Toward Robust Human Pose Estimation Under Real-World Image Degradations and Restoration Scenarios Article Swipe
Nada E. Elshami
,
Ahmad Salah
,
Ahmed Salama Abdel Latif
,
Heba Mohsen
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.3390/info16110970
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.3390/info16110970
Human Pose Estimation (HPE) models have varied applications and represent a cutting-edge branch of study, whose systems such as MediaPipe (MP), OpenPose (OP), and AlphaPose (ALP) show marked success. One of these areas, however, that is inadequately researched is the impact of image degradation on the accuracy of HPE models. Image degradation refers to images whose visual quality has been purposefully degraded by means of techniques, such as brightness adjustments (which can lead to an increase or a decrease in the intensity levels), geometric rotations, or resolution downscaling. The study of how these types of degradation impact the performance functionality of HPE models is an under-researched domaina that is a virtually unexplored area. In addition, current methods of the efficacy of existing image restoration techniques have not been rigorously evaluated and improving degraded images to a high quality has not been well examined in relation to improving HPE models. In this study, we explicitly clearly demonstrate a decline in the precision of the HPE model when image quality is degraded. Our qualitative and quantitative measurements identify a wide difference in performance in identifying landmarks as images undergo changes in brightness, rotation, or reductions in resolution. Additionally, we have tested a variety of existing image enhancement methods in an attempt to enhance their capability in restoring low-quality images, hence supporting improved functionality of HPE. Interestingly, for rotated images, using Pillow of OpenCV improves landmark recognition precision drastically, nearly restoring it to levels we see in high-quality images. In instances of brightness variation and in low-quality images, however, existing methods of enhancement fail to yield the improvements anticipated, highlighting a large direction of study that warrants further investigation and calls for additional research. In this regard, we proposed a wide-ranging system for classifying different types of image degradation systematically and for selecting appropriate algorithms for image restoration, in an effort to restore image quality. A key finding is that in a related study of current methods, the Tuned RotNet model achieves 92.04% accuracy, significantly outperforming the baseline model and surpassing the official RotNet model in predicting rotation degree of images, where the accuracy of official RotNet and Tuned RotNet classifiers were 61.59% and 92.04%, respectively. Furthermore, in an effort to facilitate future research and make it easier for other studies, we provide a new dataset of reference images and corresponding degenerated images, addressing a notable gap in controlled comparative studies, since currently there is a lack of controlled comparatives.
Related Topics
Concepts
No concepts available.
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.3390/info16110970
- https://www.mdpi.com/2078-2489/16/11/970/pdf?version=1762783551
- OA Status
- gold
- OpenAlex ID
- https://openalex.org/W4416087136
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4416087136Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.3390/info16110970Digital Object Identifier
- Title
-
Toward Robust Human Pose Estimation Under Real-World Image Degradations and Restoration ScenariosWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-11-10Full publication date if available
- Authors
-
Nada E. Elshami, Ahmad Salah, Ahmed Salama Abdel Latif, Heba MohsenList of authors in order
- Landing page
-
https://doi.org/10.3390/info16110970Publisher landing page
- PDF URL
-
https://www.mdpi.com/2078-2489/16/11/970/pdf?version=1762783551Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
goldOpen access status per OpenAlex
- OA URL
-
https://www.mdpi.com/2078-2489/16/11/970/pdf?version=1762783551Direct OA link when available
- Cited by
-
0Total citation count in OpenAlex
Full payload
| id | https://openalex.org/W4416087136 |
|---|---|
| doi | https://doi.org/10.3390/info16110970 |
| ids.doi | https://doi.org/10.3390/info16110970 |
| ids.openalex | https://openalex.org/W4416087136 |
| fwci | |
| type | article |
| title | Toward Robust Human Pose Estimation Under Real-World Image Degradations and Restoration Scenarios |
| biblio.issue | 11 |
| biblio.volume | 16 |
| biblio.last_page | 970 |
| biblio.first_page | 970 |
| is_xpac | False |
| apc_list.value | 1400 |
| apc_list.currency | CHF |
| apc_list.value_usd | 1515 |
| apc_paid.value | 1400 |
| apc_paid.currency | CHF |
| apc_paid.value_usd | 1515 |
| language | en |
| locations[0].id | doi:10.3390/info16110970 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4210219776 |
| locations[0].source.issn | 2078-2489 |
| locations[0].source.type | journal |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | 2078-2489 |
| locations[0].source.is_core | True |
| locations[0].source.is_in_doaj | True |
| locations[0].source.display_name | Information |
| locations[0].source.host_organization | https://openalex.org/P4310310987 |
| locations[0].source.host_organization_name | Multidisciplinary Digital Publishing Institute |
| locations[0].source.host_organization_lineage | https://openalex.org/P4310310987 |
| locations[0].source.host_organization_lineage_names | Multidisciplinary Digital Publishing Institute |
| locations[0].license | cc-by |
| locations[0].pdf_url | https://www.mdpi.com/2078-2489/16/11/970/pdf?version=1762783551 |
| locations[0].version | publishedVersion |
| locations[0].raw_type | journal-article |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | Information |
| locations[0].landing_page_url | https://doi.org/10.3390/info16110970 |
| locations[1].id | pmh:oai:doaj.org/article:6d6b651e41a64027926dbf9ead516d99 |
| locations[1].is_oa | False |
| locations[1].source.id | https://openalex.org/S4306401280 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | False |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | DOAJ (DOAJ: Directory of Open Access Journals) |
| locations[1].source.host_organization | |
| locations[1].source.host_organization_name | |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | submittedVersion |
| locations[1].raw_type | article |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | False |
| locations[1].raw_source_name | Information, Vol 16, Iss 11, p 970 (2025) |
| locations[1].landing_page_url | https://doaj.org/article/6d6b651e41a64027926dbf9ead516d99 |
| indexed_in | crossref, doaj |
| authorships[0].author.id | https://openalex.org/A5064323998 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-2530-5041 |
| authorships[0].author.display_name | Nada E. Elshami |
| authorships[0].countries | EG |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I192398990 |
| authorships[0].affiliations[0].raw_affiliation_string | College of Computers and Informatics, Zagazig University, Zagazig 44519, Egypt |
| authorships[0].affiliations[1].institution_ids | https://openalex.org/I186217134 |
| authorships[0].affiliations[1].raw_affiliation_string | Department of Computer Science, Faculty of Computers and Information Technology, Future University in Egypt, New Cairo 11835, Egypt |
| authorships[0].institutions[0].id | https://openalex.org/I186217134 |
| authorships[0].institutions[0].ror | https://ror.org/03s8c2x09 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I186217134 |
| authorships[0].institutions[0].country_code | EG |
| authorships[0].institutions[0].display_name | Future University in Egypt |
| authorships[0].institutions[1].id | https://openalex.org/I192398990 |
| authorships[0].institutions[1].ror | https://ror.org/053g6we49 |
| authorships[0].institutions[1].type | education |
| authorships[0].institutions[1].lineage | https://openalex.org/I192398990 |
| authorships[0].institutions[1].country_code | EG |
| authorships[0].institutions[1].display_name | Zagazig University |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Nada E. Elshami |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | College of Computers and Informatics, Zagazig University, Zagazig 44519, Egypt, Department of Computer Science, Faculty of Computers and Information Technology, Future University in Egypt, New Cairo 11835, Egypt |
| authorships[1].author.id | https://openalex.org/A5039175317 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-3433-7640 |
| authorships[1].author.display_name | Ahmad Salah |
| authorships[1].countries | OM |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I4210114546 |
| authorships[1].affiliations[0].raw_affiliation_string | College of Computing and Information Sciences, University of Technology and Applied Sciences, Ibri 516, Oman |
| authorships[1].institutions[0].id | https://openalex.org/I4210114546 |
| authorships[1].institutions[0].ror | https://ror.org/01xf31a71 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I4210114546 |
| authorships[1].institutions[0].country_code | OM |
| authorships[1].institutions[0].display_name | College of Applied Sciences, Nizwa |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Ahmad Salah |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | College of Computing and Information Sciences, University of Technology and Applied Sciences, Ibri 516, Oman |
| authorships[2].author.id | https://openalex.org/A5004750270 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-1153-8538 |
| authorships[2].author.display_name | Ahmed Salama Abdel Latif |
| authorships[2].countries | EG |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I192398990 |
| authorships[2].affiliations[0].raw_affiliation_string | College of Computers and Informatics, Zagazig University, Zagazig 44519, Egypt |
| authorships[2].institutions[0].id | https://openalex.org/I192398990 |
| authorships[2].institutions[0].ror | https://ror.org/053g6we49 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I192398990 |
| authorships[2].institutions[0].country_code | EG |
| authorships[2].institutions[0].display_name | Zagazig University |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Amr Abdellatif |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | College of Computers and Informatics, Zagazig University, Zagazig 44519, Egypt |
| authorships[3].author.id | https://openalex.org/A5039778903 |
| authorships[3].author.orcid | https://orcid.org/0000-0003-2003-0357 |
| authorships[3].author.display_name | Heba Mohsen |
| authorships[3].countries | EG |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I186217134 |
| authorships[3].affiliations[0].raw_affiliation_string | Department of Computer Science, Faculty of Computers and Information Technology, Future University in Egypt, New Cairo 11835, Egypt |
| authorships[3].institutions[0].id | https://openalex.org/I186217134 |
| authorships[3].institutions[0].ror | https://ror.org/03s8c2x09 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I186217134 |
| authorships[3].institutions[0].country_code | EG |
| authorships[3].institutions[0].display_name | Future University in Egypt |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Heba Mohsen |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | Department of Computer Science, Faculty of Computers and Information Technology, Future University in Egypt, New Cairo 11835, Egypt |
| has_content.pdf | True |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://www.mdpi.com/2078-2489/16/11/970/pdf?version=1762783551 |
| open_access.oa_status | gold |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-11-10T00:00:00 |
| display_name | Toward Robust Human Pose Estimation Under Real-World Image Degradations and Restoration Scenarios |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-28T23:14:17.795251 |
| primary_topic | |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | doi:10.3390/info16110970 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4210219776 |
| best_oa_location.source.issn | 2078-2489 |
| best_oa_location.source.type | journal |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | 2078-2489 |
| best_oa_location.source.is_core | True |
| best_oa_location.source.is_in_doaj | True |
| best_oa_location.source.display_name | Information |
| best_oa_location.source.host_organization | https://openalex.org/P4310310987 |
| best_oa_location.source.host_organization_name | Multidisciplinary Digital Publishing Institute |
| best_oa_location.source.host_organization_lineage | https://openalex.org/P4310310987 |
| best_oa_location.source.host_organization_lineage_names | Multidisciplinary Digital Publishing Institute |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | https://www.mdpi.com/2078-2489/16/11/970/pdf?version=1762783551 |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | journal-article |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | Information |
| best_oa_location.landing_page_url | https://doi.org/10.3390/info16110970 |
| primary_location.id | doi:10.3390/info16110970 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4210219776 |
| primary_location.source.issn | 2078-2489 |
| primary_location.source.type | journal |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | 2078-2489 |
| primary_location.source.is_core | True |
| primary_location.source.is_in_doaj | True |
| primary_location.source.display_name | Information |
| primary_location.source.host_organization | https://openalex.org/P4310310987 |
| primary_location.source.host_organization_name | Multidisciplinary Digital Publishing Institute |
| primary_location.source.host_organization_lineage | https://openalex.org/P4310310987 |
| primary_location.source.host_organization_lineage_names | Multidisciplinary Digital Publishing Institute |
| primary_location.license | cc-by |
| primary_location.pdf_url | https://www.mdpi.com/2078-2489/16/11/970/pdf?version=1762783551 |
| primary_location.version | publishedVersion |
| primary_location.raw_type | journal-article |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | Information |
| primary_location.landing_page_url | https://doi.org/10.3390/info16110970 |
| publication_date | 2025-11-10 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.A | 312 |
| abstract_inverted_index.a | 10, 77, 109, 135, 156, 176, 199, 267, 286, 318, 380, 391, 402 |
| abstract_inverted_index.In | 113, 149, 246, 281 |
| abstract_inverted_index.an | 74, 104, 207, 306, 365 |
| abstract_inverted_index.as | 18, 67, 184 |
| abstract_inverted_index.by | 62 |
| abstract_inverted_index.in | 79, 143, 158, 179, 181, 188, 193, 206, 213, 243, 252, 305, 317, 342, 364, 394 |
| abstract_inverted_index.is | 35, 38, 103, 108, 168, 315, 401 |
| abstract_inverted_index.it | 238, 373 |
| abstract_inverted_index.of | 13, 30, 41, 47, 64, 90, 94, 100, 117, 120, 161, 201, 221, 229, 248, 258, 270, 293, 321, 346, 351, 383, 404 |
| abstract_inverted_index.on | 44 |
| abstract_inverted_index.or | 76, 85, 191 |
| abstract_inverted_index.to | 53, 73, 134, 145, 209, 239, 261, 308, 367 |
| abstract_inverted_index.we | 152, 196, 241, 284, 378 |
| abstract_inverted_index.HPE | 48, 101, 147, 163 |
| abstract_inverted_index.One | 29 |
| abstract_inverted_index.Our | 170 |
| abstract_inverted_index.The | 88 |
| abstract_inverted_index.and | 8, 23, 130, 172, 251, 276, 297, 336, 354, 360, 371, 386 |
| abstract_inverted_index.can | 71 |
| abstract_inverted_index.for | 224, 278, 289, 298, 302, 375 |
| abstract_inverted_index.gap | 393 |
| abstract_inverted_index.has | 58, 138 |
| abstract_inverted_index.how | 91 |
| abstract_inverted_index.key | 313 |
| abstract_inverted_index.new | 381 |
| abstract_inverted_index.not | 126, 139 |
| abstract_inverted_index.see | 242 |
| abstract_inverted_index.the | 39, 45, 80, 97, 118, 159, 162, 263, 324, 333, 338, 349 |
| abstract_inverted_index.HPE. | 222 |
| abstract_inverted_index.Pose | 1 |
| abstract_inverted_index.been | 59, 127, 140 |
| abstract_inverted_index.fail | 260 |
| abstract_inverted_index.have | 5, 125, 197 |
| abstract_inverted_index.high | 136 |
| abstract_inverted_index.lack | 403 |
| abstract_inverted_index.lead | 72 |
| abstract_inverted_index.make | 372 |
| abstract_inverted_index.show | 26 |
| abstract_inverted_index.such | 17, 66 |
| abstract_inverted_index.that | 34, 107, 272, 316 |
| abstract_inverted_index.this | 150, 282 |
| abstract_inverted_index.well | 141 |
| abstract_inverted_index.were | 358 |
| abstract_inverted_index.when | 165 |
| abstract_inverted_index.wide | 177 |
| abstract_inverted_index.(ALP) | 25 |
| abstract_inverted_index.(HPE) | 3 |
| abstract_inverted_index.(MP), | 20 |
| abstract_inverted_index.(OP), | 22 |
| abstract_inverted_index.Human | 0 |
| abstract_inverted_index.Image | 50 |
| abstract_inverted_index.Tuned | 325, 355 |
| abstract_inverted_index.area. | 112 |
| abstract_inverted_index.calls | 277 |
| abstract_inverted_index.hence | 217 |
| abstract_inverted_index.image | 42, 122, 166, 203, 294, 303, 310 |
| abstract_inverted_index.large | 268 |
| abstract_inverted_index.means | 63 |
| abstract_inverted_index.model | 164, 327, 335, 341 |
| abstract_inverted_index.other | 376 |
| abstract_inverted_index.since | 398 |
| abstract_inverted_index.study | 89, 271, 320 |
| abstract_inverted_index.their | 211 |
| abstract_inverted_index.there | 400 |
| abstract_inverted_index.these | 31, 92 |
| abstract_inverted_index.types | 93, 292 |
| abstract_inverted_index.using | 227 |
| abstract_inverted_index.where | 348 |
| abstract_inverted_index.whose | 15, 55 |
| abstract_inverted_index.yield | 262 |
| abstract_inverted_index.(which | 70 |
| abstract_inverted_index.61.59% | 359 |
| abstract_inverted_index.92.04% | 329 |
| abstract_inverted_index.OpenCV | 230 |
| abstract_inverted_index.Pillow | 228 |
| abstract_inverted_index.RotNet | 326, 340, 353, 356 |
| abstract_inverted_index.areas, | 32 |
| abstract_inverted_index.branch | 12 |
| abstract_inverted_index.degree | 345 |
| abstract_inverted_index.easier | 374 |
| abstract_inverted_index.effort | 307, 366 |
| abstract_inverted_index.future | 369 |
| abstract_inverted_index.images | 54, 133, 185, 385 |
| abstract_inverted_index.impact | 40, 96 |
| abstract_inverted_index.levels | 240 |
| abstract_inverted_index.marked | 27 |
| abstract_inverted_index.models | 4, 102 |
| abstract_inverted_index.nearly | 236 |
| abstract_inverted_index.refers | 52 |
| abstract_inverted_index.study, | 14, 151 |
| abstract_inverted_index.system | 288 |
| abstract_inverted_index.tested | 198 |
| abstract_inverted_index.varied | 6 |
| abstract_inverted_index.visual | 56 |
| abstract_inverted_index.92.04%, | 361 |
| abstract_inverted_index.attempt | 208 |
| abstract_inverted_index.changes | 187 |
| abstract_inverted_index.clearly | 154 |
| abstract_inverted_index.current | 115, 322 |
| abstract_inverted_index.dataset | 382 |
| abstract_inverted_index.decline | 157 |
| abstract_inverted_index.domaina | 106 |
| abstract_inverted_index.enhance | 210 |
| abstract_inverted_index.finding | 314 |
| abstract_inverted_index.further | 274 |
| abstract_inverted_index.images, | 216, 226, 254, 347, 389 |
| abstract_inverted_index.images. | 245 |
| abstract_inverted_index.methods | 116, 205, 257 |
| abstract_inverted_index.models. | 49, 148 |
| abstract_inverted_index.notable | 392 |
| abstract_inverted_index.provide | 379 |
| abstract_inverted_index.quality | 57, 137, 167 |
| abstract_inverted_index.regard, | 283 |
| abstract_inverted_index.related | 319 |
| abstract_inverted_index.restore | 309 |
| abstract_inverted_index.rotated | 225 |
| abstract_inverted_index.systems | 16 |
| abstract_inverted_index.undergo | 186 |
| abstract_inverted_index.variety | 200 |
| abstract_inverted_index.OpenPose | 21 |
| abstract_inverted_index.accuracy | 46, 350 |
| abstract_inverted_index.achieves | 328 |
| abstract_inverted_index.baseline | 334 |
| abstract_inverted_index.decrease | 78 |
| abstract_inverted_index.degraded | 61, 132 |
| abstract_inverted_index.efficacy | 119 |
| abstract_inverted_index.examined | 142 |
| abstract_inverted_index.existing | 121, 202, 256 |
| abstract_inverted_index.however, | 33, 255 |
| abstract_inverted_index.identify | 175 |
| abstract_inverted_index.improved | 219 |
| abstract_inverted_index.improves | 231 |
| abstract_inverted_index.increase | 75 |
| abstract_inverted_index.landmark | 232 |
| abstract_inverted_index.levels), | 82 |
| abstract_inverted_index.methods, | 323 |
| abstract_inverted_index.official | 339, 352 |
| abstract_inverted_index.proposed | 285 |
| abstract_inverted_index.quality. | 311 |
| abstract_inverted_index.relation | 144 |
| abstract_inverted_index.research | 370 |
| abstract_inverted_index.rotation | 344 |
| abstract_inverted_index.studies, | 377, 397 |
| abstract_inverted_index.success. | 28 |
| abstract_inverted_index.warrants | 273 |
| abstract_inverted_index.AlphaPose | 24 |
| abstract_inverted_index.MediaPipe | 19 |
| abstract_inverted_index.accuracy, | 330 |
| abstract_inverted_index.addition, | 114 |
| abstract_inverted_index.currently | 399 |
| abstract_inverted_index.degraded. | 169 |
| abstract_inverted_index.different | 291 |
| abstract_inverted_index.direction | 269 |
| abstract_inverted_index.evaluated | 129 |
| abstract_inverted_index.geometric | 83 |
| abstract_inverted_index.improving | 131, 146 |
| abstract_inverted_index.instances | 247 |
| abstract_inverted_index.intensity | 81 |
| abstract_inverted_index.landmarks | 183 |
| abstract_inverted_index.precision | 160, 234 |
| abstract_inverted_index.reference | 384 |
| abstract_inverted_index.represent | 9 |
| abstract_inverted_index.research. | 280 |
| abstract_inverted_index.restoring | 214, 237 |
| abstract_inverted_index.rotation, | 190 |
| abstract_inverted_index.selecting | 299 |
| abstract_inverted_index.variation | 250 |
| abstract_inverted_index.virtually | 110 |
| abstract_inverted_index.Estimation | 2 |
| abstract_inverted_index.additional | 279 |
| abstract_inverted_index.addressing | 390 |
| abstract_inverted_index.algorithms | 301 |
| abstract_inverted_index.brightness | 68, 249 |
| abstract_inverted_index.capability | 212 |
| abstract_inverted_index.controlled | 395, 405 |
| abstract_inverted_index.difference | 178 |
| abstract_inverted_index.explicitly | 153 |
| abstract_inverted_index.facilitate | 368 |
| abstract_inverted_index.predicting | 343 |
| abstract_inverted_index.reductions | 192 |
| abstract_inverted_index.researched | 37 |
| abstract_inverted_index.resolution | 86 |
| abstract_inverted_index.rigorously | 128 |
| abstract_inverted_index.rotations, | 84 |
| abstract_inverted_index.supporting | 218 |
| abstract_inverted_index.surpassing | 337 |
| abstract_inverted_index.techniques | 124 |
| abstract_inverted_index.unexplored | 111 |
| abstract_inverted_index.adjustments | 69 |
| abstract_inverted_index.appropriate | 300 |
| abstract_inverted_index.brightness, | 189 |
| abstract_inverted_index.classifiers | 357 |
| abstract_inverted_index.classifying | 290 |
| abstract_inverted_index.comparative | 396 |
| abstract_inverted_index.degenerated | 388 |
| abstract_inverted_index.degradation | 43, 51, 95, 295 |
| abstract_inverted_index.demonstrate | 155 |
| abstract_inverted_index.enhancement | 204, 259 |
| abstract_inverted_index.identifying | 182 |
| abstract_inverted_index.low-quality | 215, 253 |
| abstract_inverted_index.performance | 98, 180 |
| abstract_inverted_index.qualitative | 171 |
| abstract_inverted_index.recognition | 233 |
| abstract_inverted_index.resolution. | 194 |
| abstract_inverted_index.restoration | 123 |
| abstract_inverted_index.techniques, | 65 |
| abstract_inverted_index.Furthermore, | 363 |
| abstract_inverted_index.anticipated, | 265 |
| abstract_inverted_index.applications | 7 |
| abstract_inverted_index.cutting-edge | 11 |
| abstract_inverted_index.downscaling. | 87 |
| abstract_inverted_index.drastically, | 235 |
| abstract_inverted_index.high-quality | 244 |
| abstract_inverted_index.highlighting | 266 |
| abstract_inverted_index.improvements | 264 |
| abstract_inverted_index.inadequately | 36 |
| abstract_inverted_index.measurements | 174 |
| abstract_inverted_index.purposefully | 60 |
| abstract_inverted_index.quantitative | 173 |
| abstract_inverted_index.restoration, | 304 |
| abstract_inverted_index.wide-ranging | 287 |
| abstract_inverted_index.Additionally, | 195 |
| abstract_inverted_index.comparatives. | 406 |
| abstract_inverted_index.corresponding | 387 |
| abstract_inverted_index.functionality | 99, 220 |
| abstract_inverted_index.investigation | 275 |
| abstract_inverted_index.outperforming | 332 |
| abstract_inverted_index.respectively. | 362 |
| abstract_inverted_index.significantly | 331 |
| abstract_inverted_index.Interestingly, | 223 |
| abstract_inverted_index.systematically | 296 |
| abstract_inverted_index.under-researched | 105 |
| cited_by_percentile_year | |
| countries_distinct_count | 2 |
| institutions_distinct_count | 4 |
| citation_normalized_percentile |