DeepEthogram, a machine learning pipeline for supervised behavior classification from raw pixels

Videos of animal behavior are used to quantify researcher-defined behaviors of interest to study neural function, gene mutations, and pharmacological therapies. Behaviors of interest are often scored manually, which is time-consuming, limited to few behaviors, and variable across researchers. We cre...

Full description

Saved in:
Bibliographic Details
Published in:eLife Vol. 10
Main Authors: Bohnslav, James P, Wimalasena, Nivanthika K, Clausing, Kelsey J, Dai, Yu Y, Yarmolinsky, David A, Cruz, Tomás, Kashlan, Adam D, Chiappe, M Eugenia, Orefice, Lauren L, Woolf, Clifford J, Harvey, Christopher D
Format: Journal Article
Language:English
Published: England eLife Sciences Publications Ltd 02.09.2021
eLife Sciences Publications, Ltd
Subjects:
ISSN:2050-084X, 2050-084X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Videos of animal behavior are used to quantify researcher-defined behaviors of interest to study neural function, gene mutations, and pharmacological therapies. Behaviors of interest are often scored manually, which is time-consuming, limited to few behaviors, and variable across researchers. We created DeepEthogram: software that uses supervised machine learning to convert raw video pixels into an ethogram, the behaviors of interest present in each video frame. DeepEthogram is designed to be general-purpose and applicable across species, behaviors, and video-recording hardware. It uses convolutional neural networks to compute motion, extract features from motion and images, and classify features into behaviors. Behaviors are classified with above 90% accuracy on single frames in videos of mice and flies, matching expert-level human performance. DeepEthogram accurately predicts rare behaviors, requires little training data, and generalizes across subjects. A graphical interface allows beginning-to-end analysis without end-user programming. DeepEthogram’s rapid, automatic, and reproducible labeling of researcher-defined behaviors of interest may accelerate and enhance supervised behavior analysis. Code is available at: https://github.com/jbohnslav/deepethogram .
AbstractList Videos of animal behavior are used to quantify researcher-defined behaviors of interest to study neural function, gene mutations, and pharmacological therapies. Behaviors of interest are often scored manually, which is time-consuming, limited to few behaviors, and variable across researchers. We created DeepEthogram: software that uses supervised machine learning to convert raw video pixels into an ethogram, the behaviors of interest present in each video frame. DeepEthogram is designed to be general-purpose and applicable across species, behaviors, and video-recording hardware. It uses convolutional neural networks to compute motion, extract features from motion and images, and classify features into behaviors. Behaviors are classified with above 90% accuracy on single frames in videos of mice and flies, matching expert-level human performance. DeepEthogram accurately predicts rare behaviors, requires little training data, and generalizes across subjects. A graphical interface allows beginning-to-end analysis without end-user programming. DeepEthogram’s rapid, automatic, and reproducible labeling of researcher-defined behaviors of interest may accelerate and enhance supervised behavior analysis. Code is available at: https://github.com/jbohnslav/deepethogram.
Videos of animal behavior are used to quantify researcher-defined behaviors of interest to study neural function, gene mutations, and pharmacological therapies. Behaviors of interest are often scored manually, which is time-consuming, limited to few behaviors, and variable across researchers. We created DeepEthogram: software that uses supervised machine learning to convert raw video pixels into an ethogram, the behaviors of interest present in each video frame. DeepEthogram is designed to be general-purpose and applicable across species, behaviors, and video-recording hardware. It uses convolutional neural networks to compute motion, extract features from motion and images, and classify features into behaviors. Behaviors are classified with above 90% accuracy on single frames in videos of mice and flies, matching expert-level human performance. DeepEthogram accurately predicts rare behaviors, requires little training data, and generalizes across subjects. A graphical interface allows beginning-to-end analysis without end-user programming. DeepEthogram's rapid, automatic, and reproducible labeling of researcher-defined behaviors of interest may accelerate and enhance supervised behavior analysis. Code is available at: https://github.com/jbohnslav/deepethogram.Videos of animal behavior are used to quantify researcher-defined behaviors of interest to study neural function, gene mutations, and pharmacological therapies. Behaviors of interest are often scored manually, which is time-consuming, limited to few behaviors, and variable across researchers. We created DeepEthogram: software that uses supervised machine learning to convert raw video pixels into an ethogram, the behaviors of interest present in each video frame. DeepEthogram is designed to be general-purpose and applicable across species, behaviors, and video-recording hardware. It uses convolutional neural networks to compute motion, extract features from motion and images, and classify features into behaviors. Behaviors are classified with above 90% accuracy on single frames in videos of mice and flies, matching expert-level human performance. DeepEthogram accurately predicts rare behaviors, requires little training data, and generalizes across subjects. A graphical interface allows beginning-to-end analysis without end-user programming. DeepEthogram's rapid, automatic, and reproducible labeling of researcher-defined behaviors of interest may accelerate and enhance supervised behavior analysis. Code is available at: https://github.com/jbohnslav/deepethogram.
Videos of animal behavior are used to quantify researcher-defined behaviors of interest to study neural function, gene mutations, and pharmacological therapies. Behaviors of interest are often scored manually, which is time-consuming, limited to few behaviors, and variable across researchers. We created DeepEthogram: software that uses supervised machine learning to convert raw video pixels into an ethogram, the behaviors of interest present in each video frame. DeepEthogram is designed to be general-purpose and applicable across species, behaviors, and video-recording hardware. It uses convolutional neural networks to compute motion, extract features from motion and images, and classify features into behaviors. Behaviors are classified with above 90% accuracy on single frames in videos of mice and flies, matching expert-level human performance. DeepEthogram accurately predicts rare behaviors, requires little training data, and generalizes across subjects. A graphical interface allows beginning-to-end analysis without end-user programming. DeepEthogram’s rapid, automatic, and reproducible labeling of researcher-defined behaviors of interest may accelerate and enhance supervised behavior analysis. Code is available at: https://github.com/jbohnslav/deepethogram .
Author Wimalasena, Nivanthika K
Kashlan, Adam D
Dai, Yu Y
Yarmolinsky, David A
Clausing, Kelsey J
Orefice, Lauren L
Chiappe, M Eugenia
Bohnslav, James P
Cruz, Tomás
Woolf, Clifford J
Harvey, Christopher D
Author_xml – sequence: 1
  givenname: James P
  orcidid: 0000-0002-9359-8907
  surname: Bohnslav
  fullname: Bohnslav, James P
– sequence: 2
  givenname: Nivanthika K
  surname: Wimalasena
  fullname: Wimalasena, Nivanthika K
– sequence: 3
  givenname: Kelsey J
  surname: Clausing
  fullname: Clausing, Kelsey J
– sequence: 4
  givenname: Yu Y
  surname: Dai
  fullname: Dai, Yu Y
– sequence: 5
  givenname: David A
  surname: Yarmolinsky
  fullname: Yarmolinsky, David A
– sequence: 6
  givenname: Tomás
  surname: Cruz
  fullname: Cruz, Tomás
– sequence: 7
  givenname: Adam D
  surname: Kashlan
  fullname: Kashlan, Adam D
– sequence: 8
  givenname: M Eugenia
  orcidid: 0000-0003-1761-0457
  surname: Chiappe
  fullname: Chiappe, M Eugenia
– sequence: 9
  givenname: Lauren L
  surname: Orefice
  fullname: Orefice, Lauren L
– sequence: 10
  givenname: Clifford J
  surname: Woolf
  fullname: Woolf, Clifford J
– sequence: 11
  givenname: Christopher D
  orcidid: 0000-0001-9850-2268
  surname: Harvey
  fullname: Harvey, Christopher D
BackLink https://www.ncbi.nlm.nih.gov/pubmed/34473051$$D View this record in MEDLINE/PubMed
BookMark eNptkkFv1DAQhS1UREvpiTuKxAWpbLFjO3EuSKgtUGklLiBxMxNnvOuVEwc7WeDf490tVVsxF1vjb56eZ-Y5ORrCgIS8ZPSillK8w6WzeFFxXtdPyElJJV1QJb4f3bsfk7OUNjRHLZRizTNyzIWoOZXshPy4Qhyvp3VYRejfFlD0YNZuwMIjxMENq2J0I_pdxoZYpHnEuHUJu6LFNWxdzhkPKTnrDEwuDIWNoS8i_MqFv9GnF-SpBZ_w7PY8Jd8-Xn-9_LxYfvl0c_lhuTBSsGnRCo5oug4pWtV1EiRtK2a44jWjOSnzDWqrpEJrKgsZ5EJKLk2pRKcUPyU3B90uwEaP0fUQ_-gATu8TIa40xMkZj5qKhramBCVbEIozKHNjaNcCStG0dZm13h-0xrntsTM4TBH8A9GHL4Nb61XYapUtMb4z8-ZWIIafM6ZJ9y4Z9B4GDHPSpayUbLisZEZfP0I3YY5DblWmGlnmaHbUq_uO7qz8G2QGzg-AiSGliPYOYVTvNkXvN0XvNyXT7BFt3LQfX_6O8_-t-QvMRML0
CitedBy_id crossref_primary_10_1016_j_pnpbp_2025_111445
crossref_primary_10_1016_j_neuron_2022_04_030
crossref_primary_10_1016_j_isci_2024_111223
crossref_primary_10_3390_ani12131648
crossref_primary_10_1186_s40462_024_00511_8
crossref_primary_10_1111_eth_13514
crossref_primary_10_3389_fnmol_2024_1429880
crossref_primary_10_1007_s11263_025_02493_5
crossref_primary_10_1007_s11263_024_02072_0
crossref_primary_10_3390_ani14020281
crossref_primary_10_1016_j_crmeth_2025_101050
crossref_primary_10_1016_j_jneumeth_2024_110111
crossref_primary_10_1111_1365_2656_13904
crossref_primary_10_1111_1365_2656_13826
crossref_primary_10_1111_2041_210X_14403
crossref_primary_10_1016_j_neures_2024_04_002
crossref_primary_10_7554_eLife_74314
crossref_primary_10_1007_s13042_025_02602_3
crossref_primary_10_1038_s42003_024_05864_9
crossref_primary_10_1038_s41593_023_01332_5
crossref_primary_10_1097_j_pain_0000000000002680
crossref_primary_10_1098_rsos_230700
crossref_primary_10_1016_j_crmeth_2023_100650
crossref_primary_10_1016_j_crmeth_2025_101108
crossref_primary_10_1186_s12915_023_01751_7
crossref_primary_10_1038_s41467_024_55317_4
crossref_primary_10_1038_s41592_025_02653_y
crossref_primary_10_1038_s42003_022_04080_7
crossref_primary_10_1111_2041_210X_14170
crossref_primary_10_1134_S0022093024030219
crossref_primary_10_1371_journal_pcbi_1012990
crossref_primary_10_1016_j_crmeth_2023_100415
crossref_primary_10_1016_j_conb_2022_102544
crossref_primary_10_1038_s41592_024_02200_1
crossref_primary_10_1002_eat_23752
crossref_primary_10_1016_j_nlm_2023_107833
crossref_primary_10_1038_s41592_024_02318_2
crossref_primary_10_1038_s41467_023_41261_2
crossref_primary_10_1038_s41598_023_31094_w
crossref_primary_10_1172_JCI191346
crossref_primary_10_7554_eLife_84042
crossref_primary_10_1002_dneu_22912
crossref_primary_10_1007_s11263_022_01713_6
crossref_primary_10_1038_s41596_024_01015_w
crossref_primary_10_1111_2041_210X_70128
crossref_primary_10_1038_s42256_022_00477_5
crossref_primary_10_1038_s41598_025_05712_8
crossref_primary_10_1109_TIM_2025_3551854
crossref_primary_10_1007_s10329_024_01123_x
crossref_primary_10_1371_journal_pone_0326916
crossref_primary_10_7554_eLife_86873
crossref_primary_10_3389_fnmol_2023_1155754
crossref_primary_10_1111_2041_210X_14502
crossref_primary_10_1016_j_neubiorev_2022_104621
crossref_primary_10_1016_j_cell_2024_11_001
crossref_primary_10_1016_j_isci_2024_109998
crossref_primary_10_1016_j_neurobiolaging_2023_02_009
crossref_primary_10_1248_bpb_b25_00116
crossref_primary_10_1038_s41467_025_61949_x
crossref_primary_10_1093_molehr_gaaf023
crossref_primary_10_1016_j_neuron_2022_04_008
crossref_primary_10_1016_j_ecoinf_2024_102840
crossref_primary_10_3389_fphar_2024_1396454
crossref_primary_10_1523_ENEURO_0369_24_2025
crossref_primary_10_1016_j_neuroscience_2023_08_023
crossref_primary_10_1038_s41684_025_01561_0
crossref_primary_10_3390_bioengineering11111121
crossref_primary_10_1038_s41598_023_29574_0
crossref_primary_10_3390_jimaging8040109
crossref_primary_10_1038_s41586_024_07816_z
crossref_primary_10_1002_zoo_70008
crossref_primary_10_1038_s41593_024_01649_9
crossref_primary_10_7554_eLife_86873_3
crossref_primary_10_1016_j_eswa_2025_128330
crossref_primary_10_1111_2041_210X_70124
Cites_doi 10.1126/science.abb2751
10.1038/nn.3812
10.1371/journal.pbio.3000516
10.7554/eLife.47994
10.1038/s41593-018-0209-y
10.1016/j.neuron.2016.12.041
10.1038/s41593-020-00706-3
10.1016/j.celrep.2017.06.024
10.1038/s41386-020-0776-y
10.1016/j.cell.2016.05.033
10.1016/j.neuron.2014.09.005
10.1016/j.neuron.2015.11.031
10.1038/s41551-019-0396-1
10.1111/2041-210X.12584
10.1038/s41586-019-1869-9
10.5281/zenodo.2526396
10.1101/2020.07.26.222299
10.5281/zenodo.592536
10.1109/CVPR.2018.00685
10.1146/annurev-neuro-070815-013845
10.1038/nmeth.2281
10.1038/nmeth.1310
10.1016/j.jneumeth.2019.108536
10.1109/tip.2003.819861
10.1101/2021.04.30.442096v1
10.1016/j.cell.2019.07.024
10.1038/nmeth.2019
10.1038/nn.4435
10.1038/s41596-019-0176-0
10.1038/s41598-019-56408-9
10.1098/rsif.2014.0672
10.1109/CVPR.2009.5206848
10.1016/j.neuron.2019.09.038
10.1101/2020.04.19.049452
10.1101/220855
10.1101/2020.10.26.355115
10.1038/nature09965
10.1101/770271
10.1101/331181
ContentType Journal Article
Copyright 2021, Bohnslav et al.
2021, Bohnslav et al. This work is published under https://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
2021, Bohnslav et al 2021 Bohnslav et al
Copyright_xml – notice: 2021, Bohnslav et al.
– notice: 2021, Bohnslav et al. This work is published under https://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
– notice: 2021, Bohnslav et al 2021 Bohnslav et al
DBID AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
3V.
7X7
7XB
88E
88I
8FE
8FH
8FI
8FJ
8FK
ABUWG
AFKRA
AZQEC
BBNVY
BENPR
BHPHI
CCPQU
DWQXO
FYUFA
GHDGH
GNUQQ
HCIFZ
K9.
LK8
M0S
M1P
M2P
M7P
PHGZM
PHGZT
PIMPY
PJZUB
PKEHL
PPXIY
PQEST
PQGLB
PQQKQ
PQUKI
PRINS
Q9U
7X8
5PM
DOA
DOI 10.7554/eLife.63377
DatabaseName CrossRef
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
ProQuest Central (Corporate)
Health & Medical Collection
ProQuest Central (purchase pre-March 2016)
Medical Database (Alumni Edition)
Science Database (Alumni Edition)
ProQuest SciTech Collection
ProQuest Natural Science Collection
Hospital Premium Collection
Hospital Premium Collection (Alumni Edition)
ProQuest Central (Alumni) (purchase pre-March 2016)
ProQuest Central (Alumni)
ProQuest Central UK/Ireland
ProQuest Central Essentials
Biological Science Collection
ProQuest Central (subscription)
Natural Science Collection
ProQuest One
ProQuest Central
Health Research Premium Collection
Health Research Premium Collection (Alumni)
ProQuest Central Student
SciTech Premium Collection
ProQuest Health & Medical Complete (Alumni)
ProQuest Biological Science Collection
Health & Medical Collection (Alumni Edition)
PML(ProQuest Medical Library)
Science Database (ProQuest)
Biological Science Database
ProQuest Central Premium
ProQuest One Academic
ProQuest Publicly Available Content
ProQuest Health & Medical Research Collection
ProQuest One Academic Middle East (New)
ProQuest One Health & Nursing
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Applied & Life Sciences
ProQuest One Academic (retired)
ProQuest One Academic UKI Edition
ProQuest Central China
ProQuest Central Basic
MEDLINE - Academic
PubMed Central (Full Participant titles)
DOAJ Open Access Full Text
DatabaseTitle CrossRef
MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
Publicly Available Content Database
ProQuest Central Student
ProQuest One Academic Middle East (New)
ProQuest Central Essentials
ProQuest Health & Medical Complete (Alumni)
ProQuest Central (Alumni Edition)
SciTech Premium Collection
ProQuest One Community College
ProQuest One Health & Nursing
ProQuest Natural Science Collection
ProQuest Central China
ProQuest Central
ProQuest One Applied & Life Sciences
ProQuest Health & Medical Research Collection
Health Research Premium Collection
Health and Medicine Complete (Alumni Edition)
Natural Science Collection
ProQuest Central Korea
Health & Medical Research Collection
Biological Science Collection
ProQuest Central (New)
ProQuest Medical Library (Alumni)
ProQuest Science Journals (Alumni Edition)
ProQuest Biological Science Collection
ProQuest Central Basic
ProQuest Science Journals
ProQuest One Academic Eastern Edition
ProQuest Hospital Collection
Health Research Premium Collection (Alumni)
Biological Science Database
ProQuest SciTech Collection
ProQuest Hospital Collection (Alumni)
ProQuest Health & Medical Complete
ProQuest Medical Library
ProQuest One Academic UKI Edition
ProQuest One Academic
ProQuest One Academic (New)
ProQuest Central (Alumni)
MEDLINE - Academic
DatabaseTitleList
MEDLINE - Academic
Publicly Available Content Database
MEDLINE

CrossRef
Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Open Access Full Text
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 3
  dbid: PIMPY
  name: ProQuest Publicly Available Content
  url: http://search.proquest.com/publiccontent
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Biology
EISSN 2050-084X
ExternalDocumentID oai_doaj_org_article_0490bc2a85ba4831a27480dbae549b72
PMC8455138
34473051
10_7554_eLife_63377
Genre Video-Audio Media
Research Support, U.S. Gov't, Non-P.H.S
Research Support, Non-U.S. Gov't
Journal Article
Research Support, N.I.H., Extramural
GrantInformation_xml – fundername: NICHD NIH HHS
  grantid: P50 HD105351
– fundername: NIMH NIH HHS
  grantid: DP1 MH125776
– fundername: NINDS NIH HHS
  grantid: F31 NS108450
– fundername: NCCIH NIH HHS
  grantid: R01 AT011447
– fundername: NINDS NIH HHS
  grantid: R01 NS108410
– fundername: NIDCR NIH HHS
  grantid: K99 DE028360
– fundername: NINDS NIH HHS
  grantid: R35 NS105076
– fundername: NINDS NIH HHS
  grantid: R01 NS089521
– fundername: NINDS NIH HHS
  grantid: R00 NS101057
– fundername: NIMH NIH HHS
  grantid: R01 MH107620
– fundername: ;
  grantid: R01NS108410
– fundername: ;
  grantid: Goldenson Research Award
– fundername: ;
  grantid: R01NS089521
– fundername: ;
  grantid: DP1 MH125776
– fundername: ;
  grantid: GRFP
– fundername: ;
  grantid: ERC-Stg-759782
– fundername: ;
  grantid: R01AT011447
– fundername: ;
  grantid: R00NS101057
– fundername: ;
  grantid: R01MH107620
– fundername: ;
  grantid: K99DE028360
GroupedDBID 53G
5VS
7X7
88E
88I
8FE
8FH
8FI
8FJ
AAFWJ
AAKDD
AAYXX
ABUWG
ACGFO
ACGOD
ACPRK
ADBBV
ADRAZ
AENEX
AFFHD
AFKRA
AFPKN
ALMA_UNASSIGNED_HOLDINGS
AOIJS
AZQEC
BAWUL
BBNVY
BCNDV
BENPR
BHPHI
BPHCQ
BVXVI
CCPQU
CITATION
DIK
DWQXO
EMOBN
FYUFA
GNUQQ
GROUPED_DOAJ
GX1
HCIFZ
HMCUK
HYE
IAO
IEA
IHR
INH
INR
ISR
ITC
KQ8
LK8
M1P
M2P
M48
M7P
M~E
NQS
OK1
PGMZT
PHGZM
PHGZT
PIMPY
PJZUB
PPXIY
PQGLB
PQQKQ
PROAC
PSQYO
RHI
RNS
RPM
UKHRP
ALIPV
CGR
CUY
CVF
ECM
EIF
NPM
3V.
7XB
8FK
K9.
PKEHL
PQEST
PQUKI
PRINS
Q9U
7X8
PUEGO
5PM
ID FETCH-LOGICAL-c541t-b43eecdde0ef8dd5a50b61c383710e0e5383a7f858efc6fade0345535c284d883
IEDL.DBID DOA
ISICitedReferencesCount 109
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000700445800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2050-084X
IngestDate Fri Oct 03 12:50:52 EDT 2025
Tue Nov 04 02:01:01 EST 2025
Fri Sep 05 07:51:32 EDT 2025
Tue Oct 07 07:17:05 EDT 2025
Thu Apr 03 07:00:33 EDT 2025
Tue Nov 18 21:39:31 EST 2025
Sat Nov 29 06:24:22 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords deep learning
mouse
D. melanogaster
neuroscience
behavior analysis
computer vision
Language English
License 2021, Bohnslav et al.
This article is distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use and redistribution provided that the original author and source are credited.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c541t-b43eecdde0ef8dd5a50b61c383710e0e5383a7f858efc6fade0345535c284d883
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ObjectType-Undefined-3
ORCID 0000-0003-1761-0457
0000-0002-9359-8907
0000-0001-9850-2268
OpenAccessLink https://doaj.org/article/0490bc2a85ba4831a27480dbae549b72
PMID 34473051
PQID 2595222295
PQPubID 2045579
ParticipantIDs doaj_primary_oai_doaj_org_article_0490bc2a85ba4831a27480dbae549b72
pubmedcentral_primary_oai_pubmedcentral_nih_gov_8455138
proquest_miscellaneous_2568593565
proquest_journals_2595222295
pubmed_primary_34473051
crossref_primary_10_7554_eLife_63377
crossref_citationtrail_10_7554_eLife_63377
PublicationCentury 2000
PublicationDate 2021-09-02
PublicationDateYYYYMMDD 2021-09-02
PublicationDate_xml – month: 09
  year: 2021
  text: 2021-09-02
  day: 02
PublicationDecade 2020
PublicationPlace England
PublicationPlace_xml – name: England
– name: Cambridge
PublicationTitle eLife
PublicationTitleAlternate Elife
PublicationYear 2021
Publisher eLife Sciences Publications Ltd
eLife Sciences Publications, Ltd
Publisher_xml – name: eLife Sciences Publications Ltd
– name: eLife Sciences Publications, Ltd
References Liaw (bib40) 2018
Pereira (bib57) 2018
Brown (bib6) 2017
Carreira (bib8) 2017
van Dam (bib70) 2020; 332
Lauer (bib37) 2021
Batty (bib2) 2019
Bradski (bib5) 2008
Sauerbrei (bib64) 2020; 577
Gomez-Marin (bib23) 2014; 17
Lukas von (bib42) 2021
Pedregosa (bib55) 2021
Piergiovanni (bib59) 2018
Pereira (bib58) 2018; 16
He (bib26) 2015
Nath (bib47) 2019; 14
Mathis (bib44) 2018; 21
Anderson (bib1) 2014; 84
Ronneberger (bib61) 2015
Feichtenhofer (bib20) 2019
Marks (bib43) 2020
Wang (bib71) 2004; 13
Nilsson (bib50) 2020
Falcon (bib18) 2019
Li (bib38) 2018
Berman (bib3) 2014; 11
Zhu (bib77) 2017
Srivastava (bib68) 2014; 15
Kwak (bib36) 2019
Sturman (bib69) 2020; 45
Bohnslav (bib4) 2021
Neubarth (bib49) 2020; 368
Zeng (bib76) 2019
Ryait (bib63) 2019; 17
Friard (bib21) 2016; 7
Orefice (bib51) 2016; 166
Rossum (bib62) 2010
Pennington (bib56) 2019; 9
Graving (bib24) 2019; 8
Kingma (bib33) 2017
Dankert (bib12) 2009; 6
Egnor (bib16) 2016; 39
de Chaumont (bib14) 2019; 3
Hsu (bib28) 2019
Carreira (bib9) 2019
Jaderberg (bib30) 2015
Nawhal (bib48) 2021
Riba (bib60) 2019
Kahatapitiya (bib32) 2021
Segalin (bib66) 2020
Xie (bib75) 2019
Feichtenhofer (bib19) 2016
Schindelin (bib65) 2012; 9
El-Nouby (bib17) 2018
Browne (bib7) 2017; 20
Deng (bib15) 2008
Kocaman (bib34) 2020
Paszke (bib53) 2018
Krakauer (bib35) 2017; 93
Hinton (bib27) 2012
Lin (bib41) 2018
Li (bib39) 2020
Peça (bib54) 2011; 472
Monfort (bib45) 2020
Wang (bib72) 2015
Caswell (bib10) 2021
Wiltschko (bib74) 2020; 23
Fujiwara (bib22) 2017; 20
Simonyan (bib67) 2014
Datta (bib13) 2019; 104
Müller (bib46) 2019
Orefice (bib52) 2019; 178
Kabra (bib31) 2013; 10
Hara (bib25) 2018; 10
Wiltschko (bib73) 2015; 88
Chao (bib11) 2018
Iqbal (bib29) 2018
References_xml – volume: 368
  year: 2020
  ident: bib49
  article-title: Meissner corpuscles and their spatially intermingled afferents underlie gentle touch perception
  publication-title: Science
  doi: 10.1126/science.abb2751
– year: 2017
  ident: bib8
  article-title: IEEE conference on computer vision and pattern recognition
– volume: 17
  start-page: 1455
  year: 2014
  ident: bib23
  article-title: Big behavioral data: Psychology, ethology and the foundations of neuroscience
  publication-title: Nature Neuroscience
  doi: 10.1038/nn.3812
– volume-title: arXiv
  year: 2018
  ident: bib38
  article-title: Explicit Inductive Bias for Transfer Learning with Convolutional Networks
– volume: 17
  year: 2019
  ident: bib63
  article-title: Data-driven analyses of motor impairments in animal models of neurological disorders
  publication-title: PLOS Biology
  doi: 10.1371/journal.pbio.3000516
– volume-title: Leap Estimates Animal Pose
  year: 2018
  ident: bib57
– volume-title: arXiv
  year: 2017
  ident: bib33
  article-title: Adam
– volume-title: arXiv
  year: 2015
  ident: bib61
  article-title: U-Net: Convolutional Networks for Biomedical Image Segmentation
– volume-title: Software Heritage
  year: 2021
  ident: bib4
  article-title: Deepethogram
– volume-title: arXiv
  year: 2015
  ident: bib72
  article-title: Towards Good Practices for Very Deep Two-Stream ConvNets
– volume: 8
  year: 2019
  ident: bib24
  article-title: DeepPoseKit, a software toolkit for fast and robust animal pose estimation using deep learning
  publication-title: eLife
  doi: 10.7554/eLife.47994
– volume-title: arXiv
  year: 2015
  ident: bib26
  article-title: Deep Residual Learning for Image Recognition
– volume: 21
  start-page: 1281
  year: 2018
  ident: bib44
  article-title: DeepLabCut: markerless pose estimation of user-defined body parts with deep learning
  publication-title: Nature Neuroscience
  doi: 10.1038/s41593-018-0209-y
– volume-title: arXiv
  year: 2014
  ident: bib67
  article-title: Two-Stream Convolutional Networks for Action Recognition in Videos
– volume-title: arXiv
  year: 2021
  ident: bib48
  article-title: Activity Graph Transformer for Temporal Action Localization
– volume-title: arXiv
  year: 2019
  ident: bib60
  article-title: Kornia: An Open Source Differentiable Computer Vision Library for PyTorch
– volume: 93
  start-page: 480
  year: 2017
  ident: bib35
  article-title: Neuroscience needs behavior: Correcting a reductionist bias
  publication-title: Neuron
  doi: 10.1016/j.neuron.2016.12.041
– volume: 23
  start-page: 1433
  year: 2020
  ident: bib74
  article-title: Revealing the structure of pharmacobehavioral space through motion sequencing
  publication-title: Nature Neuroscience
  doi: 10.1038/s41593-020-00706-3
– volume-title: Github
  year: 2021
  ident: bib42
  article-title: DLC analyzer
– volume: 20
  start-page: 89
  year: 2017
  ident: bib7
  article-title: Time-Resolved Fast Mammalian Behavior Reveals the Complexity of Protective Pain Responses
  publication-title: Cell Reports
  doi: 10.1016/j.celrep.2017.06.024
– volume: 45
  start-page: 1942
  year: 2020
  ident: bib69
  article-title: Deep learning-based behavioral analysis reaches human accuracy and is capable of outperforming commercial solutions
  publication-title: Neuropsychopharmacology
  doi: 10.1038/s41386-020-0776-y
– volume-title: Open Source Computer Vision Library
  year: 2008
  ident: bib5
– year: 2019
  ident: bib2
  article-title: Openreview
– volume: 166
  start-page: 299
  year: 2016
  ident: bib51
  article-title: Peripheral Mechanosensory Neuron Dysfunction Underlies Tactile and Behavioral Deficits in Mouse Models of ASDs
  publication-title: Cell
  doi: 10.1016/j.cell.2016.05.033
– volume-title: arXiv
  year: 2019
  ident: bib36
  article-title: Detecting the Starting Frame of Actions in Video
– volume-title: arXiv
  year: 2018
  ident: bib40
  article-title: Tune
– volume: 84
  start-page: 18
  year: 2014
  ident: bib1
  article-title: Toward a Science of Computational Ethology
  publication-title: Neuron
  doi: 10.1016/j.neuron.2014.09.005
– volume: 88
  start-page: 1121
  year: 2015
  ident: bib73
  article-title: Mapping Sub-Second Structure in Mouse Behavior
  publication-title: Neuron
  doi: 10.1016/j.neuron.2015.11.031
– volume: 3
  start-page: 930
  year: 2019
  ident: bib14
  article-title: Real-time analysis of the behaviour of groups of mice via a depth-sensing camera and machine learning
  publication-title: Nature Biomedical Engineering
  doi: 10.1038/s41551-019-0396-1
– volume: 7
  start-page: 1325
  year: 2016
  ident: bib21
  article-title: BORIS : a free, versatile open‐source event‐logging software for video/audio coding and live observations
  publication-title: Methods in Ecology and Evolution
  doi: 10.1111/2041-210X.12584
– volume: 577
  start-page: 386
  year: 2020
  ident: bib64
  article-title: Cortical pattern generation during dexterous movement is input-driven
  publication-title: Nature
  doi: 10.1038/s41586-019-1869-9
– volume-title: Zenodo
  year: 2018
  ident: bib29
  article-title: Harisiqbal88/plotneuralnet
  doi: 10.5281/zenodo.2526396
– volume-title: Python Software Foundation
  year: 2010
  ident: bib62
  article-title: The Python language reference
– volume-title: bioRxiv
  year: 2020
  ident: bib66
  article-title: The Mouse Action Recognition System (MARS): A Software Pipeline for Automated Analysis of Social Behaviors in Mice
  doi: 10.1101/2020.07.26.222299
– volume-title: Zenodo
  year: 2021
  ident: bib10
  article-title: Matplotlib/matplotlib: REL
  doi: 10.5281/zenodo.592536
– volume: 10
  year: 2018
  ident: bib25
  article-title: Can spatiotemporal 3D CNNS retrace the history of 2D
  publication-title: CNNs and ImageNet
  doi: 10.1109/CVPR.2018.00685
– volume-title: arXiv
  year: 2018
  ident: bib11
  article-title: Rethinking the Faster R-CNN Architecture for Temporal Action Localization
– volume: 39
  start-page: 217
  year: 2016
  ident: bib16
  article-title: Computational analysis of behavior
  publication-title: Annual Review of Neuroscience
  doi: 10.1146/annurev-neuro-070815-013845
– volume: 10
  start-page: 64
  year: 2013
  ident: bib31
  article-title: JAABA: Interactive machine learning for automatic annotation of animal behavior
  publication-title: Nature Methods
  doi: 10.1038/nmeth.2281
– volume-title: arXiv
  year: 2018
  ident: bib17
  article-title: Real-Time End-to-End Action Detection with Two-Stream Networks
– volume-title: arXiv
  year: 2021
  ident: bib32
  article-title: Coarse-Fine Networks for Temporal Activity Detection in Videos
– volume: 6
  start-page: 297
  year: 2009
  ident: bib12
  article-title: Automated monitoring and analysis of social behavior in Drosophila
  publication-title: Nature Methods
  doi: 10.1038/nmeth.1310
– volume-title: Github
  year: 2019
  ident: bib18
  article-title: Pytorch lightning
– volume: 332
  year: 2020
  ident: bib70
  article-title: Deep learning improves automated rodent behavior recognition within a specific experimental setup
  publication-title: Journal of Neuroscience Methods
  doi: 10.1016/j.jneumeth.2019.108536
– volume-title: arXiv
  year: 2020
  ident: bib34
  article-title: Improving Model Accuracy for Imbalanced Image Classification Tasks by Adding a Final Batch Normalization Layer
– volume: 13
  start-page: 600
  year: 2004
  ident: bib71
  article-title: Image Quality Assessment: From Error Visibility to Structural Similarity
  publication-title: IEEE Transactions on Image Processing
  doi: 10.1109/tip.2003.819861
– volume-title: arXiv
  year: 2018
  ident: bib53
  article-title: Pytorch: An Imperative Style, High-Performance Deep Learning Library
– volume-title: bioRxiv
  year: 2021
  ident: bib37
  article-title: Multi-Animal Pose Estimation and Tracking with Deeplabcut
  doi: 10.1101/2021.04.30.442096v1
– volume-title: arXiv
  year: 2020
  ident: bib45
  article-title: Multi-Moments in Time
– volume: 178
  start-page: 867
  year: 2019
  ident: bib52
  article-title: Targeting Peripheral Somatosensory Neurons to Improve Tactile-Related Phenotypes in ASD Models
  publication-title: Cell
  doi: 10.1016/j.cell.2019.07.024
– volume: 9
  start-page: 676
  year: 2012
  ident: bib65
  article-title: Fiji: an open-source platform for biological-image analysis
  publication-title: Nature Methods
  doi: 10.1038/nmeth.2019
– volume: 20
  start-page: 72
  year: 2017
  ident: bib22
  article-title: A faithful internal representation of walking movements in the Drosophila visual system
  publication-title: Nature Neuroscience
  doi: 10.1038/nn.4435
– volume-title: arXiv
  year: 2016
  ident: bib19
  article-title: Convolutional Two-Stream Network Fusion for Video Action Recognition
– volume-title: Mach. Learn. Python
  year: 2021
  ident: bib55
  article-title: Scikit-learn: Machine learning in Python
– volume-title: arXiv
  year: 2019
  ident: bib75
  article-title: Exploring Feature Representation and Training Strategies in Temporal Action Localization
– volume-title: arXiv
  year: 2019
  ident: bib20
  article-title: SlowFast Networks for Video Recognition
– volume: 14
  start-page: 2152
  year: 2019
  ident: bib47
  article-title: Using DeepLabCut for 3D markerless pose estimation across species and behaviors
  publication-title: Nature Protocols
  doi: 10.1038/s41596-019-0176-0
– volume: 9
  year: 2019
  ident: bib56
  article-title: ezTrack: An open-source video analysis pipeline for the investigation of animal behavior
  publication-title: Scientific Reports
  doi: 10.1038/s41598-019-56408-9
– volume: 15
  start-page: 1929
  year: 2014
  ident: bib68
  article-title: Dropout: A Simple Way to Prevent Neural Networks from Overfitting
  publication-title: Journal of Machine Learning Research
– volume: 11
  year: 2014
  ident: bib3
  article-title: Mapping the stereotyped behaviour of freely moving fruit flies
  publication-title: Journal of the Royal Society, Interface
  doi: 10.1098/rsif.2014.0672
– year: 2008
  ident: bib15
  article-title: IEEE Conference
  doi: 10.1109/CVPR.2009.5206848
– volume: 104
  start-page: 11
  year: 2019
  ident: bib13
  article-title: Computational Neuroethology: A Call to Action
  publication-title: Neuron
  doi: 10.1016/j.neuron.2019.09.038
– volume-title: arXiv
  year: 2017
  ident: bib77
  article-title: Hidden Two-Stream Convolutional Networks for Action Recognition
– volume-title: arXiv
  year: 2012
  ident: bib27
  article-title: Improving Neural Networks by Preventing Co-Adaptation of Feature Detectors
– volume-title: bioRxiv
  year: 2020
  ident: bib50
  article-title: Simple Behavioral Analysis (SIMBA) – an Open Source Toolkit for Computer Classification of Complex Social Behaviors in Experimental Animals
  doi: 10.1101/2020.04.19.049452
– volume-title: bioRxiv
  year: 2017
  ident: bib6
  article-title: Ethology as a Physical Science
  doi: 10.1101/220855
– volume-title: arXiv
  year: 2019
  ident: bib76
  article-title: Graph Convolutional Networks for Temporal Action Localization
– volume-title: arXiv
  year: 2020
  ident: bib39
  article-title: A System for Massively Parallel Hyperparameter Tuning
– volume-title: bioRxiv
  year: 2020
  ident: bib43
  article-title: SIPEC: The Deep-Learning Swiss Knife for Behavioral Data Analysis
  doi: 10.1101/2020.10.26.355115
– volume: 472
  start-page: 437
  year: 2011
  ident: bib54
  article-title: Shank3 mutant mice display autistic-like behaviours and striatal dysfunction
  publication-title: Nature
  doi: 10.1038/nature09965
– volume-title: arXiv
  year: 2018
  ident: bib41
  article-title: Focal Loss for Dense Object Detection
– volume-title: arXiv
  year: 2019
  ident: bib46
  article-title: When Does Label Smoothing Help?
– volume-title: arXiv
  year: 2018
  ident: bib59
  article-title: Temporal Gaussian Mixture Layer for Videos
– volume-title: arXiv
  year: 2019
  ident: bib9
  article-title: A Short Note on the Kinetics-700 Human Action Dataset
– volume-title: bioRxiv
  year: 2019
  ident: bib28
  article-title: B-SOID: An Open Source Unsupervised Algorithm for Discovery of Spontaneous Behaviors
  doi: 10.1101/770271
– volume-title: arXiv
  year: 2015
  ident: bib30
  article-title: Spatial Transformer Networks
– volume: 16
  start-page: 117
  year: 2018
  ident: bib58
  article-title: Fast Animal Pose Estimation Using Deep Neural Networks
  publication-title: Nature
  doi: 10.1101/331181
SSID ssj0000748819
Score 2.6112082
Snippet Videos of animal behavior are used to quantify researcher-defined behaviors of interest to study neural function, gene mutations, and pharmacological...
SourceID doaj
pubmedcentral
proquest
pubmed
crossref
SourceType Open Website
Open Access Repository
Aggregation Database
Index Database
Enrichment Source
SubjectTerms Animal behavior
Animals
behavior analysis
Biomedical research
Classification
computer vision
Datasets
deep learning
Drosophila melanogaster
Female
Grooming
Humans
Image Processing, Computer-Assisted
Kinetics
Learning algorithms
Machine learning
Male
Mars
Mice
Mice, Inbred C57BL
Motor Activity
Neural networks
Neural Networks, Computer
Neuroscience
Pattern Recognition, Automated
Reproducibility of Results
Researchers
Social Behavior
Software
Supervised Machine Learning
Tools and Resources
Walking
SummonAdditionalLinks – databaseName: Health & Medical Collection
  dbid: 7X7
  link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lb9QwEB5BAamX8i6BgozUEyI0Wduxc0I8WnGoKg6A9hYc22lXotl0s0vh3zPjeAOLKi5c44lk6fO87Jn5APaFapqCNzqtRalT9BCoUk6WaZ2rrKxVactQbfHlWJ2c6Om0_Bgv3PpYVrm2icFQu7mlO_IDDNMxVCDy6dfdRUqsUfS6Gik0rsMNos2mc66marxjQfeo0eMNbXkKHeeBP541_lXBuVIbjijM678qyPy7VvIP53N0-3-3fQd2YtjJ3gzn5C5c8-09uDUQUf68D1_fe98dLs9CrdZLZth5qLH0LJJKnLJu1lHnumcY5LJ-1ZGJ6b1j6zZ_ZikMp7qjADWjthW2MJf44w90vw_g89Hhp3cf0si9kFop8iVCx723aPsy32jnpJFZXeSW8tk8w49oJ7lRjZbaN7ZoDApyISWXFv2d05o_hK123vpHwDiGkHmphZCuFo5LzLmtx6xJWOty5XUCL9ZAVDYOJid-jG8VJiiEWhVQqwJqCeyPwt0wj-NqsbeE6ChCQ7TDh_nitIo6WdGjZ20nRsvaCM1zgxm6zlxtPCbNtZoksLfGtIqa3Ve_AU3g-biMOkkPLab18xXJFDRGDmPlBHaH4zPuhCYsoo3NE1AbB2tjq5sr7ewszP3Wgth49ON_b-sJbE-o7oYevSZ7sLVcrPxTuGm_L2f94llQkF9SPx0h
  priority: 102
  providerName: ProQuest
Title DeepEthogram, a machine learning pipeline for supervised behavior classification from raw pixels
URI https://www.ncbi.nlm.nih.gov/pubmed/34473051
https://www.proquest.com/docview/2595222295
https://www.proquest.com/docview/2568593565
https://pubmed.ncbi.nlm.nih.gov/PMC8455138
https://doaj.org/article/0490bc2a85ba4831a27480dbae549b72
Volume 10
WOSCitedRecordID wos000700445800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Open Access Full Text
  customDbUrl:
  eissn: 2050-084X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000748819
  issn: 2050-084X
  databaseCode: DOA
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2050-084X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000748819
  issn: 2050-084X
  databaseCode: M~E
  dateStart: 20120101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
– providerCode: PRVPQU
  databaseName: Biological Science Database
  customDbUrl:
  eissn: 2050-084X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000748819
  issn: 2050-084X
  databaseCode: M7P
  dateStart: 20120101
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/biologicalscijournals
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Health & Medical Collection
  customDbUrl:
  eissn: 2050-084X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000748819
  issn: 2050-084X
  databaseCode: 7X7
  dateStart: 20120101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/healthcomplete
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 2050-084X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000748819
  issn: 2050-084X
  databaseCode: BENPR
  dateStart: 20120101
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Publicly Available Content
  customDbUrl:
  eissn: 2050-084X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000748819
  issn: 2050-084X
  databaseCode: PIMPY
  dateStart: 20120101
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/publiccontent
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Science Database
  customDbUrl:
  eissn: 2050-084X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000748819
  issn: 2050-084X
  databaseCode: M2P
  dateStart: 20120101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/sciencejournals
  providerName: ProQuest
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrR3LbtQwcAQtSFxQeZVAWRmpJ0RosrZj59iWrUBqVxECtJyCYzt0JUijffD4-8442dUuqsSFiw_2RHLmPfI8AA6FquuM1zquRK5jtBAoUk7mcZWqJK9UbvOQbfH5XI3HejLJi41RX5QT1rUH7hB3RC9TlR0aLSsjNE8NhlE6cZXxGNlUKmjfROUbwVTQwQiEtq4ryFNoMo_8-bT2bzLOldoyQaFT_03u5d9Zkhtm52wP7vf-Ijvu7vkAbvnmIdztJkj-eQRf33rfjhaXIcnqNTPsR0iO9KyfBvGNtdOWSs49Q--UzZct6Ya5d2xVn88s-c-UMBRoxKjehM3ML_zwN9rNx_DpbPTx9F3cD02IrRTpAnHOvbeotBJfa-ekkUmVpZYC0TTBTVRw3KhaS-1rm9UGAbmQkkuLhsppzZ_ATnPV-KfAOPp-aa6FkK4SjksMlq3HcEdY61LldQSvVngsbd9RnAZbfC8xsiCklwHpZUB6BIdr4LZrpHEz2AkRZA1C3a_DBvJE2fNE-S-eiOBgRc6yF8l5iXEe-po0vTyCl-tjFCZ6ITGNv1oSTEb939DJjWC_o_76JtQaEZVjGoHa4outq26fNNPL0LBbCxqjo5_9j397DveGlFZDb1rDA9hZzJb-BdyxPxfT-WwAt9VEhVUPYPdkNC4-DIJk4HoxLGhVuO4W7y-KL9czHRW9
linkProvider Directory of Open Access Journals
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9QwEB6VLahceFMCBYxULojQJLY3zgEhoK266na1h4LaU-o4TrsSZMNml9I_xW9kJi9YVHHrgas9iZzkm1c8ng9gU4RZ1ueZchMRKRc9BKpUKiM38UMvSsLIRFW1xedhOBqpo6NovAI_27MwVFbZ2sTKUKdTQ__ItzBMx1CByKffFd9cYo2i3dWWQqOGxb69OMeUrXw72Mbv-zIIdncOP-65DauAa6Tw57gobq1BrfZsptJUauklfd9QpuZ7OIgWgOswU1LZzPQzjYJcSMmlQUueKsXxvtdgVSDYvR6sjgcH4-Purw46ZIU-tj4IGKKr3rLDSWbf9DkPwyXXVzEEXBbW_l2d-Ye72739v72oO3CrCazZ-1oT7sKKze_BjZpq8-I-nGxbW-zMz6pqtNdMs69VFallDW3GKSsmBZ3NtwzDeFYuCjKipU1Z28iAGUo0qLKqAjOjgzlsps_xwh8YYDyAT1fyeA-hl09z-wgYxyDZj5QQMk1EyqVSyljMC4UxqR9a5cCr9sPHpmm9TgwgX2JMwQglcYWSuEKJA5udcFF3HLlc7AMhqBOhNuHVwHR2GjdWJ6Zt3cQEWslEC8V9HSA-vTTRVgrUxMCBjRZDcWO7yvg3gBx40U2j1aGtJJ3b6YJk-tQoD7MBB9ZruHYroR6S6EV8B8IlIC8tdXkmn5xVnc2VIL4h9fjfy3oOa3uHB8N4OBjtP4GbAVUZ0RZfsAG9-Wxhn8J1830-KWfPGvVkcHLVQP8F9zh9DQ
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9QwEB6VLSAuvB-BAkYqF0TYJLZj54AQZXdF1dVqhQD1liaO064E2bAPSv8av46ZvGBRxa0HrvEkcpJvXvZ4PoBdofI85Ll2UxFpFz0EqlQmIzf1lRelKjJRVW3xeawmE314GE234Gd7FobKKlubWBnqbG5ojbyPYTqGCkQ-3c-bsojpYPSm_OYSgxTttLZ0GjVEDuzZKaZvy9f7A_zXz4NgNPz47r3bMAy4Rgp_hRPk1hrUcM_mOstkIr009A1lbb6HF9Ea8ETlWmqbmzBPUJALKbk0aNUzrTk-9xJsK45JTw-294aT6YduhQeds0Z_Wx8KVOi2-3Y8y-2rkHOlNtxgxRZwXoj7d6XmH65vdON__mg34XoTcLO3tYbcgi1b3IYrNQXn2R04GlhbDlcnVZXaS5awr1V1qWUNncYxK2clndm3DMN7tlyXZFyXNmNtgwNmKAGhiqsK5IwO7LBFcoo3_sDA4y58upDXuwe9Yl7YB8A4Bs9-pIWQWSoyLrXWxmK-KIzJfGW1Ay9aEMSmaclOzCBfYkzNCDFxhZi4QowDu51wWXciOV9sj9DUiVD78OrCfHEcN9Yopu3e1ASJlmkiNPeTALHqZWlipUANDRzYafEUNzZtGf8GkwPPumG0RrTFlBR2viaZkBroYZbgwP0aut1MqLckehffAbUB6o2pbo4Us5Oq47kWxEOkH_57Wk_hKqI7Hu9PDh7BtYCKj2jnL9iB3mqxto_hsvm-mi0XTxpNZXB00Tj_BYfAhac
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=DeepEthogram%2C+a+machine+learning+pipeline+for+supervised+behavior+classification+from+raw+pixels&rft.jtitle=eLife&rft.au=Bohnslav%2C+James+P&rft.au=Wimalasena%2C+Nivanthika+K&rft.au=Clausing%2C+Kelsey+J&rft.au=Dai%2C+Yu+Y&rft.date=2021-09-02&rft.issn=2050-084X&rft.eissn=2050-084X&rft.volume=10&rft_id=info:doi/10.7554%2FeLife.63377&rft.externalDBID=n%2Fa&rft.externalDocID=10_7554_eLife_63377
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2050-084X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2050-084X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2050-084X&client=summon