Advances in fine-grained visual categorization Article Swipe
The objective of this work is to improve performance in fine-grained visual categorization (FGVC). In particular, we are interested in the large-scale classification between hundreds of different flower, bird, dog species. FGVC is challenging due to high intra-class variances caused by deformation, view angle, illumination and occlusion, and low inter-class variance since some categories only differ in detail that only experts notice. Applications include field guides, automatic image annotation, one-click shopping app and 3D reconstruction. At the start, we discuss the importance of foreground segmentation in FGVC, where we focus on the unsupervised segmentation of image training sets into fore- ground and background in order to improve image classification performance. To this end, we introduce a new scalable, alternation-based algorithm for co-segmentation, Bi-CoS, which is simpler than many of its predecessors, and yet has superior performance on standard benchmark image datasets. Next, we extend BiCos to a new model, Tri- CoS, that adds a class-discriminitiveness term directly into the segmentation objective. The new term aims at removing image regions that, although appearing as foreground, do not contribute to the discrimination between classes. We also propose a model that combines parts alignment and foreground segmentation into a unified convex framework. The model is called Symbiotic in that part discovery/localization is helped by segmentation and, conversely, the segmentation is helped by the detection (e.g. part layout). The joined system improves over what can be achieved with an analogous system that runs segmentation and part-localization independently. Finally, we built a new flower dataset consisting of 26,798 high quality images collected by ourselves and 187,559 images gathered from existing datasets. The construction of this dataset follows a strict biological taxonomy. We also evaluate the impact of using the Amazon Mechanical Turk (AMT) service for filtering fine-grained data.
Related Topics
Concepts
Metadata
- Type
- dissertation
- Language
- en
- https://ora.ox.ac.uk/objects/uuid:f5dc5e73-118b-470c-900b-b7fce1d85786
- OA Status
- green
- Cited By
- 10
- Related Works
- 20
- OpenAlex ID
- https://openalex.org/W1414260227
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W1414260227Canonical identifier for this work in OpenAlex
- Title
-
Advances in fine-grained visual categorizationWork title
- Type
-
dissertationOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2015Year of publication
- Publication date
-
2015-01-01Full publication date if available
- Authors
-
Yuning ChaiList of authors in order
- PDF URL
-
https://ora.ox.ac.uk/objects/uuid:f5dc5e73-118b-470c-900b-b7fce1d85786Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://ora.ox.ac.uk/objects/uuid:f5dc5e73-118b-470c-900b-b7fce1d85786Direct OA link when available
- Concepts
-
Segmentation, Computer science, Artificial intelligence, Benchmark (surveying), Categorization, Scalability, Image segmentation, Focus (optics), Class (philosophy), Pattern recognition (psychology), Computer vision, Machine learning, Geography, Cartography, Database, Optics, PhysicsTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
10Total citation count in OpenAlex
- Citations by year (recent)
-
2024: 1, 2020: 3, 2019: 4, 2018: 1, 2016: 1Per-year citation counts (last 5 years)
- Related works (count)
-
20Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W1414260227 |
|---|---|
| doi | |
| ids.mag | 1414260227 |
| ids.openalex | https://openalex.org/W1414260227 |
| fwci | |
| type | dissertation |
| title | Advances in fine-grained visual categorization |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10616 |
| topics[0].field.id | https://openalex.org/fields/11 |
| topics[0].field.display_name | Agricultural and Biological Sciences |
| topics[0].score | 0.9930999875068665 |
| topics[0].domain.id | https://openalex.org/domains/1 |
| topics[0].domain.display_name | Life Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1110 |
| topics[0].subfield.display_name | Plant Science |
| topics[0].display_name | Smart Agriculture and AI |
| topics[1].id | https://openalex.org/T10627 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9889000058174133 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1707 |
| topics[1].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[1].display_name | Advanced Image and Video Retrieval Techniques |
| topics[2].id | https://openalex.org/T12388 |
| topics[2].field.id | https://openalex.org/fields/13 |
| topics[2].field.display_name | Biochemistry, Genetics and Molecular Biology |
| topics[2].score | 0.9753999710083008 |
| topics[2].domain.id | https://openalex.org/domains/1 |
| topics[2].domain.display_name | Life Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1312 |
| topics[2].subfield.display_name | Molecular Biology |
| topics[2].display_name | Identification and Quantification in Food |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C89600930 |
| concepts[0].level | 2 |
| concepts[0].score | 0.8208041191101074 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q1423946 |
| concepts[0].display_name | Segmentation |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.7210134863853455 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C154945302 |
| concepts[2].level | 1 |
| concepts[2].score | 0.6726200580596924 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[2].display_name | Artificial intelligence |
| concepts[3].id | https://openalex.org/C185798385 |
| concepts[3].level | 2 |
| concepts[3].score | 0.6036149263381958 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q1161707 |
| concepts[3].display_name | Benchmark (surveying) |
| concepts[4].id | https://openalex.org/C94124525 |
| concepts[4].level | 2 |
| concepts[4].score | 0.56666100025177 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q912550 |
| concepts[4].display_name | Categorization |
| concepts[5].id | https://openalex.org/C48044578 |
| concepts[5].level | 2 |
| concepts[5].score | 0.5458976030349731 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q727490 |
| concepts[5].display_name | Scalability |
| concepts[6].id | https://openalex.org/C124504099 |
| concepts[6].level | 3 |
| concepts[6].score | 0.5251402854919434 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q56933 |
| concepts[6].display_name | Image segmentation |
| concepts[7].id | https://openalex.org/C192209626 |
| concepts[7].level | 2 |
| concepts[7].score | 0.4998021125793457 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q190909 |
| concepts[7].display_name | Focus (optics) |
| concepts[8].id | https://openalex.org/C2777212361 |
| concepts[8].level | 2 |
| concepts[8].score | 0.4882254898548126 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q5127848 |
| concepts[8].display_name | Class (philosophy) |
| concepts[9].id | https://openalex.org/C153180895 |
| concepts[9].level | 2 |
| concepts[9].score | 0.4778858423233032 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[9].display_name | Pattern recognition (psychology) |
| concepts[10].id | https://openalex.org/C31972630 |
| concepts[10].level | 1 |
| concepts[10].score | 0.3505462110042572 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q844240 |
| concepts[10].display_name | Computer vision |
| concepts[11].id | https://openalex.org/C119857082 |
| concepts[11].level | 1 |
| concepts[11].score | 0.3205462396144867 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[11].display_name | Machine learning |
| concepts[12].id | https://openalex.org/C205649164 |
| concepts[12].level | 0 |
| concepts[12].score | 0.11075019836425781 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q1071 |
| concepts[12].display_name | Geography |
| concepts[13].id | https://openalex.org/C58640448 |
| concepts[13].level | 1 |
| concepts[13].score | 0.08764916658401489 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q42515 |
| concepts[13].display_name | Cartography |
| concepts[14].id | https://openalex.org/C77088390 |
| concepts[14].level | 1 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q8513 |
| concepts[14].display_name | Database |
| concepts[15].id | https://openalex.org/C120665830 |
| concepts[15].level | 1 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q14620 |
| concepts[15].display_name | Optics |
| concepts[16].id | https://openalex.org/C121332964 |
| concepts[16].level | 0 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q413 |
| concepts[16].display_name | Physics |
| keywords[0].id | https://openalex.org/keywords/segmentation |
| keywords[0].score | 0.8208041191101074 |
| keywords[0].display_name | Segmentation |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.7210134863853455 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[2].score | 0.6726200580596924 |
| keywords[2].display_name | Artificial intelligence |
| keywords[3].id | https://openalex.org/keywords/benchmark |
| keywords[3].score | 0.6036149263381958 |
| keywords[3].display_name | Benchmark (surveying) |
| keywords[4].id | https://openalex.org/keywords/categorization |
| keywords[4].score | 0.56666100025177 |
| keywords[4].display_name | Categorization |
| keywords[5].id | https://openalex.org/keywords/scalability |
| keywords[5].score | 0.5458976030349731 |
| keywords[5].display_name | Scalability |
| keywords[6].id | https://openalex.org/keywords/image-segmentation |
| keywords[6].score | 0.5251402854919434 |
| keywords[6].display_name | Image segmentation |
| keywords[7].id | https://openalex.org/keywords/focus |
| keywords[7].score | 0.4998021125793457 |
| keywords[7].display_name | Focus (optics) |
| keywords[8].id | https://openalex.org/keywords/class |
| keywords[8].score | 0.4882254898548126 |
| keywords[8].display_name | Class (philosophy) |
| keywords[9].id | https://openalex.org/keywords/pattern-recognition |
| keywords[9].score | 0.4778858423233032 |
| keywords[9].display_name | Pattern recognition (psychology) |
| keywords[10].id | https://openalex.org/keywords/computer-vision |
| keywords[10].score | 0.3505462110042572 |
| keywords[10].display_name | Computer vision |
| keywords[11].id | https://openalex.org/keywords/machine-learning |
| keywords[11].score | 0.3205462396144867 |
| keywords[11].display_name | Machine learning |
| keywords[12].id | https://openalex.org/keywords/geography |
| keywords[12].score | 0.11075019836425781 |
| keywords[12].display_name | Geography |
| keywords[13].id | https://openalex.org/keywords/cartography |
| keywords[13].score | 0.08764916658401489 |
| keywords[13].display_name | Cartography |
| language | en |
| locations[0].id | pmh:oai:ora.ox.ac.uk:uuid:f5dc5e73-118b-470c-900b-b7fce1d85786 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306402636 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | False |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | Oxford University Research Archive (ORA) (University of Oxford) |
| locations[0].source.host_organization | https://openalex.org/I40120149 |
| locations[0].source.host_organization_name | University of Oxford |
| locations[0].source.host_organization_lineage | https://openalex.org/I40120149 |
| locations[0].license | |
| locations[0].pdf_url | https://ora.ox.ac.uk/objects/uuid:f5dc5e73-118b-470c-900b-b7fce1d85786 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | Thesis |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | |
| locations[1].id | mag:1414260227 |
| locations[1].is_oa | False |
| locations[1].source | |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.655128 |
| authorships[0].author.id | https://openalex.org/A5079961895 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Yuning Chai |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Yuning Chai |
| authorships[0].is_corresponding | True |
| has_content.pdf | True |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://ora.ox.ac.uk/objects/uuid:f5dc5e73-118b-470c-900b-b7fce1d85786 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Advances in fine-grained visual categorization |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T04:12:42.849631 |
| primary_topic.id | https://openalex.org/T10616 |
| primary_topic.field.id | https://openalex.org/fields/11 |
| primary_topic.field.display_name | Agricultural and Biological Sciences |
| primary_topic.score | 0.9930999875068665 |
| primary_topic.domain.id | https://openalex.org/domains/1 |
| primary_topic.domain.display_name | Life Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1110 |
| primary_topic.subfield.display_name | Plant Science |
| primary_topic.display_name | Smart Agriculture and AI |
| related_works | https://openalex.org/W2132467081, https://openalex.org/W744862910, https://openalex.org/W2962835968, https://openalex.org/W2569554659, https://openalex.org/W2471678645, https://openalex.org/W1496650988, https://openalex.org/W1980526845, https://openalex.org/W2145360759, https://openalex.org/W2962957359, https://openalex.org/W2945674360, https://openalex.org/W2474812003, https://openalex.org/W2897407161, https://openalex.org/W3019368125, https://openalex.org/W3168495321, https://openalex.org/W2999219213, https://openalex.org/W2914809781, https://openalex.org/W2289708887, https://openalex.org/W3099903704, https://openalex.org/W3207483566, https://openalex.org/W3125055358 |
| cited_by_count | 10 |
| counts_by_year[0].year | 2024 |
| counts_by_year[0].cited_by_count | 1 |
| counts_by_year[1].year | 2020 |
| counts_by_year[1].cited_by_count | 3 |
| counts_by_year[2].year | 2019 |
| counts_by_year[2].cited_by_count | 4 |
| counts_by_year[3].year | 2018 |
| counts_by_year[3].cited_by_count | 1 |
| counts_by_year[4].year | 2016 |
| counts_by_year[4].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:ora.ox.ac.uk:uuid:f5dc5e73-118b-470c-900b-b7fce1d85786 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306402636 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | False |
| 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 | Oxford University Research Archive (ORA) (University of Oxford) |
| best_oa_location.source.host_organization | https://openalex.org/I40120149 |
| best_oa_location.source.host_organization_name | University of Oxford |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I40120149 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://ora.ox.ac.uk/objects/uuid:f5dc5e73-118b-470c-900b-b7fce1d85786 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | Thesis |
| 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 | |
| primary_location.id | pmh:oai:ora.ox.ac.uk:uuid:f5dc5e73-118b-470c-900b-b7fce1d85786 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306402636 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | False |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | Oxford University Research Archive (ORA) (University of Oxford) |
| primary_location.source.host_organization | https://openalex.org/I40120149 |
| primary_location.source.host_organization_name | University of Oxford |
| primary_location.source.host_organization_lineage | https://openalex.org/I40120149 |
| primary_location.license | |
| primary_location.pdf_url | https://ora.ox.ac.uk/objects/uuid:f5dc5e73-118b-470c-900b-b7fce1d85786 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | Thesis |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | |
| publication_date | 2015-01-01 |
| publication_year | 2015 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 115, 146, 153, 185, 195, 246, 272 |
| abstract_inverted_index.3D | 73 |
| abstract_inverted_index.In | 14 |
| abstract_inverted_index.To | 110 |
| abstract_inverted_index.We | 276 |
| abstract_inverted_index.an | 234 |
| abstract_inverted_index.as | 172 |
| abstract_inverted_index.at | 165 |
| abstract_inverted_index.be | 231 |
| abstract_inverted_index.by | 40, 210, 218, 257 |
| abstract_inverted_index.do | 174 |
| abstract_inverted_index.in | 9, 19, 56, 85, 103, 204 |
| abstract_inverted_index.is | 5, 32, 124, 201, 208, 216 |
| abstract_inverted_index.of | 2, 25, 82, 94, 128, 251, 268, 281 |
| abstract_inverted_index.on | 90, 136 |
| abstract_inverted_index.to | 6, 35, 105, 145, 177 |
| abstract_inverted_index.we | 16, 78, 88, 113, 142, 244 |
| abstract_inverted_index.The | 161, 199, 224, 266 |
| abstract_inverted_index.and | 45, 47, 72, 101, 131, 191, 240, 259 |
| abstract_inverted_index.app | 71 |
| abstract_inverted_index.are | 17 |
| abstract_inverted_index.can | 230 |
| abstract_inverted_index.dog | 29 |
| abstract_inverted_index.due | 34 |
| abstract_inverted_index.for | 120, 289 |
| abstract_inverted_index.has | 133 |
| abstract_inverted_index.its | 129 |
| abstract_inverted_index.low | 48 |
| abstract_inverted_index.new | 116, 147, 162, 247 |
| abstract_inverted_index.not | 175 |
| abstract_inverted_index.the | 20, 76, 80, 91, 158, 178, 214, 219, 279, 283 |
| abstract_inverted_index.yet | 132 |
| abstract_inverted_index.FGVC | 31 |
| abstract_inverted_index.Turk | 286 |
| abstract_inverted_index.adds | 152 |
| abstract_inverted_index.aims | 164 |
| abstract_inverted_index.also | 183, 277 |
| abstract_inverted_index.and, | 212 |
| abstract_inverted_index.end, | 112 |
| abstract_inverted_index.from | 263 |
| abstract_inverted_index.high | 36, 253 |
| abstract_inverted_index.into | 98, 157, 194 |
| abstract_inverted_index.many | 127 |
| abstract_inverted_index.only | 54, 59 |
| abstract_inverted_index.over | 228 |
| abstract_inverted_index.part | 206, 222 |
| abstract_inverted_index.runs | 238 |
| abstract_inverted_index.sets | 97 |
| abstract_inverted_index.some | 52 |
| abstract_inverted_index.term | 155, 163 |
| abstract_inverted_index.than | 126 |
| abstract_inverted_index.that | 58, 151, 187, 205, 237 |
| abstract_inverted_index.this | 3, 111, 269 |
| abstract_inverted_index.view | 42 |
| abstract_inverted_index.what | 229 |
| abstract_inverted_index.with | 233 |
| abstract_inverted_index.work | 4 |
| abstract_inverted_index.(AMT) | 287 |
| abstract_inverted_index.(e.g. | 221 |
| abstract_inverted_index.BiCos | 144 |
| abstract_inverted_index.FGVC, | 86 |
| abstract_inverted_index.Next, | 141 |
| abstract_inverted_index.bird, | 28 |
| abstract_inverted_index.built | 245 |
| abstract_inverted_index.field | 64 |
| abstract_inverted_index.focus | 89 |
| abstract_inverted_index.fore- | 99 |
| abstract_inverted_index.image | 67, 95, 107, 139, 167 |
| abstract_inverted_index.model | 186, 200 |
| abstract_inverted_index.order | 104 |
| abstract_inverted_index.parts | 189 |
| abstract_inverted_index.since | 51 |
| abstract_inverted_index.that, | 169 |
| abstract_inverted_index.using | 282 |
| abstract_inverted_index.where | 87 |
| abstract_inverted_index.which | 123 |
| abstract_inverted_index.26,798 | 252 |
| abstract_inverted_index.Amazon | 284 |
| abstract_inverted_index.angle, | 43 |
| abstract_inverted_index.called | 202 |
| abstract_inverted_index.caused | 39 |
| abstract_inverted_index.convex | 197 |
| abstract_inverted_index.detail | 57 |
| abstract_inverted_index.differ | 55 |
| abstract_inverted_index.extend | 143 |
| abstract_inverted_index.flower | 248 |
| abstract_inverted_index.ground | 100 |
| abstract_inverted_index.helped | 209, 217 |
| abstract_inverted_index.images | 255, 261 |
| abstract_inverted_index.impact | 280 |
| abstract_inverted_index.joined | 225 |
| abstract_inverted_index.model, | 148 |
| abstract_inverted_index.start, | 77 |
| abstract_inverted_index.strict | 273 |
| abstract_inverted_index.system | 226, 236 |
| abstract_inverted_index.visual | 11 |
| abstract_inverted_index.(FGVC). | 13 |
| abstract_inverted_index.187,559 | 260 |
| abstract_inverted_index.between | 23, 180 |
| abstract_inverted_index.dataset | 249, 270 |
| abstract_inverted_index.discuss | 79 |
| abstract_inverted_index.experts | 60 |
| abstract_inverted_index.flower, | 27 |
| abstract_inverted_index.follows | 271 |
| abstract_inverted_index.guides, | 65 |
| abstract_inverted_index.improve | 7, 106 |
| abstract_inverted_index.include | 63 |
| abstract_inverted_index.notice. | 61 |
| abstract_inverted_index.propose | 184 |
| abstract_inverted_index.quality | 254 |
| abstract_inverted_index.regions | 168 |
| abstract_inverted_index.service | 288 |
| abstract_inverted_index.simpler | 125 |
| abstract_inverted_index.unified | 196 |
| abstract_inverted_index.achieved | 232 |
| abstract_inverted_index.although | 170 |
| abstract_inverted_index.combines | 188 |
| abstract_inverted_index.directly | 156 |
| abstract_inverted_index.evaluate | 278 |
| abstract_inverted_index.existing | 264 |
| abstract_inverted_index.gathered | 262 |
| abstract_inverted_index.hundreds | 24 |
| abstract_inverted_index.improves | 227 |
| abstract_inverted_index.layout). | 223 |
| abstract_inverted_index.removing | 166 |
| abstract_inverted_index.shopping | 70 |
| abstract_inverted_index.species. | 30 |
| abstract_inverted_index.standard | 137 |
| abstract_inverted_index.superior | 134 |
| abstract_inverted_index.training | 96 |
| abstract_inverted_index.variance | 50 |
| abstract_inverted_index.algorithm | 119 |
| abstract_inverted_index.alignment | 190 |
| abstract_inverted_index.analogous | 235 |
| abstract_inverted_index.appearing | 171 |
| abstract_inverted_index.automatic | 66 |
| abstract_inverted_index.benchmark | 138 |
| abstract_inverted_index.collected | 256 |
| abstract_inverted_index.datasets. | 140, 265 |
| abstract_inverted_index.detection | 220 |
| abstract_inverted_index.different | 26 |
| abstract_inverted_index.filtering | 290 |
| abstract_inverted_index.introduce | 114 |
| abstract_inverted_index.objective | 1 |
| abstract_inverted_index.one-click | 69 |
| abstract_inverted_index.ourselves | 258 |
| abstract_inverted_index.scalable, | 117 |
| abstract_inverted_index.taxonomy. | 275 |
| abstract_inverted_index.variances | 38 |
| abstract_inverted_index.Mechanical | 285 |
| abstract_inverted_index.background | 102 |
| abstract_inverted_index.biological | 274 |
| abstract_inverted_index.categories | 53 |
| abstract_inverted_index.consisting | 250 |
| abstract_inverted_index.contribute | 176 |
| abstract_inverted_index.foreground | 83, 192 |
| abstract_inverted_index.framework. | 198 |
| abstract_inverted_index.importance | 81 |
| abstract_inverted_index.interested | 18 |
| abstract_inverted_index.objective. | 160 |
| abstract_inverted_index.occlusion, | 46 |
| abstract_inverted_index.<p>At | 75 |
| abstract_inverted_index.<p>We | 182 |
| abstract_inverted_index.annotation, | 68 |
| abstract_inverted_index.challenging | 33 |
| abstract_inverted_index.conversely, | 213 |
| abstract_inverted_index.foreground, | 173 |
| abstract_inverted_index.inter-class | 49 |
| abstract_inverted_index.intra-class | 37 |
| abstract_inverted_index.large-scale | 21 |
| abstract_inverted_index.particular, | 15 |
| abstract_inverted_index.performance | 8, 135 |
| abstract_inverted_index.<p>The | 0 |
| abstract_inverted_index.Applications | 62 |
| abstract_inverted_index.construction | 267 |
| abstract_inverted_index.deformation, | 41 |
| abstract_inverted_index.fine-grained | 10, 291 |
| abstract_inverted_index.illumination | 44 |
| abstract_inverted_index.performance. | 109 |
| abstract_inverted_index.segmentation | 84, 93, 159, 193, 211, 215, 239 |
| abstract_inverted_index.unsupervised | 92 |
| abstract_inverted_index.predecessors, | 130 |
| abstract_inverted_index.<em>Tri- | 149 |
| abstract_inverted_index.categorization | 12 |
| abstract_inverted_index.classification | 22, 108 |
| abstract_inverted_index.discrimination | 179 |
| abstract_inverted_index.CoS</em>, | 150 |
| abstract_inverted_index.data.</p> | 292 |
| abstract_inverted_index.co-segmentation, | 121 |
| abstract_inverted_index.<p>Finally, | 243 |
| abstract_inverted_index.alternation-based | 118 |
| abstract_inverted_index.part-localization | 241 |
| abstract_inverted_index.classes.</p> | 181 |
| abstract_inverted_index.discovery/localization | 207 |
| abstract_inverted_index.class-discriminitiveness | 154 |
| abstract_inverted_index.independently.</p> | 242 |
| abstract_inverted_index.reconstruction.</p> | 74 |
| abstract_inverted_index.<em>Bi-CoS</em>, | 122 |
| abstract_inverted_index.<em>Symbiotic</em> | 203 |
| cited_by_percentile_year | |
| corresponding_author_ids | https://openalex.org/A5079961895 |
| countries_distinct_count | 0 |
| institutions_distinct_count | 1 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/10 |
| sustainable_development_goals[0].score | 0.5899999737739563 |
| sustainable_development_goals[0].display_name | Reduced inequalities |
| citation_normalized_percentile |