, Katselidis KA, Dimopoulos P, et al (2008) Investigating the viability of photo-identification as an objective tool to study endangered sea turtle populations. Journal of experimental marine biology and ecology 360(2):103–108

    2008

  63. [63]

    Ecology 101(7):e03027

    Schofield G, Klaassen M, Papafitsoros K, et al (2020) Long-term photo-id and satel- lite tracking reveal sex-biased survival linked to movements in an endangered species. Ecology 101(7):e03027. https://doi.org/https://doi.org/10.1002/ecy.3027

    work page doi:10.1002/ecy.3027 2020

  64. [64]

    Animal Behaviour 190:209–219

    Schofield G, Papafitsoros K, Chapman C, et al (2022) More aggressive sea turtles win fights over foraging resources independent of body size and years of presence. Animal Behaviour 190:209–219

    2022

  65. [65]

    Biometrics pp 267–292

    Seber GA (1986) A review of estimating animal abundance. Biometrics pp 267–292

    1986

  66. [66]

    Frontiers in zoology 4(1):2

    Speed CW, Meekan MG, Bradshaw CJ (2007) Spot the match–wildlife photo- identification using information theory. Frontiers in zoology 4(1):2

    2007

  67. [67]

    arXiv preprint arXiv:210610377

    Stewart CV, Parham JR, Holmberg J, et al (2021) The animal id problem: continual curation. arXiv preprint arXiv:210610377

    2021

  68. [68]

    BioScience 69(1):15–25

    Sugai LSM, Silva TSF, Ribeiro Jr JW, et al (2019) Terrestrial passive acoustic monitoring: review and perspectives. BioScience 69(1):15–25

    2019

  69. [69]

    Trends in Ecology & Evolution 32(7):518–530

    Swan GJ, Redpath SM, Bearhop S, et al (2017) Ecology of problem individuals and the efficacy of selective wildlife management. Trends in Ecology & Evolution 32(7):518–530

    2017

  70. [70]

    Biological Conservation 233:298–315

    Toivonen T, Heikinheimo V, Fink C, et al (2019) Social media data for conservation science: A methodological overview. Biological Conservation 233:298–315

    2019

  71. [71]

    Ecology and evolution 3(7):1902– 1914

    Town C, Marshall A, Sethasathien N (2013) Manta matcher: automated photographic identification of manta rays using keypoint features. Ecology and evolution 3(7):1902– 1914

    2013

  72. [72]

    Journal of Experimental Marine Biology and Ecology 383(1):48–55

    Tucker AD (2010) Nest site fidelity and clutch frequency of loggerhead turtles are better elucidated by satellite telemetry than by nocturnal tagging efforts: implications for stock estimation. Journal of Experimental Marine Biology and Ecology 383(1):48–55

    2010

  73. [73]

    Nature communications 13(1):792

    Tuia D, Kellenberger B, Beery S, et al (2022) Perspectives in machine learning for wildlife conservation. Nature communications 13(1):792

    2022

  74. [74]

    Integrative and comparative biology 61(3):900–916

    Vidal M, Wolf N, Rosenberg B, et al (2021) Perspectives on individual animal iden- tification from biology and computer vision. Integrative and comparative biology 61(3):900–916

    2021

  75. [75]

    Scientific data 3(1):1–9

    Wilkinson MD, Dumontier M, Aalbersberg IJ, et al (2016) The fair guiding principles for scientific data management and stewardship. Scientific data 3(1):1–9

    2016

  76. [76]

    Academic Press, San Diego, CA 19

    Williams BK, Nichols JD, Conroy MJ (2002) Analysis and Management of Animal Populations: Modeling, Estimation and Decision Making. Academic Press, San Diego, CA 19

    2002

  77. [77]

    Ecology 90(1):3–9 20

    Yoshizaki J, Pollock KH, Brownie C, et al (2009) Modeling misidentification errors in capture–recapture studies using photographic identification of evolving marks. Ecology 90(1):3–9 20

    2009