Contrastive Proposal Extension with LSTM Network for Weakly Supervised Object Detection Article Swipe
Pei Lv
,
Suqi Hu
,
Tianran Hao
,
Haohan Ji
,
Lisha Cui
,
Haoyi Fan
,
Mingliang Xu
,
Changsheng Xu
·
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2110.07511
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2110.07511
Weakly supervised object detection (WSOD) has attracted more and more attention since it only uses image-level labels and can save huge annotation costs. Most of the WSOD methods use Multiple Instance Learning (MIL) as their basic framework, which regard it as an instance classification problem. However, these methods based on MIL tends to converge only on the most discriminate regions of different instances, rather than their corresponding complete regions, that is, insufficient integrity. Inspired by the habit of observing things by the human, we propose a new method by comparing the initial proposals and the extension ones to optimize those initial proposals. Specifically, we propose one new strategy for WSOD by involving contrastive proposal extension (CPE), which consists of multiple directional contrastive proposal extensions (D-CPE), and each D-CPE contains encoders based on LSTM network and corresponding decoders. Firstly, the boundary of initial proposals in MIL is extended to different positions according to well-designed sequential order. Then, CPE compares the extended proposal and the initial proposal by extracting the feature semantics of them using the encoders, and calculates the integrity of the initial proposal to optimize the score of the initial proposal. These contrastive contextual semantics will guide the basic WSOD to suppress bad proposals and improve the scores of good ones. In addition, a simple two-stream network is designed as the decoder to constrain the temporal coding of LSTM and improve the performance of WSOD further. Experiments on PASCAL VOC 2007, VOC 2012 and MS-COCO datasets show that our method has achieved the state-of-the-art results.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2110.07511
- https://arxiv.org/pdf/2110.07511
- OA Status
- green
- Cited By
- 2
- References
- 53
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W3205283899
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W3205283899Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2110.07511Digital Object Identifier
- Title
-
Contrastive Proposal Extension with LSTM Network for Weakly Supervised Object DetectionWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2021Year of publication
- Publication date
-
2021-10-14Full publication date if available
- Authors
-
Pei Lv, Suqi Hu, Tianran Hao, Haohan Ji, Lisha Cui, Haoyi Fan, Mingliang Xu, Changsheng XuList of authors in order
- Landing page
-
https://arxiv.org/abs/2110.07511Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2110.07511Direct 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/2110.07511Direct OA link when available
- Concepts
-
Computer science, Pascal (unit), Extension (predicate logic), Annotation, Artificial intelligence, Encoder, Object (grammar), Pattern recognition (psychology), Semantics (computer science), Feature (linguistics), Natural language processing, Programming language, Operating system, Linguistics, PhilosophyTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
2Total citation count in OpenAlex
- Citations by year (recent)
-
2023: 2Per-year citation counts (last 5 years)
- References (count)
-
53Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W3205283899 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2110.07511 |
| ids.doi | https://doi.org/10.48550/arxiv.2110.07511 |
| ids.mag | 3205283899 |
| ids.openalex | https://openalex.org/W3205283899 |
| fwci | 0.20443896 |
| type | preprint |
| title | Contrastive Proposal Extension with LSTM Network for Weakly Supervised Object Detection |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10627 |
| 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 Image and Video Retrieval Techniques |
| topics[1].id | https://openalex.org/T10036 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9979000091552734 |
| 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 Neural Network Applications |
| topics[2].id | https://openalex.org/T11307 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9945999979972839 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1702 |
| topics[2].subfield.display_name | Artificial Intelligence |
| topics[2].display_name | Domain Adaptation and Few-Shot Learning |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.786095380783081 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C75608658 |
| concepts[1].level | 2 |
| concepts[1].score | 0.7169617414474487 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q44395 |
| concepts[1].display_name | Pascal (unit) |
| concepts[2].id | https://openalex.org/C2778029271 |
| concepts[2].level | 2 |
| concepts[2].score | 0.5590105056762695 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q5421931 |
| concepts[2].display_name | Extension (predicate logic) |
| concepts[3].id | https://openalex.org/C2776321320 |
| concepts[3].level | 2 |
| concepts[3].score | 0.535487949848175 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q857525 |
| concepts[3].display_name | Annotation |
| concepts[4].id | https://openalex.org/C154945302 |
| concepts[4].level | 1 |
| concepts[4].score | 0.5276780724525452 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[4].display_name | Artificial intelligence |
| concepts[5].id | https://openalex.org/C118505674 |
| concepts[5].level | 2 |
| concepts[5].score | 0.49419286847114563 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q42586063 |
| concepts[5].display_name | Encoder |
| concepts[6].id | https://openalex.org/C2781238097 |
| concepts[6].level | 2 |
| concepts[6].score | 0.4510357975959778 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q175026 |
| concepts[6].display_name | Object (grammar) |
| concepts[7].id | https://openalex.org/C153180895 |
| concepts[7].level | 2 |
| concepts[7].score | 0.44940468668937683 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[7].display_name | Pattern recognition (psychology) |
| concepts[8].id | https://openalex.org/C184337299 |
| concepts[8].level | 2 |
| concepts[8].score | 0.43684256076812744 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q1437428 |
| concepts[8].display_name | Semantics (computer science) |
| concepts[9].id | https://openalex.org/C2776401178 |
| concepts[9].level | 2 |
| concepts[9].score | 0.43222230672836304 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q12050496 |
| concepts[9].display_name | Feature (linguistics) |
| concepts[10].id | https://openalex.org/C204321447 |
| concepts[10].level | 1 |
| concepts[10].score | 0.3476562798023224 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[10].display_name | Natural language processing |
| concepts[11].id | https://openalex.org/C199360897 |
| concepts[11].level | 1 |
| concepts[11].score | 0.09418180584907532 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q9143 |
| concepts[11].display_name | Programming language |
| concepts[12].id | https://openalex.org/C111919701 |
| concepts[12].level | 1 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q9135 |
| concepts[12].display_name | Operating system |
| concepts[13].id | https://openalex.org/C41895202 |
| concepts[13].level | 1 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q8162 |
| concepts[13].display_name | Linguistics |
| concepts[14].id | https://openalex.org/C138885662 |
| concepts[14].level | 0 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[14].display_name | Philosophy |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.786095380783081 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/pascal |
| keywords[1].score | 0.7169617414474487 |
| keywords[1].display_name | Pascal (unit) |
| keywords[2].id | https://openalex.org/keywords/extension |
| keywords[2].score | 0.5590105056762695 |
| keywords[2].display_name | Extension (predicate logic) |
| keywords[3].id | https://openalex.org/keywords/annotation |
| keywords[3].score | 0.535487949848175 |
| keywords[3].display_name | Annotation |
| keywords[4].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[4].score | 0.5276780724525452 |
| keywords[4].display_name | Artificial intelligence |
| keywords[5].id | https://openalex.org/keywords/encoder |
| keywords[5].score | 0.49419286847114563 |
| keywords[5].display_name | Encoder |
| keywords[6].id | https://openalex.org/keywords/object |
| keywords[6].score | 0.4510357975959778 |
| keywords[6].display_name | Object (grammar) |
| keywords[7].id | https://openalex.org/keywords/pattern-recognition |
| keywords[7].score | 0.44940468668937683 |
| keywords[7].display_name | Pattern recognition (psychology) |
| keywords[8].id | https://openalex.org/keywords/semantics |
| keywords[8].score | 0.43684256076812744 |
| keywords[8].display_name | Semantics (computer science) |
| keywords[9].id | https://openalex.org/keywords/feature |
| keywords[9].score | 0.43222230672836304 |
| keywords[9].display_name | Feature (linguistics) |
| keywords[10].id | https://openalex.org/keywords/natural-language-processing |
| keywords[10].score | 0.3476562798023224 |
| keywords[10].display_name | Natural language processing |
| keywords[11].id | https://openalex.org/keywords/programming-language |
| keywords[11].score | 0.09418180584907532 |
| keywords[11].display_name | Programming language |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2110.07511 |
| 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/2110.07511 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| 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/2110.07511 |
| locations[1].id | doi:10.48550/arxiv.2110.07511 |
| 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-journal |
| 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.2110.07511 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5069492002 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-2654-0561 |
| authorships[0].author.display_name | Pei Lv |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Pei Lv |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5036703488 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Suqi Hu |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Suqi Hu |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5082673454 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-3416-464X |
| authorships[2].author.display_name | Tianran Hao |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Tianran Hao |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5019230793 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Haohan Ji |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Haohan Ji |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5103121791 |
| authorships[4].author.orcid | https://orcid.org/0009-0002-8570-5482 |
| authorships[4].author.display_name | Lisha Cui |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Lisha Cui |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5005638593 |
| authorships[5].author.orcid | https://orcid.org/0000-0001-9428-7812 |
| authorships[5].author.display_name | Haoyi Fan |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Haoyi Fan |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5081346568 |
| authorships[6].author.orcid | https://orcid.org/0000-0002-6885-3451 |
| authorships[6].author.display_name | Mingliang Xu |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Mingliang Xu |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5022636178 |
| authorships[7].author.orcid | https://orcid.org/0000-0001-8343-9665 |
| authorships[7].author.display_name | Changsheng Xu |
| authorships[7].author_position | last |
| authorships[7].raw_author_name | Changsheng Xu |
| authorships[7].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/2110.07511 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Contrastive Proposal Extension with LSTM Network for Weakly Supervised Object Detection |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10627 |
| 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 Image and Video Retrieval Techniques |
| related_works | https://openalex.org/W2361861616, https://openalex.org/W2263699433, https://openalex.org/W2377979023, https://openalex.org/W2218034408, https://openalex.org/W2392921965, https://openalex.org/W2358755282, https://openalex.org/W2625833328, https://openalex.org/W2069133146, https://openalex.org/W1533177136, https://openalex.org/W1663079876 |
| cited_by_count | 2 |
| counts_by_year[0].year | 2023 |
| counts_by_year[0].cited_by_count | 2 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2110.07511 |
| 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/2110.07511 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| 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/2110.07511 |
| primary_location.id | pmh:oai:arXiv.org:2110.07511 |
| 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/2110.07511 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| 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/2110.07511 |
| publication_date | 2021-10-14 |
| publication_year | 2021 |
| referenced_works | https://openalex.org/W3099828125, https://openalex.org/W3116963012, https://openalex.org/W2309415944, https://openalex.org/W2969764577, https://openalex.org/W2798748179, https://openalex.org/W2037227137, https://openalex.org/W3126494835, https://openalex.org/W2613833277, https://openalex.org/W2991533779, https://openalex.org/W2891894830, https://openalex.org/W2016016818, https://openalex.org/W2994041372, https://openalex.org/W2061629163, https://openalex.org/W2892522889, https://openalex.org/W2990400263, https://openalex.org/W2031489346, https://openalex.org/W2604260814, https://openalex.org/W1536680647, https://openalex.org/W3109481033, https://openalex.org/W2064675550, https://openalex.org/W607748843, https://openalex.org/W2963093690, https://openalex.org/W2963403868, https://openalex.org/W2944938209, https://openalex.org/W2954087924, https://openalex.org/W2798269247, https://openalex.org/W2963254348, https://openalex.org/W2298838696, https://openalex.org/W2964328846, https://openalex.org/W2088049833, https://openalex.org/W2441255125, https://openalex.org/W2813911573, https://openalex.org/W2799177530, https://openalex.org/W2559348937, https://openalex.org/W2517617019, https://openalex.org/W1686810756, https://openalex.org/W3017351200, https://openalex.org/W318792885, https://openalex.org/W2997125355, https://openalex.org/W3035725370, https://openalex.org/W2288122362, https://openalex.org/W2267126114, https://openalex.org/W2963952323, https://openalex.org/W2962758679, https://openalex.org/W2963603913, https://openalex.org/W1861492603, https://openalex.org/W2168804568, https://openalex.org/W2220111505, https://openalex.org/W3034329658, https://openalex.org/W2991662170, https://openalex.org/W2962858109, https://openalex.org/W2895038424, https://openalex.org/W1934621328 |
| referenced_works_count | 53 |
| abstract_inverted_index.a | 85, 213 |
| abstract_inverted_index.In | 211 |
| abstract_inverted_index.an | 41 |
| abstract_inverted_index.as | 33, 40, 219 |
| abstract_inverted_index.by | 74, 80, 88, 110, 165 |
| abstract_inverted_index.in | 143 |
| abstract_inverted_index.is | 145, 217 |
| abstract_inverted_index.it | 12, 39 |
| abstract_inverted_index.of | 24, 60, 77, 118, 140, 170, 179, 187, 208, 227, 233 |
| abstract_inverted_index.on | 49, 55, 131, 237 |
| abstract_inverted_index.to | 52, 97, 147, 151, 183, 200, 222 |
| abstract_inverted_index.we | 83, 103 |
| abstract_inverted_index.CPE | 156 |
| abstract_inverted_index.MIL | 50, 144 |
| abstract_inverted_index.VOC | 239, 241 |
| abstract_inverted_index.and | 8, 17, 93, 125, 134, 161, 175, 204, 229, 243 |
| abstract_inverted_index.bad | 202 |
| abstract_inverted_index.can | 18 |
| abstract_inverted_index.for | 108 |
| abstract_inverted_index.has | 5, 250 |
| abstract_inverted_index.is, | 70 |
| abstract_inverted_index.new | 86, 106 |
| abstract_inverted_index.one | 105 |
| abstract_inverted_index.our | 248 |
| abstract_inverted_index.the | 25, 56, 75, 81, 90, 94, 138, 158, 162, 167, 173, 177, 180, 185, 188, 197, 206, 220, 224, 231, 252 |
| abstract_inverted_index.use | 28 |
| abstract_inverted_index.2012 | 242 |
| abstract_inverted_index.LSTM | 132, 228 |
| abstract_inverted_index.Most | 23 |
| abstract_inverted_index.WSOD | 26, 109, 199, 234 |
| abstract_inverted_index.each | 126 |
| abstract_inverted_index.good | 209 |
| abstract_inverted_index.huge | 20 |
| abstract_inverted_index.more | 7, 9 |
| abstract_inverted_index.most | 57 |
| abstract_inverted_index.ones | 96 |
| abstract_inverted_index.only | 13, 54 |
| abstract_inverted_index.save | 19 |
| abstract_inverted_index.show | 246 |
| abstract_inverted_index.than | 64 |
| abstract_inverted_index.that | 69, 247 |
| abstract_inverted_index.them | 171 |
| abstract_inverted_index.uses | 14 |
| abstract_inverted_index.will | 195 |
| abstract_inverted_index.(MIL) | 32 |
| abstract_inverted_index.2007, | 240 |
| abstract_inverted_index.D-CPE | 127 |
| abstract_inverted_index.Then, | 155 |
| abstract_inverted_index.These | 191 |
| abstract_inverted_index.based | 48, 130 |
| abstract_inverted_index.basic | 35, 198 |
| abstract_inverted_index.guide | 196 |
| abstract_inverted_index.habit | 76 |
| abstract_inverted_index.ones. | 210 |
| abstract_inverted_index.score | 186 |
| abstract_inverted_index.since | 11 |
| abstract_inverted_index.tends | 51 |
| abstract_inverted_index.their | 34, 65 |
| abstract_inverted_index.these | 46 |
| abstract_inverted_index.those | 99 |
| abstract_inverted_index.using | 172 |
| abstract_inverted_index.which | 37, 116 |
| abstract_inverted_index.(CPE), | 115 |
| abstract_inverted_index.(WSOD) | 4 |
| abstract_inverted_index.PASCAL | 238 |
| abstract_inverted_index.Weakly | 0 |
| abstract_inverted_index.coding | 226 |
| abstract_inverted_index.costs. | 22 |
| abstract_inverted_index.human, | 82 |
| abstract_inverted_index.labels | 16 |
| abstract_inverted_index.method | 87, 249 |
| abstract_inverted_index.object | 2 |
| abstract_inverted_index.order. | 154 |
| abstract_inverted_index.rather | 63 |
| abstract_inverted_index.regard | 38 |
| abstract_inverted_index.scores | 207 |
| abstract_inverted_index.simple | 214 |
| abstract_inverted_index.things | 79 |
| abstract_inverted_index.MS-COCO | 244 |
| abstract_inverted_index.decoder | 221 |
| abstract_inverted_index.feature | 168 |
| abstract_inverted_index.improve | 205, 230 |
| abstract_inverted_index.initial | 91, 100, 141, 163, 181, 189 |
| abstract_inverted_index.methods | 27, 47 |
| abstract_inverted_index.network | 133, 216 |
| abstract_inverted_index.propose | 84, 104 |
| abstract_inverted_index.regions | 59 |
| abstract_inverted_index.(D-CPE), | 124 |
| abstract_inverted_index.Firstly, | 137 |
| abstract_inverted_index.However, | 45 |
| abstract_inverted_index.Inspired | 73 |
| abstract_inverted_index.Instance | 30 |
| abstract_inverted_index.Learning | 31 |
| abstract_inverted_index.Multiple | 29 |
| abstract_inverted_index.achieved | 251 |
| abstract_inverted_index.boundary | 139 |
| abstract_inverted_index.compares | 157 |
| abstract_inverted_index.complete | 67 |
| abstract_inverted_index.consists | 117 |
| abstract_inverted_index.contains | 128 |
| abstract_inverted_index.converge | 53 |
| abstract_inverted_index.datasets | 245 |
| abstract_inverted_index.designed | 218 |
| abstract_inverted_index.encoders | 129 |
| abstract_inverted_index.extended | 146, 159 |
| abstract_inverted_index.further. | 235 |
| abstract_inverted_index.instance | 42 |
| abstract_inverted_index.multiple | 119 |
| abstract_inverted_index.optimize | 98, 184 |
| abstract_inverted_index.problem. | 44 |
| abstract_inverted_index.proposal | 113, 122, 160, 164, 182 |
| abstract_inverted_index.regions, | 68 |
| abstract_inverted_index.results. | 254 |
| abstract_inverted_index.strategy | 107 |
| abstract_inverted_index.suppress | 201 |
| abstract_inverted_index.temporal | 225 |
| abstract_inverted_index.according | 150 |
| abstract_inverted_index.addition, | 212 |
| abstract_inverted_index.attention | 10 |
| abstract_inverted_index.attracted | 6 |
| abstract_inverted_index.comparing | 89 |
| abstract_inverted_index.constrain | 223 |
| abstract_inverted_index.decoders. | 136 |
| abstract_inverted_index.detection | 3 |
| abstract_inverted_index.different | 61, 148 |
| abstract_inverted_index.encoders, | 174 |
| abstract_inverted_index.extension | 95, 114 |
| abstract_inverted_index.integrity | 178 |
| abstract_inverted_index.involving | 111 |
| abstract_inverted_index.observing | 78 |
| abstract_inverted_index.positions | 149 |
| abstract_inverted_index.proposal. | 190 |
| abstract_inverted_index.proposals | 92, 142, 203 |
| abstract_inverted_index.semantics | 169, 194 |
| abstract_inverted_index.annotation | 21 |
| abstract_inverted_index.calculates | 176 |
| abstract_inverted_index.contextual | 193 |
| abstract_inverted_index.extensions | 123 |
| abstract_inverted_index.extracting | 166 |
| abstract_inverted_index.framework, | 36 |
| abstract_inverted_index.instances, | 62 |
| abstract_inverted_index.integrity. | 72 |
| abstract_inverted_index.proposals. | 101 |
| abstract_inverted_index.sequential | 153 |
| abstract_inverted_index.supervised | 1 |
| abstract_inverted_index.two-stream | 215 |
| abstract_inverted_index.Experiments | 236 |
| abstract_inverted_index.contrastive | 112, 121, 192 |
| abstract_inverted_index.directional | 120 |
| abstract_inverted_index.image-level | 15 |
| abstract_inverted_index.performance | 232 |
| abstract_inverted_index.discriminate | 58 |
| abstract_inverted_index.insufficient | 71 |
| abstract_inverted_index.Specifically, | 102 |
| abstract_inverted_index.corresponding | 66, 135 |
| abstract_inverted_index.well-designed | 152 |
| abstract_inverted_index.classification | 43 |
| abstract_inverted_index.state-of-the-art | 253 |
| cited_by_percentile_year.max | 96 |
| cited_by_percentile_year.min | 94 |
| countries_distinct_count | 0 |
| institutions_distinct_count | 8 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/10 |
| sustainable_development_goals[0].score | 0.6800000071525574 |
| sustainable_development_goals[0].display_name | Reduced inequalities |
| citation_normalized_percentile.value | 0.51270276 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |