Improving Real-Time Small Objects Detection by Fusion Features of Spatial Coordinates Article Swipe
Qianjiang Yu
,
Tongyuan Huang
,
Weifeng Zhang
,
Jia Xu
,
Yunze He
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.21203/rs.3.rs-2717722/v1
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.21203/rs.3.rs-2717722/v1
The small-object detection challenge has long limited the advanced development of deep learning-based detection models. The downsampling of visual models leads to a severe loss of spatial information of small objects causing a great increase in the difficulty of models to capture the location of small ones. Inspired by the logic of human visual perception behavior, we found that the main limitation of small object detection is the position regression rather than category differentiation. Therefore, we first introduce coordinate features to perform multi-scale spatial information perception and element-level width and height independent coordinate encoding of image features in anticipation of easing the difficulty of small-object detection by convolutional neural network models. Secondly, we design a lightweight one-stage detector for the real-time small-object detection task based on the coordinate feature scheme and dense prediction architecture, and different lightweight cross-stage locally connected fusion attention methods are also proposed for feature maps of different scales suitable for use, including GSCSP-S and GSCSP-A. Finally, we take only 7 million parameters in VisDrone2019 UAV detection benchmark task accomplishes a test performance of 32.3% mAP, which provides a superior accuracy-speed tradeoff compared to current state-of-the-art one-stage real-time detectors of the same size.
Related Topics
Concepts
Computer science
Artificial intelligence
Object detection
Benchmark (surveying)
Upsampling
Feature (linguistics)
Computer vision
Convolutional neural network
Pattern recognition (psychology)
Object (grammar)
Position (finance)
Image (mathematics)
Geography
Philosophy
Economics
Linguistics
Geodesy
Finance
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- https://doi.org/10.21203/rs.3.rs-2717722/v1
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4360618747
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4360618747Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.21203/rs.3.rs-2717722/v1Digital Object Identifier
- Title
-
Improving Real-Time Small Objects Detection by Fusion Features of Spatial CoordinatesWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-03-23Full publication date if available
- Authors
-
Qianjiang Yu, Tongyuan Huang, Weifeng Zhang, Jia Xu, Yunze HeList of authors in order
- Landing page
-
https://doi.org/10.21203/rs.3.rs-2717722/v1Publisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://doi.org/10.21203/rs.3.rs-2717722/v1Direct OA link when available
- Concepts
-
Computer science, Artificial intelligence, Object detection, Benchmark (surveying), Upsampling, Feature (linguistics), Computer vision, Convolutional neural network, Pattern recognition (psychology), Object (grammar), Position (finance), Image (mathematics), Geography, Philosophy, Economics, Linguistics, Geodesy, FinanceTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4360618747 |
|---|---|
| doi | https://doi.org/10.21203/rs.3.rs-2717722/v1 |
| ids.doi | https://doi.org/10.21203/rs.3.rs-2717722/v1 |
| ids.openalex | https://openalex.org/W4360618747 |
| fwci | 0.0 |
| type | preprint |
| title | Improving Real-Time Small Objects Detection by Fusion Features of Spatial Coordinates |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10036 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9994999766349792 |
| 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 | Advanced Neural Network Applications |
| topics[1].id | https://openalex.org/T12389 |
| topics[1].field.id | https://openalex.org/fields/22 |
| topics[1].field.display_name | Engineering |
| topics[1].score | 0.996999979019165 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/2202 |
| topics[1].subfield.display_name | Aerospace Engineering |
| topics[1].display_name | Infrared Target Detection Methodologies |
| topics[2].id | https://openalex.org/T10627 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9896000027656555 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1707 |
| topics[2].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[2].display_name | Advanced Image and Video Retrieval Techniques |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.7406824231147766 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C154945302 |
| concepts[1].level | 1 |
| concepts[1].score | 0.7159446477890015 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[1].display_name | Artificial intelligence |
| concepts[2].id | https://openalex.org/C2776151529 |
| concepts[2].level | 3 |
| concepts[2].score | 0.6206979751586914 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q3045304 |
| concepts[2].display_name | Object detection |
| concepts[3].id | https://openalex.org/C185798385 |
| concepts[3].level | 2 |
| concepts[3].score | 0.569862961769104 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q1161707 |
| concepts[3].display_name | Benchmark (surveying) |
| concepts[4].id | https://openalex.org/C110384440 |
| concepts[4].level | 3 |
| concepts[4].score | 0.5633894205093384 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q1143270 |
| concepts[4].display_name | Upsampling |
| concepts[5].id | https://openalex.org/C2776401178 |
| concepts[5].level | 2 |
| concepts[5].score | 0.5380496382713318 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q12050496 |
| concepts[5].display_name | Feature (linguistics) |
| concepts[6].id | https://openalex.org/C31972630 |
| concepts[6].level | 1 |
| concepts[6].score | 0.524782121181488 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q844240 |
| concepts[6].display_name | Computer vision |
| concepts[7].id | https://openalex.org/C81363708 |
| concepts[7].level | 2 |
| concepts[7].score | 0.5054738521575928 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q17084460 |
| concepts[7].display_name | Convolutional neural network |
| concepts[8].id | https://openalex.org/C153180895 |
| concepts[8].level | 2 |
| concepts[8].score | 0.48994630575180054 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[8].display_name | Pattern recognition (psychology) |
| concepts[9].id | https://openalex.org/C2781238097 |
| concepts[9].level | 2 |
| concepts[9].score | 0.4526136517524719 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q175026 |
| concepts[9].display_name | Object (grammar) |
| concepts[10].id | https://openalex.org/C198082294 |
| concepts[10].level | 2 |
| concepts[10].score | 0.449042946100235 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q3399648 |
| concepts[10].display_name | Position (finance) |
| concepts[11].id | https://openalex.org/C115961682 |
| concepts[11].level | 2 |
| concepts[11].score | 0.1547602117061615 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q860623 |
| concepts[11].display_name | Image (mathematics) |
| concepts[12].id | https://openalex.org/C205649164 |
| concepts[12].level | 0 |
| concepts[12].score | 0.10255557298660278 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q1071 |
| concepts[12].display_name | Geography |
| concepts[13].id | https://openalex.org/C138885662 |
| concepts[13].level | 0 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[13].display_name | Philosophy |
| concepts[14].id | https://openalex.org/C162324750 |
| concepts[14].level | 0 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q8134 |
| concepts[14].display_name | Economics |
| concepts[15].id | https://openalex.org/C41895202 |
| concepts[15].level | 1 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q8162 |
| concepts[15].display_name | Linguistics |
| concepts[16].id | https://openalex.org/C13280743 |
| concepts[16].level | 1 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q131089 |
| concepts[16].display_name | Geodesy |
| concepts[17].id | https://openalex.org/C10138342 |
| concepts[17].level | 1 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q43015 |
| concepts[17].display_name | Finance |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.7406824231147766 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[1].score | 0.7159446477890015 |
| keywords[1].display_name | Artificial intelligence |
| keywords[2].id | https://openalex.org/keywords/object-detection |
| keywords[2].score | 0.6206979751586914 |
| keywords[2].display_name | Object detection |
| keywords[3].id | https://openalex.org/keywords/benchmark |
| keywords[3].score | 0.569862961769104 |
| keywords[3].display_name | Benchmark (surveying) |
| keywords[4].id | https://openalex.org/keywords/upsampling |
| keywords[4].score | 0.5633894205093384 |
| keywords[4].display_name | Upsampling |
| keywords[5].id | https://openalex.org/keywords/feature |
| keywords[5].score | 0.5380496382713318 |
| keywords[5].display_name | Feature (linguistics) |
| keywords[6].id | https://openalex.org/keywords/computer-vision |
| keywords[6].score | 0.524782121181488 |
| keywords[6].display_name | Computer vision |
| keywords[7].id | https://openalex.org/keywords/convolutional-neural-network |
| keywords[7].score | 0.5054738521575928 |
| keywords[7].display_name | Convolutional neural network |
| keywords[8].id | https://openalex.org/keywords/pattern-recognition |
| keywords[8].score | 0.48994630575180054 |
| keywords[8].display_name | Pattern recognition (psychology) |
| keywords[9].id | https://openalex.org/keywords/object |
| keywords[9].score | 0.4526136517524719 |
| keywords[9].display_name | Object (grammar) |
| keywords[10].id | https://openalex.org/keywords/position |
| keywords[10].score | 0.449042946100235 |
| keywords[10].display_name | Position (finance) |
| keywords[11].id | https://openalex.org/keywords/image |
| keywords[11].score | 0.1547602117061615 |
| keywords[11].display_name | Image (mathematics) |
| keywords[12].id | https://openalex.org/keywords/geography |
| keywords[12].score | 0.10255557298660278 |
| keywords[12].display_name | Geography |
| language | en |
| locations[0].id | doi:10.21203/rs.3.rs-2717722/v1 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306402450 |
| 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 | Research Square (Research Square) |
| locations[0].source.host_organization | https://openalex.org/I4210096694 |
| locations[0].source.host_organization_name | Research Square (United States) |
| locations[0].source.host_organization_lineage | https://openalex.org/I4210096694 |
| locations[0].license | cc-by |
| locations[0].pdf_url | |
| locations[0].version | acceptedVersion |
| locations[0].raw_type | posted-content |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | True |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | https://doi.org/10.21203/rs.3.rs-2717722/v1 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5023698044 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Qianjiang Yu |
| authorships[0].countries | CN |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I50632499 |
| authorships[0].affiliations[0].raw_affiliation_string | School of Artificial Intelligence, Chongqing University of Technology |
| authorships[0].institutions[0].id | https://openalex.org/I50632499 |
| authorships[0].institutions[0].ror | https://ror.org/04vgbd477 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I50632499 |
| authorships[0].institutions[0].country_code | CN |
| authorships[0].institutions[0].display_name | Chongqing University of Technology |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Qianjiang Yu |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | School of Artificial Intelligence, Chongqing University of Technology |
| authorships[1].author.id | https://openalex.org/A5079089150 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-3155-6728 |
| authorships[1].author.display_name | Tongyuan Huang |
| authorships[1].countries | CN |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I50632499 |
| authorships[1].affiliations[0].raw_affiliation_string | School of Artificial Intelligence, Chongqing University of Technology |
| authorships[1].institutions[0].id | https://openalex.org/I50632499 |
| authorships[1].institutions[0].ror | https://ror.org/04vgbd477 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I50632499 |
| authorships[1].institutions[0].country_code | CN |
| authorships[1].institutions[0].display_name | Chongqing University of Technology |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Tongyuan Huang |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | School of Artificial Intelligence, Chongqing University of Technology |
| authorships[2].author.id | https://openalex.org/A5100426672 |
| authorships[2].author.orcid | https://orcid.org/0000-0001-6454-1314 |
| authorships[2].author.display_name | Weifeng Zhang |
| authorships[2].countries | CN |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I50632499 |
| authorships[2].affiliations[0].raw_affiliation_string | School of Artificial Intelligence, Chongqing University of Technology |
| authorships[2].institutions[0].id | https://openalex.org/I50632499 |
| authorships[2].institutions[0].ror | https://ror.org/04vgbd477 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I50632499 |
| authorships[2].institutions[0].country_code | CN |
| authorships[2].institutions[0].display_name | Chongqing University of Technology |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Weifeng Zhang |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | School of Artificial Intelligence, Chongqing University of Technology |
| authorships[3].author.id | https://openalex.org/A5044793383 |
| authorships[3].author.orcid | https://orcid.org/0000-0001-9699-6073 |
| authorships[3].author.display_name | Jia Xu |
| authorships[3].countries | CN |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I50632499 |
| authorships[3].affiliations[0].raw_affiliation_string | School of Artificial Intelligence, Chongqing University of Technology |
| authorships[3].institutions[0].id | https://openalex.org/I50632499 |
| authorships[3].institutions[0].ror | https://ror.org/04vgbd477 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I50632499 |
| authorships[3].institutions[0].country_code | CN |
| authorships[3].institutions[0].display_name | Chongqing University of Technology |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Jia Xu |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | School of Artificial Intelligence, Chongqing University of Technology |
| authorships[4].author.id | https://openalex.org/A5081305539 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-7081-8225 |
| authorships[4].author.display_name | Yunze He |
| authorships[4].countries | CN |
| authorships[4].affiliations[0].institution_ids | https://openalex.org/I50632499 |
| authorships[4].affiliations[0].raw_affiliation_string | School of Artificial Intelligence, Chongqing University of Technology |
| authorships[4].institutions[0].id | https://openalex.org/I50632499 |
| authorships[4].institutions[0].ror | https://ror.org/04vgbd477 |
| authorships[4].institutions[0].type | education |
| authorships[4].institutions[0].lineage | https://openalex.org/I50632499 |
| authorships[4].institutions[0].country_code | CN |
| authorships[4].institutions[0].display_name | Chongqing University of Technology |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Yunze He |
| authorships[4].is_corresponding | False |
| authorships[4].raw_affiliation_strings | School of Artificial Intelligence, Chongqing University of Technology |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://doi.org/10.21203/rs.3.rs-2717722/v1 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Improving Real-Time Small Objects Detection by Fusion Features of Spatial Coordinates |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T10036 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9994999766349792 |
| 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 | Advanced Neural Network Applications |
| related_works | https://openalex.org/W2062399876, https://openalex.org/W2607795551, https://openalex.org/W3155117723, https://openalex.org/W1991429770, https://openalex.org/W1983892167, https://openalex.org/W2281134365, https://openalex.org/W4310746709, https://openalex.org/W4287991909, https://openalex.org/W4390721878, https://openalex.org/W2969228573 |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | doi:10.21203/rs.3.rs-2717722/v1 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306402450 |
| 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 | Research Square (Research Square) |
| best_oa_location.source.host_organization | https://openalex.org/I4210096694 |
| best_oa_location.source.host_organization_name | Research Square (United States) |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I4210096694 |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | |
| best_oa_location.version | acceptedVersion |
| best_oa_location.raw_type | posted-content |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | https://doi.org/10.21203/rs.3.rs-2717722/v1 |
| primary_location.id | doi:10.21203/rs.3.rs-2717722/v1 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306402450 |
| 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 | Research Square (Research Square) |
| primary_location.source.host_organization | https://openalex.org/I4210096694 |
| primary_location.source.host_organization_name | Research Square (United States) |
| primary_location.source.host_organization_lineage | https://openalex.org/I4210096694 |
| primary_location.license | cc-by |
| primary_location.pdf_url | |
| primary_location.version | acceptedVersion |
| primary_location.raw_type | posted-content |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | True |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | https://doi.org/10.21203/rs.3.rs-2717722/v1 |
| publication_date | 2023-03-23 |
| publication_year | 2023 |
| referenced_works_count | 0 |
| abstract_inverted_index.7 | 164 |
| abstract_inverted_index.a | 23, 33, 115, 174, 182 |
| abstract_inverted_index.by | 49, 107 |
| abstract_inverted_index.in | 36, 98, 167 |
| abstract_inverted_index.is | 67 |
| abstract_inverted_index.of | 11, 18, 26, 29, 39, 45, 52, 63, 95, 100, 104, 150, 177, 193 |
| abstract_inverted_index.on | 126 |
| abstract_inverted_index.to | 22, 41, 81, 187 |
| abstract_inverted_index.we | 57, 76, 113, 161 |
| abstract_inverted_index.The | 1, 16 |
| abstract_inverted_index.UAV | 169 |
| abstract_inverted_index.and | 87, 90, 131, 135, 158 |
| abstract_inverted_index.are | 144 |
| abstract_inverted_index.for | 119, 147, 154 |
| abstract_inverted_index.has | 5 |
| abstract_inverted_index.the | 8, 37, 43, 50, 60, 68, 102, 120, 127, 194 |
| abstract_inverted_index.also | 145 |
| abstract_inverted_index.deep | 12 |
| abstract_inverted_index.long | 6 |
| abstract_inverted_index.loss | 25 |
| abstract_inverted_index.mAP, | 179 |
| abstract_inverted_index.main | 61 |
| abstract_inverted_index.maps | 149 |
| abstract_inverted_index.only | 163 |
| abstract_inverted_index.same | 195 |
| abstract_inverted_index.take | 162 |
| abstract_inverted_index.task | 124, 172 |
| abstract_inverted_index.test | 175 |
| abstract_inverted_index.than | 72 |
| abstract_inverted_index.that | 59 |
| abstract_inverted_index.use, | 155 |
| abstract_inverted_index.32.3% | 178 |
| abstract_inverted_index.based | 125 |
| abstract_inverted_index.dense | 132 |
| abstract_inverted_index.first | 77 |
| abstract_inverted_index.found | 58 |
| abstract_inverted_index.great | 34 |
| abstract_inverted_index.human | 53 |
| abstract_inverted_index.image | 96 |
| abstract_inverted_index.leads | 21 |
| abstract_inverted_index.logic | 51 |
| abstract_inverted_index.ones. | 47 |
| abstract_inverted_index.size. | 196 |
| abstract_inverted_index.small | 30, 46, 64 |
| abstract_inverted_index.which | 180 |
| abstract_inverted_index.width | 89 |
| abstract_inverted_index.design | 114 |
| abstract_inverted_index.easing | 101 |
| abstract_inverted_index.fusion | 141 |
| abstract_inverted_index.height | 91 |
| abstract_inverted_index.models | 20, 40 |
| abstract_inverted_index.neural | 109 |
| abstract_inverted_index.object | 65 |
| abstract_inverted_index.rather | 71 |
| abstract_inverted_index.scales | 152 |
| abstract_inverted_index.scheme | 130 |
| abstract_inverted_index.severe | 24 |
| abstract_inverted_index.visual | 19, 54 |
| abstract_inverted_index.GSCSP-S | 157 |
| abstract_inverted_index.capture | 42 |
| abstract_inverted_index.causing | 32 |
| abstract_inverted_index.current | 188 |
| abstract_inverted_index.feature | 129, 148 |
| abstract_inverted_index.limited | 7 |
| abstract_inverted_index.locally | 139 |
| abstract_inverted_index.methods | 143 |
| abstract_inverted_index.million | 165 |
| abstract_inverted_index.models. | 15, 111 |
| abstract_inverted_index.network | 110 |
| abstract_inverted_index.objects | 31 |
| abstract_inverted_index.perform | 82 |
| abstract_inverted_index.spatial | 27, 84 |
| abstract_inverted_index.Finally, | 160 |
| abstract_inverted_index.GSCSP-A. | 159 |
| abstract_inverted_index.Inspired | 48 |
| abstract_inverted_index.advanced | 9 |
| abstract_inverted_index.category | 73 |
| abstract_inverted_index.compared | 186 |
| abstract_inverted_index.detector | 118 |
| abstract_inverted_index.encoding | 94 |
| abstract_inverted_index.features | 80, 97 |
| abstract_inverted_index.increase | 35 |
| abstract_inverted_index.location | 44 |
| abstract_inverted_index.position | 69 |
| abstract_inverted_index.proposed | 146 |
| abstract_inverted_index.provides | 181 |
| abstract_inverted_index.suitable | 153 |
| abstract_inverted_index.superior | 183 |
| abstract_inverted_index.tradeoff | 185 |
| abstract_inverted_index.Secondly, | 112 |
| abstract_inverted_index.attention | 142 |
| abstract_inverted_index.behavior, | 56 |
| abstract_inverted_index.benchmark | 171 |
| abstract_inverted_index.challenge | 4 |
| abstract_inverted_index.connected | 140 |
| abstract_inverted_index.detection | 3, 14, 66, 106, 123, 170 |
| abstract_inverted_index.detectors | 192 |
| abstract_inverted_index.different | 136, 151 |
| abstract_inverted_index.including | 156 |
| abstract_inverted_index.introduce | 78 |
| abstract_inverted_index.one-stage | 117, 190 |
| abstract_inverted_index.real-time | 121, 191 |
| abstract_inverted_index.Therefore, | 75 |
| abstract_inverted_index.coordinate | 79, 93, 128 |
| abstract_inverted_index.difficulty | 38, 103 |
| abstract_inverted_index.limitation | 62 |
| abstract_inverted_index.parameters | 166 |
| abstract_inverted_index.perception | 55, 86 |
| abstract_inverted_index.prediction | 133 |
| abstract_inverted_index.regression | 70 |
| abstract_inverted_index.cross-stage | 138 |
| abstract_inverted_index.development | 10 |
| abstract_inverted_index.independent | 92 |
| abstract_inverted_index.information | 28, 85 |
| abstract_inverted_index.lightweight | 116, 137 |
| abstract_inverted_index.multi-scale | 83 |
| abstract_inverted_index.performance | 176 |
| abstract_inverted_index.VisDrone2019 | 168 |
| abstract_inverted_index.accomplishes | 173 |
| abstract_inverted_index.anticipation | 99 |
| abstract_inverted_index.downsampling | 17 |
| abstract_inverted_index.small-object | 2, 105, 122 |
| abstract_inverted_index.architecture, | 134 |
| abstract_inverted_index.convolutional | 108 |
| abstract_inverted_index.element-level | 88 |
| abstract_inverted_index.accuracy-speed | 184 |
| abstract_inverted_index.learning-based | 13 |
| abstract_inverted_index.differentiation. | 74 |
| abstract_inverted_index.state-of-the-art | 189 |
| abstract_inverted_index.<title>Abstract</title> | 0 |
| cited_by_percentile_year | |
| countries_distinct_count | 1 |
| institutions_distinct_count | 5 |
| citation_normalized_percentile.value | 0.02497399 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |