{"doi":"10.7554/elife.63377","title":"DeepEthogram, a machine learning pipeline for supervised behavior classification from raw pixels","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.","journal":"eLife","year":2021,"id":146362,"datarank":4.480820040038633,"base_score":5.438079308923196,"endowment":5.438079308923196,"self_citation_contribution":0.8157118963384794,"citation_network_contribution":3.6651081437001536,"self_endowment_contribution":0.8157118963384794,"citer_contribution":3.6651081437001536,"corpus_percentile":95.08780072716021,"corpus_rank":636,"citation_count":229,"citer_count":100,"citers_with_citation_signal":100,"citers_with_endowment":100,"datacite_reuse_total":0,"is_dataset":true,"is_dataset_confidence":0.744,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2021-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":407584,"name":"Nivanthika K. Wimalasena","orcid":"0000-0001-6188-790X","position":1,"is_corresponding":false},{"id":552788,"name":"Kelsey J. Clausing","orcid":"0000-0003-4365-9764","position":2,"is_corresponding":false},{"id":621816,"name":"Yu Dai","orcid":"0000-0002-2445-4563","position":3,"is_corresponding":false},{"id":621817,"name":"David A. Yarmolinsky","orcid":"0009-0007-7750-9154","position":4,"is_corresponding":false},{"id":552789,"name":"Tomás Cruz","orcid":"0000-0001-6622-1541","position":5,"is_corresponding":false},{"id":621818,"name":"Adam D. Kashlan","orcid":"0000-0003-4620-5266","position":6,"is_corresponding":false},{"id":552790,"name":"M Eugenia Chiappe","orcid":"0000-0003-1761-0457","position":7,"is_corresponding":false},{"id":552791,"name":"Lauren L. Orefice","orcid":"0000-0003-3389-7320","position":8,"is_corresponding":false},{"id":262675,"name":"Clifford J. Woolf","orcid":"0000-0002-6636-3897","position":9,"is_corresponding":false},{"id":273843,"name":"Christopher D. Harvey","orcid":"0000-0001-9850-2268","position":10,"is_corresponding":false},{"id":552787,"name":"James P. Bohnslav","orcid":"0000-0002-9359-8907","position":0,"is_corresponding":true}],"reference_count":105,"raw_metadata":null,"created_at":"2026-07-18T23:42:18.947086Z","pmid":"34473051","pmcid":"PMC8455138","fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}