SAM 2: Segment Anything in Images and Videos Article Swipe
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2408.00714
We present Segment Anything Model 2 (SAM 2), a foundation model towards solving promptable visual segmentation in images and videos. We build a data engine, which improves model and data via user interaction, to collect the largest video segmentation dataset to date. Our model is a simple transformer architecture with streaming memory for real-time video processing. SAM 2 trained on our data provides strong performance across a wide range of tasks. In video segmentation, we observe better accuracy, using 3x fewer interactions than prior approaches. In image segmentation, our model is more accurate and 6x faster than the Segment Anything Model (SAM). We believe that our data, model, and insights will serve as a significant milestone for video segmentation and related perception tasks. We are releasing our main model, dataset, as well as code for model training and our demo.
Related Topics
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2408.00714
- https://arxiv.org/pdf/2408.00714
- OA Status
- green
- Cited By
- 186
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4401307635
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4401307635Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2408.00714Digital Object Identifier
- Title
-
SAM 2: Segment Anything in Images and VideosWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-08-01Full publication date if available
- Authors
-
Nikhila Ravi, Valentin Gabeur, Yuan-Ting Hu, Ronghang Hu, Chaitanya K. Ryali, Tengyu Ma, Haitham Khedr, Roman Rädle, Chloe Rolland, Laura Gustafson, Eric Mintun, Junting Pan, Kalyan Vasudev Alwala, Nicolas Carion, Chao-Yuan Wu, Ross Girshick, Piotr Dollár, Christoph FeichtenhoferList of authors in order
- Landing page
-
https://arxiv.org/abs/2408.00714Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2408.00714Direct 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/2408.00714Direct OA link when available
- Concepts
-
Computer science, Computer vision, Artificial intelligenceTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
186Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 169, 2024: 17Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4401307635 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2408.00714 |
| ids.doi | https://doi.org/10.48550/arxiv.2408.00714 |
| ids.openalex | https://openalex.org/W4401307635 |
| fwci | |
| type | preprint |
| title | SAM 2: Segment Anything in Images and Videos |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10775 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.0560000017285347 |
| 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 | Generative Adversarial Networks and Image Synthesis |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.4786342680454254 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C31972630 |
| concepts[1].level | 1 |
| concepts[1].score | 0.45397141575813293 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q844240 |
| concepts[1].display_name | Computer vision |
| concepts[2].id | https://openalex.org/C154945302 |
| concepts[2].level | 1 |
| concepts[2].score | 0.4273913502693176 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[2].display_name | Artificial intelligence |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.4786342680454254 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/computer-vision |
| keywords[1].score | 0.45397141575813293 |
| keywords[1].display_name | Computer vision |
| keywords[2].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[2].score | 0.4273913502693176 |
| keywords[2].display_name | Artificial intelligence |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2408.00714 |
| 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/2408.00714 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | |
| 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/2408.00714 |
| locations[1].id | doi:10.48550/arxiv.2408.00714 |
| 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 | |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | |
| 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.2408.00714 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5045356290 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-0097-5222 |
| authorships[0].author.display_name | Nikhila Ravi |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Ravi, Nikhila |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5001789528 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Valentin Gabeur |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Gabeur, Valentin |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5015863645 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Yuan-Ting Hu |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Hu, Yuan-Ting |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5072304825 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-5060-9485 |
| authorships[3].author.display_name | Ronghang Hu |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Hu, Ronghang |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5028978530 |
| authorships[4].author.orcid | |
| authorships[4].author.display_name | Chaitanya K. Ryali |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Ryali, Chaitanya |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5101821970 |
| authorships[5].author.orcid | https://orcid.org/0000-0003-3916-5040 |
| authorships[5].author.display_name | Tengyu Ma |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Ma, Tengyu |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5090549040 |
| authorships[6].author.orcid | https://orcid.org/0000-0002-3220-1558 |
| authorships[6].author.display_name | Haitham Khedr |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Khedr, Haitham |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5018955742 |
| authorships[7].author.orcid | https://orcid.org/0000-0002-0168-186X |
| authorships[7].author.display_name | Roman Rädle |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Rädle, Roman |
| authorships[7].is_corresponding | False |
| authorships[8].author.id | https://openalex.org/A5043279771 |
| authorships[8].author.orcid | |
| authorships[8].author.display_name | Chloe Rolland |
| authorships[8].author_position | middle |
| authorships[8].raw_author_name | Rolland, Chloe |
| authorships[8].is_corresponding | False |
| authorships[9].author.id | https://openalex.org/A5033942765 |
| authorships[9].author.orcid | |
| authorships[9].author.display_name | Laura Gustafson |
| authorships[9].author_position | middle |
| authorships[9].raw_author_name | Gustafson, Laura |
| authorships[9].is_corresponding | False |
| authorships[10].author.id | https://openalex.org/A5042149832 |
| authorships[10].author.orcid | |
| authorships[10].author.display_name | Eric Mintun |
| authorships[10].author_position | middle |
| authorships[10].raw_author_name | Mintun, Eric |
| authorships[10].is_corresponding | False |
| authorships[11].author.id | https://openalex.org/A5088732762 |
| authorships[11].author.orcid | |
| authorships[11].author.display_name | Junting Pan |
| authorships[11].author_position | middle |
| authorships[11].raw_author_name | Pan, Junting |
| authorships[11].is_corresponding | False |
| authorships[12].author.id | https://openalex.org/A5078659702 |
| authorships[12].author.orcid | |
| authorships[12].author.display_name | Kalyan Vasudev Alwala |
| authorships[12].author_position | middle |
| authorships[12].raw_author_name | Alwala, Kalyan Vasudev |
| authorships[12].is_corresponding | False |
| authorships[13].author.id | https://openalex.org/A5029981206 |
| authorships[13].author.orcid | https://orcid.org/0000-0002-2308-9680 |
| authorships[13].author.display_name | Nicolas Carion |
| authorships[13].author_position | middle |
| authorships[13].raw_author_name | Carion, Nicolas |
| authorships[13].is_corresponding | False |
| authorships[14].author.id | https://openalex.org/A5023917342 |
| authorships[14].author.orcid | https://orcid.org/0000-0002-5690-8865 |
| authorships[14].author.display_name | Chao-Yuan Wu |
| authorships[14].author_position | middle |
| authorships[14].raw_author_name | Wu, Chao-Yuan |
| authorships[14].is_corresponding | False |
| authorships[15].author.id | https://openalex.org/A5049246408 |
| authorships[15].author.orcid | |
| authorships[15].author.display_name | Ross Girshick |
| authorships[15].author_position | middle |
| authorships[15].raw_author_name | Girshick, Ross |
| authorships[15].is_corresponding | False |
| authorships[16].author.id | https://openalex.org/A5057866698 |
| authorships[16].author.orcid | |
| authorships[16].author.display_name | Piotr Dollár |
| authorships[16].author_position | middle |
| authorships[16].raw_author_name | Dollár, Piotr |
| authorships[16].is_corresponding | False |
| authorships[17].author.id | https://openalex.org/A5036069974 |
| authorships[17].author.orcid | https://orcid.org/0000-0001-9756-7238 |
| authorships[17].author.display_name | Christoph Feichtenhofer |
| authorships[17].author_position | last |
| authorships[17].raw_author_name | Feichtenhofer, Christoph |
| authorships[17].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/2408.00714 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | SAM 2: Segment Anything in Images and Videos |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10775 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.0560000017285347 |
| 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 | Generative Adversarial Networks and Image Synthesis |
| related_works | https://openalex.org/W2058170566, https://openalex.org/W2755342338, https://openalex.org/W2772917594, https://openalex.org/W2775347418, https://openalex.org/W2166024367, https://openalex.org/W3116076068, https://openalex.org/W2229312674, https://openalex.org/W2951359407, https://openalex.org/W2079911747, https://openalex.org/W1969923398 |
| cited_by_count | 186 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 169 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 17 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2408.00714 |
| 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/2408.00714 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | |
| 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/2408.00714 |
| primary_location.id | pmh:oai:arXiv.org:2408.00714 |
| 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/2408.00714 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | |
| 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/2408.00714 |
| publication_date | 2024-08-01 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.2 | 5, 57 |
| abstract_inverted_index.a | 8, 22, 45, 66, 113 |
| abstract_inverted_index.3x | 79 |
| abstract_inverted_index.6x | 94 |
| abstract_inverted_index.In | 71, 85 |
| abstract_inverted_index.We | 0, 20, 102, 123 |
| abstract_inverted_index.as | 112, 130, 132 |
| abstract_inverted_index.in | 16 |
| abstract_inverted_index.is | 44, 90 |
| abstract_inverted_index.of | 69 |
| abstract_inverted_index.on | 59 |
| abstract_inverted_index.to | 33, 40 |
| abstract_inverted_index.we | 74 |
| abstract_inverted_index.2), | 7 |
| abstract_inverted_index.Our | 42 |
| abstract_inverted_index.SAM | 56 |
| abstract_inverted_index.and | 18, 28, 93, 108, 119, 137 |
| abstract_inverted_index.are | 124 |
| abstract_inverted_index.for | 52, 116, 134 |
| abstract_inverted_index.our | 60, 88, 105, 126, 138 |
| abstract_inverted_index.the | 35, 97 |
| abstract_inverted_index.via | 30 |
| abstract_inverted_index.(SAM | 6 |
| abstract_inverted_index.code | 133 |
| abstract_inverted_index.data | 23, 29, 61 |
| abstract_inverted_index.main | 127 |
| abstract_inverted_index.more | 91 |
| abstract_inverted_index.than | 82, 96 |
| abstract_inverted_index.that | 104 |
| abstract_inverted_index.user | 31 |
| abstract_inverted_index.well | 131 |
| abstract_inverted_index.wide | 67 |
| abstract_inverted_index.will | 110 |
| abstract_inverted_index.with | 49 |
| abstract_inverted_index.Model | 4, 100 |
| abstract_inverted_index.build | 21 |
| abstract_inverted_index.data, | 106 |
| abstract_inverted_index.date. | 41 |
| abstract_inverted_index.demo. | 139 |
| abstract_inverted_index.fewer | 80 |
| abstract_inverted_index.image | 86 |
| abstract_inverted_index.model | 10, 27, 43, 89, 135 |
| abstract_inverted_index.prior | 83 |
| abstract_inverted_index.range | 68 |
| abstract_inverted_index.serve | 111 |
| abstract_inverted_index.using | 78 |
| abstract_inverted_index.video | 37, 54, 72, 117 |
| abstract_inverted_index.which | 25 |
| abstract_inverted_index.(SAM). | 101 |
| abstract_inverted_index.across | 65 |
| abstract_inverted_index.better | 76 |
| abstract_inverted_index.faster | 95 |
| abstract_inverted_index.images | 17 |
| abstract_inverted_index.memory | 51 |
| abstract_inverted_index.model, | 107, 128 |
| abstract_inverted_index.simple | 46 |
| abstract_inverted_index.strong | 63 |
| abstract_inverted_index.tasks. | 70, 122 |
| abstract_inverted_index.visual | 14 |
| abstract_inverted_index.Segment | 2, 98 |
| abstract_inverted_index.believe | 103 |
| abstract_inverted_index.collect | 34 |
| abstract_inverted_index.dataset | 39 |
| abstract_inverted_index.engine, | 24 |
| abstract_inverted_index.largest | 36 |
| abstract_inverted_index.observe | 75 |
| abstract_inverted_index.present | 1 |
| abstract_inverted_index.related | 120 |
| abstract_inverted_index.solving | 12 |
| abstract_inverted_index.towards | 11 |
| abstract_inverted_index.trained | 58 |
| abstract_inverted_index.videos. | 19 |
| abstract_inverted_index.Anything | 3, 99 |
| abstract_inverted_index.accurate | 92 |
| abstract_inverted_index.dataset, | 129 |
| abstract_inverted_index.improves | 26 |
| abstract_inverted_index.insights | 109 |
| abstract_inverted_index.provides | 62 |
| abstract_inverted_index.training | 136 |
| abstract_inverted_index.accuracy, | 77 |
| abstract_inverted_index.milestone | 115 |
| abstract_inverted_index.real-time | 53 |
| abstract_inverted_index.releasing | 125 |
| abstract_inverted_index.streaming | 50 |
| abstract_inverted_index.foundation | 9 |
| abstract_inverted_index.perception | 121 |
| abstract_inverted_index.promptable | 13 |
| abstract_inverted_index.approaches. | 84 |
| abstract_inverted_index.performance | 64 |
| abstract_inverted_index.processing. | 55 |
| abstract_inverted_index.significant | 114 |
| abstract_inverted_index.transformer | 47 |
| abstract_inverted_index.architecture | 48 |
| abstract_inverted_index.interaction, | 32 |
| abstract_inverted_index.interactions | 81 |
| abstract_inverted_index.segmentation | 15, 38, 118 |
| abstract_inverted_index.segmentation, | 73, 87 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 18 |
| citation_normalized_percentile |