(Un)likelihood Training for Interpretable Embedding Article Swipe
Jiaxin Wu
,
Chong‐Wah Ngo
,
W. K. Chan
,
Zhijian Hou
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.1145/3632752
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.1145/3632752
Cross-modal representation learning has become a new normal for bridging the semantic gap between text and visual data. Learning modality agnostic representations in a continuous latent space, however, is often treated as a black-box data-driven training process. It is well known that the effectiveness of representation learning depends heavily on the quality and scale of training data. For video representation learning, having a complete set of labels that annotate the full spectrum of video content for training is highly difficult, if not impossible. These issues, black-box training and dataset bias, make representation learning practically challenging to be deployed for video understanding due to unexplainable and unpredictable results. In this article, we propose two novel training objectives, likelihood and unlikelihood functions, to unroll the semantics behind embeddings while addressing the label sparsity problem in training. The likelihood training aims to interpret semantics of embeddings beyond training labels, while the unlikelihood training leverages prior knowledge for regularization to ensure semantically coherent interpretation. With both training objectives, a new encoder-decoder network, which learns interpretable cross-modal representation, is proposed for ad-hoc video search. Extensive experiments on TRECVid and MSR-VTT datasets show that the proposed network outperforms several state-of-the-art retrieval models with a statistically significant performance margin.
Related Topics
Concepts
Computer science
Feature learning
Regularization (linguistics)
Artificial intelligence
Machine learning
Representation (politics)
Semantics (computer science)
Bridging (networking)
Embedding
Set (abstract data type)
Encoder
Natural language processing
Operating system
Politics
Programming language
Political science
Computer network
Law
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1145/3632752
- OA Status
- bronze
- Cited By
- 2
- References
- 47
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4388638745
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4388638745Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1145/3632752Digital Object Identifier
- Title
-
(Un)likelihood Training for Interpretable EmbeddingWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-11-13Full publication date if available
- Authors
-
Jiaxin Wu, Chong‐Wah Ngo, W. K. Chan, Zhijian HouList of authors in order
- Landing page
-
https://doi.org/10.1145/3632752Publisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
bronzeOpen access status per OpenAlex
- OA URL
-
https://scholars.cityu.edu.hk/en/publications/unlikelihood-training-for-interpretable-embeddingDirect OA link when available
- Concepts
-
Computer science, Feature learning, Regularization (linguistics), Artificial intelligence, Machine learning, Representation (politics), Semantics (computer science), Bridging (networking), Embedding, Set (abstract data type), Encoder, Natural language processing, Operating system, Politics, Programming language, Political science, Computer network, LawTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
2Total citation count in OpenAlex
- Citations by year (recent)
-
2024: 1, 2023: 1Per-year citation counts (last 5 years)
- References (count)
-
47Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4388638745 |
|---|---|
| doi | https://doi.org/10.1145/3632752 |
| ids.doi | https://doi.org/10.1145/3632752 |
| ids.openalex | https://openalex.org/W4388638745 |
| fwci | 0.36393668 |
| type | article |
| title | (Un)likelihood Training for Interpretable Embedding |
| biblio.issue | 3 |
| biblio.volume | 42 |
| biblio.last_page | 26 |
| biblio.first_page | 1 |
| 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 | 1.0 |
| 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/T11307 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9987999796867371 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1702 |
| topics[1].subfield.display_name | Artificial Intelligence |
| topics[1].display_name | Domain Adaptation and Few-Shot Learning |
| topics[2].id | https://openalex.org/T10812 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9976999759674072 |
| 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 | Human Pose and Action Recognition |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.8670696020126343 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C59404180 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6430738568305969 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q17013334 |
| concepts[1].display_name | Feature learning |
| concepts[2].id | https://openalex.org/C2776135515 |
| concepts[2].level | 2 |
| concepts[2].score | 0.5962338447570801 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q17143721 |
| concepts[2].display_name | Regularization (linguistics) |
| concepts[3].id | https://openalex.org/C154945302 |
| concepts[3].level | 1 |
| concepts[3].score | 0.5952699184417725 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[3].display_name | Artificial intelligence |
| concepts[4].id | https://openalex.org/C119857082 |
| concepts[4].level | 1 |
| concepts[4].score | 0.5542096495628357 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[4].display_name | Machine learning |
| concepts[5].id | https://openalex.org/C2776359362 |
| concepts[5].level | 3 |
| concepts[5].score | 0.5252358913421631 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q2145286 |
| concepts[5].display_name | Representation (politics) |
| concepts[6].id | https://openalex.org/C184337299 |
| concepts[6].level | 2 |
| concepts[6].score | 0.521446168422699 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q1437428 |
| concepts[6].display_name | Semantics (computer science) |
| concepts[7].id | https://openalex.org/C174348530 |
| concepts[7].level | 2 |
| concepts[7].score | 0.4669177532196045 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q188635 |
| concepts[7].display_name | Bridging (networking) |
| concepts[8].id | https://openalex.org/C41608201 |
| concepts[8].level | 2 |
| concepts[8].score | 0.456617534160614 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q980509 |
| concepts[8].display_name | Embedding |
| concepts[9].id | https://openalex.org/C177264268 |
| concepts[9].level | 2 |
| concepts[9].score | 0.4166962802410126 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q1514741 |
| concepts[9].display_name | Set (abstract data type) |
| concepts[10].id | https://openalex.org/C118505674 |
| concepts[10].level | 2 |
| concepts[10].score | 0.41337263584136963 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q42586063 |
| concepts[10].display_name | Encoder |
| concepts[11].id | https://openalex.org/C204321447 |
| concepts[11].level | 1 |
| concepts[11].score | 0.33319422602653503 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[11].display_name | Natural language processing |
| 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/C94625758 |
| concepts[13].level | 2 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q7163 |
| concepts[13].display_name | Politics |
| concepts[14].id | https://openalex.org/C199360897 |
| concepts[14].level | 1 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q9143 |
| concepts[14].display_name | Programming language |
| concepts[15].id | https://openalex.org/C17744445 |
| concepts[15].level | 0 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q36442 |
| concepts[15].display_name | Political science |
| concepts[16].id | https://openalex.org/C31258907 |
| concepts[16].level | 1 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q1301371 |
| concepts[16].display_name | Computer network |
| concepts[17].id | https://openalex.org/C199539241 |
| concepts[17].level | 1 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q7748 |
| concepts[17].display_name | Law |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.8670696020126343 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/feature-learning |
| keywords[1].score | 0.6430738568305969 |
| keywords[1].display_name | Feature learning |
| keywords[2].id | https://openalex.org/keywords/regularization |
| keywords[2].score | 0.5962338447570801 |
| keywords[2].display_name | Regularization (linguistics) |
| keywords[3].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[3].score | 0.5952699184417725 |
| keywords[3].display_name | Artificial intelligence |
| keywords[4].id | https://openalex.org/keywords/machine-learning |
| keywords[4].score | 0.5542096495628357 |
| keywords[4].display_name | Machine learning |
| keywords[5].id | https://openalex.org/keywords/representation |
| keywords[5].score | 0.5252358913421631 |
| keywords[5].display_name | Representation (politics) |
| keywords[6].id | https://openalex.org/keywords/semantics |
| keywords[6].score | 0.521446168422699 |
| keywords[6].display_name | Semantics (computer science) |
| keywords[7].id | https://openalex.org/keywords/bridging |
| keywords[7].score | 0.4669177532196045 |
| keywords[7].display_name | Bridging (networking) |
| keywords[8].id | https://openalex.org/keywords/embedding |
| keywords[8].score | 0.456617534160614 |
| keywords[8].display_name | Embedding |
| keywords[9].id | https://openalex.org/keywords/set |
| keywords[9].score | 0.4166962802410126 |
| keywords[9].display_name | Set (abstract data type) |
| keywords[10].id | https://openalex.org/keywords/encoder |
| keywords[10].score | 0.41337263584136963 |
| keywords[10].display_name | Encoder |
| keywords[11].id | https://openalex.org/keywords/natural-language-processing |
| keywords[11].score | 0.33319422602653503 |
| keywords[11].display_name | Natural language processing |
| language | en |
| locations[0].id | doi:10.1145/3632752 |
| locations[0].is_oa | False |
| locations[0].source.id | https://openalex.org/S4394735545 |
| locations[0].source.issn | 1046-8188, 1558-2868 |
| locations[0].source.type | journal |
| locations[0].source.is_oa | False |
| locations[0].source.issn_l | 1046-8188 |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | ACM Transactions on Information Systems |
| locations[0].source.host_organization | |
| locations[0].source.host_organization_name | |
| locations[0].license | |
| locations[0].pdf_url | |
| locations[0].version | publishedVersion |
| locations[0].raw_type | journal-article |
| locations[0].license_id | |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | ACM Transactions on Information Systems |
| locations[0].landing_page_url | https://doi.org/10.1145/3632752 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4394735545 |
| locations[1].source.issn | 1046-8188, 1558-2868 |
| locations[1].source.type | journal |
| locations[1].source.is_oa | False |
| locations[1].source.issn_l | 1046-8188 |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | ACM Transactions on Information Systems |
| locations[1].source.host_organization | |
| locations[1].source.host_organization_name | |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | publishedVersion |
| locations[1].raw_type | journal-article |
| locations[1].license_id | |
| locations[1].is_accepted | True |
| locations[1].is_published | True |
| locations[1].raw_source_name | ACM Transactions on Information Systems |
| locations[1].landing_page_url | https://scholars.cityu.edu.hk/en/publications/unlikelihood-training-for-interpretable-embedding |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5056908913 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-4074-3442 |
| authorships[0].author.display_name | Jiaxin Wu |
| authorships[0].countries | HK |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I168719708 |
| authorships[0].affiliations[0].raw_affiliation_string | City University of Hong Kong, Hong Kong |
| authorships[0].institutions[0].id | https://openalex.org/I168719708 |
| authorships[0].institutions[0].ror | https://ror.org/03q8dnn23 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I168719708 |
| authorships[0].institutions[0].country_code | HK |
| authorships[0].institutions[0].display_name | City University of Hong Kong |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Jiaxin Wu |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | City University of Hong Kong, Hong Kong |
| authorships[1].author.id | https://openalex.org/A5010722442 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-4182-8261 |
| authorships[1].author.display_name | Chong‐Wah Ngo |
| authorships[1].countries | SG |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I79891267 |
| authorships[1].affiliations[0].raw_affiliation_string | Singapore Management University, Singapore |
| authorships[1].institutions[0].id | https://openalex.org/I79891267 |
| authorships[1].institutions[0].ror | https://ror.org/050qmg959 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I79891267 |
| authorships[1].institutions[0].country_code | SG |
| authorships[1].institutions[0].display_name | Singapore Management University |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Chong-Wah Ngo |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | Singapore Management University, Singapore |
| authorships[2].author.id | https://openalex.org/A5020936420 |
| authorships[2].author.orcid | https://orcid.org/0000-0001-7726-6235 |
| authorships[2].author.display_name | W. K. Chan |
| authorships[2].countries | HK |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I168719708 |
| authorships[2].affiliations[0].raw_affiliation_string | City University of Hong Kong, Hong Kong |
| authorships[2].institutions[0].id | https://openalex.org/I168719708 |
| authorships[2].institutions[0].ror | https://ror.org/03q8dnn23 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I168719708 |
| authorships[2].institutions[0].country_code | HK |
| authorships[2].institutions[0].display_name | City University of Hong Kong |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Wing-Kwong Chan |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | City University of Hong Kong, Hong Kong |
| authorships[3].author.id | https://openalex.org/A5101556026 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-7297-6817 |
| authorships[3].author.display_name | Zhijian Hou |
| authorships[3].countries | HK |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I168719708 |
| authorships[3].affiliations[0].raw_affiliation_string | City University of Hong Kong, Hong Kong |
| authorships[3].institutions[0].id | https://openalex.org/I168719708 |
| authorships[3].institutions[0].ror | https://ror.org/03q8dnn23 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I168719708 |
| authorships[3].institutions[0].country_code | HK |
| authorships[3].institutions[0].display_name | City University of Hong Kong |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Zhijian Hou |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | City University of Hong Kong, Hong Kong |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://scholars.cityu.edu.hk/en/publications/unlikelihood-training-for-interpretable-embedding |
| open_access.oa_status | bronze |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | (Un)likelihood Training for Interpretable Embedding |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| 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 | 1.0 |
| 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/W4388870064, https://openalex.org/W4235186151, https://openalex.org/W2054685365, https://openalex.org/W2272354214, https://openalex.org/W2120383820, https://openalex.org/W2043010663, https://openalex.org/W2667588871, https://openalex.org/W4248308508, https://openalex.org/W118554674, https://openalex.org/W2757563118 |
| cited_by_count | 2 |
| counts_by_year[0].year | 2024 |
| counts_by_year[0].cited_by_count | 1 |
| counts_by_year[1].year | 2023 |
| counts_by_year[1].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4394735545 |
| best_oa_location.source.issn | 1046-8188, 1558-2868 |
| best_oa_location.source.type | journal |
| best_oa_location.source.is_oa | False |
| best_oa_location.source.issn_l | 1046-8188 |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | ACM Transactions on Information Systems |
| best_oa_location.source.host_organization | |
| best_oa_location.source.host_organization_name | |
| best_oa_location.license | |
| best_oa_location.pdf_url | |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | journal-article |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | ACM Transactions on Information Systems |
| best_oa_location.landing_page_url | https://scholars.cityu.edu.hk/en/publications/unlikelihood-training-for-interpretable-embedding |
| primary_location.id | doi:10.1145/3632752 |
| primary_location.is_oa | False |
| primary_location.source.id | https://openalex.org/S4394735545 |
| primary_location.source.issn | 1046-8188, 1558-2868 |
| primary_location.source.type | journal |
| primary_location.source.is_oa | False |
| primary_location.source.issn_l | 1046-8188 |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | ACM Transactions on Information Systems |
| primary_location.source.host_organization | |
| primary_location.source.host_organization_name | |
| primary_location.license | |
| primary_location.pdf_url | |
| primary_location.version | publishedVersion |
| primary_location.raw_type | journal-article |
| primary_location.license_id | |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | ACM Transactions on Information Systems |
| primary_location.landing_page_url | https://doi.org/10.1145/3632752 |
| publication_date | 2023-11-13 |
| publication_year | 2023 |
| referenced_works | https://openalex.org/W2761419673, https://openalex.org/W6754337694, https://openalex.org/W3035356601, https://openalex.org/W1889081078, https://openalex.org/W2157331557, https://openalex.org/W1996204097, https://openalex.org/W2108598243, https://openalex.org/W2753311918, https://openalex.org/W2975813532, https://openalex.org/W3130796238, https://openalex.org/W4211053420, https://openalex.org/W2194775991, https://openalex.org/W4210565368, https://openalex.org/W4321488152, https://openalex.org/W6839503575, https://openalex.org/W2013075750, https://openalex.org/W6955071965, https://openalex.org/W2031602671, https://openalex.org/W4318718936, https://openalex.org/W3107973541, https://openalex.org/W3035605030, https://openalex.org/W3138516171, https://openalex.org/W3152798676, https://openalex.org/W2081580037, https://openalex.org/W4312629998, https://openalex.org/W2089150756, https://openalex.org/W2062903088, https://openalex.org/W2095705004, https://openalex.org/W3004819763, https://openalex.org/W3169472988, https://openalex.org/W2549139847, https://openalex.org/W2735355755, https://openalex.org/W2914092515, https://openalex.org/W2596164567, https://openalex.org/W2998717410, https://openalex.org/W2560674852, https://openalex.org/W2593713917, https://openalex.org/W2911542843, https://openalex.org/W2607303097, https://openalex.org/W2186222003, https://openalex.org/W2619947201, https://openalex.org/W4301409532, https://openalex.org/W1503398984, https://openalex.org/W2887051120, https://openalex.org/W3102887392, https://openalex.org/W4236965008, https://openalex.org/W4282937884 |
| referenced_works_count | 47 |
| abstract_inverted_index.a | 5, 23, 32, 62, 164, 197 |
| abstract_inverted_index.In | 107 |
| abstract_inverted_index.It | 37 |
| abstract_inverted_index.as | 31 |
| abstract_inverted_index.be | 96 |
| abstract_inverted_index.if | 80 |
| abstract_inverted_index.in | 22, 132 |
| abstract_inverted_index.is | 28, 38, 77, 173 |
| abstract_inverted_index.of | 44, 54, 65, 72, 141 |
| abstract_inverted_index.on | 49, 181 |
| abstract_inverted_index.to | 95, 102, 120, 138, 155 |
| abstract_inverted_index.we | 110 |
| abstract_inverted_index.For | 57 |
| abstract_inverted_index.The | 134 |
| abstract_inverted_index.and | 15, 52, 87, 104, 117, 183 |
| abstract_inverted_index.due | 101 |
| abstract_inverted_index.for | 8, 75, 98, 153, 175 |
| abstract_inverted_index.gap | 12 |
| abstract_inverted_index.has | 3 |
| abstract_inverted_index.new | 6, 165 |
| abstract_inverted_index.not | 81 |
| abstract_inverted_index.set | 64 |
| abstract_inverted_index.the | 10, 42, 50, 69, 122, 128, 147, 188 |
| abstract_inverted_index.two | 112 |
| abstract_inverted_index.With | 160 |
| abstract_inverted_index.aims | 137 |
| abstract_inverted_index.both | 161 |
| abstract_inverted_index.full | 70 |
| abstract_inverted_index.make | 90 |
| abstract_inverted_index.show | 186 |
| abstract_inverted_index.text | 14 |
| abstract_inverted_index.that | 41, 67, 187 |
| abstract_inverted_index.this | 108 |
| abstract_inverted_index.well | 39 |
| abstract_inverted_index.with | 196 |
| abstract_inverted_index.These | 83 |
| abstract_inverted_index.bias, | 89 |
| abstract_inverted_index.data. | 17, 56 |
| abstract_inverted_index.known | 40 |
| abstract_inverted_index.label | 129 |
| abstract_inverted_index.novel | 113 |
| abstract_inverted_index.often | 29 |
| abstract_inverted_index.prior | 151 |
| abstract_inverted_index.scale | 53 |
| abstract_inverted_index.video | 58, 73, 99, 177 |
| abstract_inverted_index.which | 168 |
| abstract_inverted_index.while | 126, 146 |
| abstract_inverted_index.ad-hoc | 176 |
| abstract_inverted_index.become | 4 |
| abstract_inverted_index.behind | 124 |
| abstract_inverted_index.beyond | 143 |
| abstract_inverted_index.ensure | 156 |
| abstract_inverted_index.having | 61 |
| abstract_inverted_index.highly | 78 |
| abstract_inverted_index.labels | 66 |
| abstract_inverted_index.latent | 25 |
| abstract_inverted_index.learns | 169 |
| abstract_inverted_index.models | 195 |
| abstract_inverted_index.normal | 7 |
| abstract_inverted_index.space, | 26 |
| abstract_inverted_index.unroll | 121 |
| abstract_inverted_index.visual | 16 |
| abstract_inverted_index.MSR-VTT | 184 |
| abstract_inverted_index.TRECVid | 182 |
| abstract_inverted_index.between | 13 |
| abstract_inverted_index.content | 74 |
| abstract_inverted_index.dataset | 88 |
| abstract_inverted_index.depends | 47 |
| abstract_inverted_index.heavily | 48 |
| abstract_inverted_index.issues, | 84 |
| abstract_inverted_index.labels, | 145 |
| abstract_inverted_index.margin. | 201 |
| abstract_inverted_index.network | 190 |
| abstract_inverted_index.problem | 131 |
| abstract_inverted_index.propose | 111 |
| abstract_inverted_index.quality | 51 |
| abstract_inverted_index.search. | 178 |
| abstract_inverted_index.several | 192 |
| abstract_inverted_index.treated | 30 |
| abstract_inverted_index.Learning | 18 |
| abstract_inverted_index.agnostic | 20 |
| abstract_inverted_index.annotate | 68 |
| abstract_inverted_index.article, | 109 |
| abstract_inverted_index.bridging | 9 |
| abstract_inverted_index.coherent | 158 |
| abstract_inverted_index.complete | 63 |
| abstract_inverted_index.datasets | 185 |
| abstract_inverted_index.deployed | 97 |
| abstract_inverted_index.however, | 27 |
| abstract_inverted_index.learning | 2, 46, 92 |
| abstract_inverted_index.modality | 19 |
| abstract_inverted_index.network, | 167 |
| abstract_inverted_index.process. | 36 |
| abstract_inverted_index.proposed | 174, 189 |
| abstract_inverted_index.results. | 106 |
| abstract_inverted_index.semantic | 11 |
| abstract_inverted_index.sparsity | 130 |
| abstract_inverted_index.spectrum | 71 |
| abstract_inverted_index.training | 35, 55, 76, 86, 114, 136, 144, 149, 162 |
| abstract_inverted_index.Extensive | 179 |
| abstract_inverted_index.black-box | 33, 85 |
| abstract_inverted_index.interpret | 139 |
| abstract_inverted_index.knowledge | 152 |
| abstract_inverted_index.learning, | 60 |
| abstract_inverted_index.leverages | 150 |
| abstract_inverted_index.retrieval | 194 |
| abstract_inverted_index.semantics | 123, 140 |
| abstract_inverted_index.training. | 133 |
| abstract_inverted_index.addressing | 127 |
| abstract_inverted_index.continuous | 24 |
| abstract_inverted_index.difficult, | 79 |
| abstract_inverted_index.embeddings | 125, 142 |
| abstract_inverted_index.functions, | 119 |
| abstract_inverted_index.likelihood | 116, 135 |
| abstract_inverted_index.Cross-modal | 0 |
| abstract_inverted_index.challenging | 94 |
| abstract_inverted_index.cross-modal | 171 |
| abstract_inverted_index.data-driven | 34 |
| abstract_inverted_index.experiments | 180 |
| abstract_inverted_index.impossible. | 82 |
| abstract_inverted_index.objectives, | 115, 163 |
| abstract_inverted_index.outperforms | 191 |
| abstract_inverted_index.performance | 200 |
| abstract_inverted_index.practically | 93 |
| abstract_inverted_index.significant | 199 |
| abstract_inverted_index.semantically | 157 |
| abstract_inverted_index.unlikelihood | 118, 148 |
| abstract_inverted_index.effectiveness | 43 |
| abstract_inverted_index.interpretable | 170 |
| abstract_inverted_index.statistically | 198 |
| abstract_inverted_index.understanding | 100 |
| abstract_inverted_index.unexplainable | 103 |
| abstract_inverted_index.unpredictable | 105 |
| abstract_inverted_index.regularization | 154 |
| abstract_inverted_index.representation | 1, 45, 59, 91 |
| abstract_inverted_index.encoder-decoder | 166 |
| abstract_inverted_index.interpretation. | 159 |
| abstract_inverted_index.representation, | 172 |
| abstract_inverted_index.representations | 21 |
| abstract_inverted_index.state-of-the-art | 193 |
| cited_by_percentile_year.max | 94 |
| cited_by_percentile_year.min | 89 |
| countries_distinct_count | 2 |
| institutions_distinct_count | 4 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/4 |
| sustainable_development_goals[0].score | 0.7400000095367432 |
| sustainable_development_goals[0].display_name | Quality Education |
| citation_normalized_percentile.value | 0.58026905 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |