MAMA: Meta-optimized Angular Margin Contrastive Framework for Video-Language Representation Learning Article Swipe
T. Q. Nguyen
,
Bin Yi
,
Xiaobao Wu
,
Xinshuai Dong
,
Zhiyuan Hu
,
Khoi M. Le
,
Cong-Duy Nguyen
,
See-Kiong Ng
,
Luu Anh Tuan
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2407.03788
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2407.03788
Data quality stands at the forefront of deciding the effectiveness of video-language representation learning. However, video-text pairs in previous data typically do not align perfectly with each other, which might lead to video-language representations that do not accurately reflect cross-modal semantics. Moreover, previous data also possess an uneven distribution of concepts, thereby hampering the downstream performance across unpopular subjects. To address these problems, we propose MAMA, a new approach to learning video-language representations by utilizing a contrastive objective with a subtractive angular margin to regularize cross-modal representations in their effort to reach perfect similarity. Furthermore, to adapt to the non-uniform concept distribution, MAMA utilizes a multi-layer perceptron (MLP)-parameterized weighting function that maps loss values to sample weights which enable dynamic adjustment of the model's focus throughout the training. With the training guided by a small amount of unbiased meta-data and augmented by video-text data generated by large vision-language model, MAMA improves video-language representations and achieve superior performances on commonly used video question answering and text-video retrieval datasets. The code, model, and data have been made available at https://nguyentthong.github.io/MAMA.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2407.03788
- https://arxiv.org/pdf/2407.03788
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4400434033
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4400434033Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2407.03788Digital Object Identifier
- Title
-
MAMA: Meta-optimized Angular Margin Contrastive Framework for Video-Language Representation LearningWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-07-04Full publication date if available
- Authors
-
T. Q. Nguyen, Bin Yi, Xiaobao Wu, Xinshuai Dong, Zhiyuan Hu, Khoi M. Le, Cong-Duy Nguyen, See-Kiong Ng, Luu Anh TuanList of authors in order
- Landing page
-
https://arxiv.org/abs/2407.03788Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2407.03788Direct 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/2407.03788Direct OA link when available
- Concepts
-
Margin (machine learning), Computer science, Representation (politics), Natural language processing, Artificial intelligence, Feature learning, Machine learning, Political science, Law, PoliticsTop 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/W4400434033 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2407.03788 |
| ids.doi | https://doi.org/10.48550/arxiv.2407.03788 |
| ids.openalex | https://openalex.org/W4400434033 |
| fwci | |
| type | preprint |
| title | MAMA: Meta-optimized Angular Margin Contrastive Framework for Video-Language Representation Learning |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11714 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9941999912261963 |
| 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 | Multimodal Machine Learning Applications |
| topics[1].id | https://openalex.org/T10812 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9929999709129333 |
| 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 | Human Pose and Action Recognition |
| topics[2].id | https://openalex.org/T11439 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9830999970436096 |
| 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 | Video Analysis and Summarization |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C774472 |
| concepts[0].level | 2 |
| concepts[0].score | 0.836654782295227 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q6760393 |
| concepts[0].display_name | Margin (machine learning) |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.6203455924987793 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C2776359362 |
| concepts[2].level | 3 |
| concepts[2].score | 0.6188117265701294 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q2145286 |
| concepts[2].display_name | Representation (politics) |
| concepts[3].id | https://openalex.org/C204321447 |
| concepts[3].level | 1 |
| concepts[3].score | 0.4554750919342041 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[3].display_name | Natural language processing |
| concepts[4].id | https://openalex.org/C154945302 |
| concepts[4].level | 1 |
| concepts[4].score | 0.44752395153045654 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[4].display_name | Artificial intelligence |
| concepts[5].id | https://openalex.org/C59404180 |
| concepts[5].level | 2 |
| concepts[5].score | 0.4399040639400482 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q17013334 |
| concepts[5].display_name | Feature learning |
| concepts[6].id | https://openalex.org/C119857082 |
| concepts[6].level | 1 |
| concepts[6].score | 0.21887359023094177 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[6].display_name | Machine learning |
| concepts[7].id | https://openalex.org/C17744445 |
| concepts[7].level | 0 |
| concepts[7].score | 0.05697512626647949 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q36442 |
| concepts[7].display_name | Political science |
| concepts[8].id | https://openalex.org/C199539241 |
| concepts[8].level | 1 |
| concepts[8].score | 0.0 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q7748 |
| concepts[8].display_name | Law |
| concepts[9].id | https://openalex.org/C94625758 |
| concepts[9].level | 2 |
| concepts[9].score | 0.0 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q7163 |
| concepts[9].display_name | Politics |
| keywords[0].id | https://openalex.org/keywords/margin |
| keywords[0].score | 0.836654782295227 |
| keywords[0].display_name | Margin (machine learning) |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.6203455924987793 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/representation |
| keywords[2].score | 0.6188117265701294 |
| keywords[2].display_name | Representation (politics) |
| keywords[3].id | https://openalex.org/keywords/natural-language-processing |
| keywords[3].score | 0.4554750919342041 |
| keywords[3].display_name | Natural language processing |
| keywords[4].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[4].score | 0.44752395153045654 |
| keywords[4].display_name | Artificial intelligence |
| keywords[5].id | https://openalex.org/keywords/feature-learning |
| keywords[5].score | 0.4399040639400482 |
| keywords[5].display_name | Feature learning |
| keywords[6].id | https://openalex.org/keywords/machine-learning |
| keywords[6].score | 0.21887359023094177 |
| keywords[6].display_name | Machine learning |
| keywords[7].id | https://openalex.org/keywords/political-science |
| keywords[7].score | 0.05697512626647949 |
| keywords[7].display_name | Political science |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2407.03788 |
| 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/2407.03788 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2407.03788 |
| locations[1].id | doi:10.48550/arxiv.2407.03788 |
| 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 | cc-by |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | https://openalex.org/licenses/cc-by |
| 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.2407.03788 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5101561868 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-3954-5131 |
| authorships[0].author.display_name | T. Q. Nguyen |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Nguyen, Thong |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5084911441 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-5840-2086 |
| authorships[1].author.display_name | Bin Yi |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Bin, Yi |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5011376608 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-0076-3924 |
| authorships[2].author.display_name | Xiaobao Wu |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Wu, Xiaobao |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5079198353 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Xinshuai Dong |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Dong, Xinshuai |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5101468117 |
| authorships[4].author.orcid | https://orcid.org/0000-0003-4095-0249 |
| authorships[4].author.display_name | Zhiyuan Hu |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Hu, Zhiyuan |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5028581687 |
| authorships[5].author.orcid | https://orcid.org/0000-0003-2250-0818 |
| authorships[5].author.display_name | Khoi M. Le |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Le, Khoi |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5025645183 |
| authorships[6].author.orcid | https://orcid.org/0000-0002-0931-460X |
| authorships[6].author.display_name | Cong-Duy Nguyen |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Nguyen, Cong-Duy |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5090171111 |
| authorships[7].author.orcid | https://orcid.org/0000-0001-6565-7511 |
| authorships[7].author.display_name | See-Kiong Ng |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Ng, See-Kiong |
| authorships[7].is_corresponding | False |
| authorships[8].author.id | https://openalex.org/A5001659855 |
| authorships[8].author.orcid | https://orcid.org/0000-0001-6062-207X |
| authorships[8].author.display_name | Luu Anh Tuan |
| authorships[8].author_position | last |
| authorships[8].raw_author_name | Tuan, Luu Anh |
| authorships[8].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/2407.03788 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2024-07-09T00:00:00 |
| display_name | MAMA: Meta-optimized Angular Margin Contrastive Framework for Video-Language Representation Learning |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11714 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9941999912261963 |
| 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 | Multimodal Machine Learning Applications |
| related_works | https://openalex.org/W3125011624, https://openalex.org/W1508631387, https://openalex.org/W2370917603, https://openalex.org/W2952760143, https://openalex.org/W2017776670, https://openalex.org/W2347897961, https://openalex.org/W2340870721, https://openalex.org/W2358318464, https://openalex.org/W2979236518, https://openalex.org/W3204019825 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2407.03788 |
| 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/2407.03788 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2407.03788 |
| primary_location.id | pmh:oai:arXiv.org:2407.03788 |
| 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/2407.03788 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2407.03788 |
| publication_date | 2024-07-04 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 66, 75, 79, 104, 133 |
| abstract_inverted_index.To | 59 |
| abstract_inverted_index.an | 46 |
| abstract_inverted_index.at | 3, 176 |
| abstract_inverted_index.by | 73, 132, 141, 145 |
| abstract_inverted_index.do | 21, 35 |
| abstract_inverted_index.in | 17, 87 |
| abstract_inverted_index.of | 6, 10, 49, 121, 136 |
| abstract_inverted_index.on | 157 |
| abstract_inverted_index.to | 31, 69, 83, 90, 95, 97, 114 |
| abstract_inverted_index.we | 63 |
| abstract_inverted_index.The | 167 |
| abstract_inverted_index.and | 139, 153, 163, 170 |
| abstract_inverted_index.new | 67 |
| abstract_inverted_index.not | 22, 36 |
| abstract_inverted_index.the | 4, 8, 53, 98, 122, 126, 129 |
| abstract_inverted_index.Data | 0 |
| abstract_inverted_index.MAMA | 102, 149 |
| abstract_inverted_index.With | 128 |
| abstract_inverted_index.also | 44 |
| abstract_inverted_index.been | 173 |
| abstract_inverted_index.data | 19, 43, 143, 171 |
| abstract_inverted_index.each | 26 |
| abstract_inverted_index.have | 172 |
| abstract_inverted_index.lead | 30 |
| abstract_inverted_index.loss | 112 |
| abstract_inverted_index.made | 174 |
| abstract_inverted_index.maps | 111 |
| abstract_inverted_index.that | 34, 110 |
| abstract_inverted_index.used | 159 |
| abstract_inverted_index.with | 25, 78 |
| abstract_inverted_index.MAMA, | 65 |
| abstract_inverted_index.adapt | 96 |
| abstract_inverted_index.align | 23 |
| abstract_inverted_index.code, | 168 |
| abstract_inverted_index.focus | 124 |
| abstract_inverted_index.large | 146 |
| abstract_inverted_index.might | 29 |
| abstract_inverted_index.pairs | 16 |
| abstract_inverted_index.reach | 91 |
| abstract_inverted_index.small | 134 |
| abstract_inverted_index.their | 88 |
| abstract_inverted_index.these | 61 |
| abstract_inverted_index.video | 160 |
| abstract_inverted_index.which | 28, 117 |
| abstract_inverted_index.across | 56 |
| abstract_inverted_index.amount | 135 |
| abstract_inverted_index.effort | 89 |
| abstract_inverted_index.enable | 118 |
| abstract_inverted_index.guided | 131 |
| abstract_inverted_index.margin | 82 |
| abstract_inverted_index.model, | 148, 169 |
| abstract_inverted_index.other, | 27 |
| abstract_inverted_index.sample | 115 |
| abstract_inverted_index.stands | 2 |
| abstract_inverted_index.uneven | 47 |
| abstract_inverted_index.values | 113 |
| abstract_inverted_index.achieve | 154 |
| abstract_inverted_index.address | 60 |
| abstract_inverted_index.angular | 81 |
| abstract_inverted_index.concept | 100 |
| abstract_inverted_index.dynamic | 119 |
| abstract_inverted_index.model's | 123 |
| abstract_inverted_index.perfect | 92 |
| abstract_inverted_index.possess | 45 |
| abstract_inverted_index.propose | 64 |
| abstract_inverted_index.quality | 1 |
| abstract_inverted_index.reflect | 38 |
| abstract_inverted_index.thereby | 51 |
| abstract_inverted_index.weights | 116 |
| abstract_inverted_index.However, | 14 |
| abstract_inverted_index.approach | 68 |
| abstract_inverted_index.commonly | 158 |
| abstract_inverted_index.deciding | 7 |
| abstract_inverted_index.function | 109 |
| abstract_inverted_index.improves | 150 |
| abstract_inverted_index.learning | 70 |
| abstract_inverted_index.previous | 18, 42 |
| abstract_inverted_index.question | 161 |
| abstract_inverted_index.superior | 155 |
| abstract_inverted_index.training | 130 |
| abstract_inverted_index.unbiased | 137 |
| abstract_inverted_index.utilizes | 103 |
| abstract_inverted_index.Moreover, | 41 |
| abstract_inverted_index.answering | 162 |
| abstract_inverted_index.augmented | 140 |
| abstract_inverted_index.available | 175 |
| abstract_inverted_index.concepts, | 50 |
| abstract_inverted_index.datasets. | 166 |
| abstract_inverted_index.forefront | 5 |
| abstract_inverted_index.generated | 144 |
| abstract_inverted_index.hampering | 52 |
| abstract_inverted_index.learning. | 13 |
| abstract_inverted_index.meta-data | 138 |
| abstract_inverted_index.objective | 77 |
| abstract_inverted_index.perfectly | 24 |
| abstract_inverted_index.problems, | 62 |
| abstract_inverted_index.retrieval | 165 |
| abstract_inverted_index.subjects. | 58 |
| abstract_inverted_index.training. | 127 |
| abstract_inverted_index.typically | 20 |
| abstract_inverted_index.unpopular | 57 |
| abstract_inverted_index.utilizing | 74 |
| abstract_inverted_index.weighting | 108 |
| abstract_inverted_index.accurately | 37 |
| abstract_inverted_index.adjustment | 120 |
| abstract_inverted_index.downstream | 54 |
| abstract_inverted_index.perceptron | 106 |
| abstract_inverted_index.regularize | 84 |
| abstract_inverted_index.semantics. | 40 |
| abstract_inverted_index.text-video | 164 |
| abstract_inverted_index.throughout | 125 |
| abstract_inverted_index.video-text | 15, 142 |
| abstract_inverted_index.contrastive | 76 |
| abstract_inverted_index.cross-modal | 39, 85 |
| abstract_inverted_index.multi-layer | 105 |
| abstract_inverted_index.non-uniform | 99 |
| abstract_inverted_index.performance | 55 |
| abstract_inverted_index.similarity. | 93 |
| abstract_inverted_index.subtractive | 80 |
| abstract_inverted_index.Furthermore, | 94 |
| abstract_inverted_index.distribution | 48 |
| abstract_inverted_index.performances | 156 |
| abstract_inverted_index.distribution, | 101 |
| abstract_inverted_index.effectiveness | 9 |
| abstract_inverted_index.representation | 12 |
| abstract_inverted_index.video-language | 11, 32, 71, 151 |
| abstract_inverted_index.representations | 33, 72, 86, 152 |
| abstract_inverted_index.vision-language | 147 |
| abstract_inverted_index.(MLP)-parameterized | 107 |
| abstract_inverted_index.https://nguyentthong.github.io/MAMA. | 177 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 9 |
| citation_normalized_percentile |