Matches in SemOpenAlex for { <https://semopenalex.org/work/W4378804941> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4378804941 endingPage "1" @default.
- W4378804941 startingPage "1" @default.
- W4378804941 abstract "Unsupervised Domain Adaptation (UDA) can transfer knowledge from labeled source data to unlabeled target data of the same categories. However, UDA for first-person video action recognition is an under-explored problem, with a lack of benchmark datasets and limited consideration of first-person video characteristics. Existing benchmark datasets provide videos with a single activity scene, e.g. kitchen, and similar global video statistics. However, multiple activity scenes and different global video statistics are still essential for developing robust UDA networks for real-world applications. To this end, we first introduce two first-person video domain adaptation datasets: ADL-7 and GTEA_KITCHEN-6. To the best of our knowledge, they are the first to provide multi-scene and cross-site settings for UDA problem on first-person video action recognition, promoting diversity. They provide five more domains based on the original three from existing datasets, enriching data for this area. They are also compatible with existing datasets, ensuring scalability. First-person videos have unique challenges, i.e. actions tend to occur in hand-object interaction areas. Therefore, networks paying more attention to such areas can benefit common feature learning in UDA. Attention mechanisms can endow networks with the ability to allocate resources adaptively for the important parts of the inputs and fade out the rest. Hence, we introduce channel-temporal attention modules to capture the channel-wise and temporal-wise relationships and model their inter-dependencies important to this characteristic. Moreover, we propose a Channel-Temporal Attention Network (CTAN) to integrate these modules into existing architectures. CTAN outperforms baselines on the new datasets and one existing dataset, EPIC-8." @default.
- W4378804941 created "2023-06-01" @default.
- W4378804941 creator A5009807039 @default.
- W4378804941 creator A5030752617 @default.
- W4378804941 creator A5043749454 @default.
- W4378804941 creator A5045410206 @default.
- W4378804941 creator A5074861884 @default.
- W4378804941 creator A5076863723 @default.
- W4378804941 date "2023-01-01" @default.
- W4378804941 modified "2023-10-16" @default.
- W4378804941 title "First-Person Video Domain Adaptation with Multi-Scene Cross-Site Datasets and Attention-Based Methods" @default.
- W4378804941 doi "https://doi.org/10.1109/tcsvt.2023.3281671" @default.
- W4378804941 hasPublicationYear "2023" @default.
- W4378804941 type Work @default.
- W4378804941 citedByCount "0" @default.
- W4378804941 crossrefType "journal-article" @default.
- W4378804941 hasAuthorship W4378804941A5009807039 @default.
- W4378804941 hasAuthorship W4378804941A5030752617 @default.
- W4378804941 hasAuthorship W4378804941A5043749454 @default.
- W4378804941 hasAuthorship W4378804941A5045410206 @default.
- W4378804941 hasAuthorship W4378804941A5074861884 @default.
- W4378804941 hasAuthorship W4378804941A5076863723 @default.
- W4378804941 hasConcept C119857082 @default.
- W4378804941 hasConcept C120665830 @default.
- W4378804941 hasConcept C121332964 @default.
- W4378804941 hasConcept C127162648 @default.
- W4378804941 hasConcept C13280743 @default.
- W4378804941 hasConcept C134306372 @default.
- W4378804941 hasConcept C138885662 @default.
- W4378804941 hasConcept C139807058 @default.
- W4378804941 hasConcept C154945302 @default.
- W4378804941 hasConcept C185798385 @default.
- W4378804941 hasConcept C205649164 @default.
- W4378804941 hasConcept C2776401178 @default.
- W4378804941 hasConcept C2780791683 @default.
- W4378804941 hasConcept C2781238097 @default.
- W4378804941 hasConcept C31258907 @default.
- W4378804941 hasConcept C33923547 @default.
- W4378804941 hasConcept C36503486 @default.
- W4378804941 hasConcept C41008148 @default.
- W4378804941 hasConcept C41895202 @default.
- W4378804941 hasConcept C48044578 @default.
- W4378804941 hasConcept C62520636 @default.
- W4378804941 hasConcept C77088390 @default.
- W4378804941 hasConceptScore W4378804941C119857082 @default.
- W4378804941 hasConceptScore W4378804941C120665830 @default.
- W4378804941 hasConceptScore W4378804941C121332964 @default.
- W4378804941 hasConceptScore W4378804941C127162648 @default.
- W4378804941 hasConceptScore W4378804941C13280743 @default.
- W4378804941 hasConceptScore W4378804941C134306372 @default.
- W4378804941 hasConceptScore W4378804941C138885662 @default.
- W4378804941 hasConceptScore W4378804941C139807058 @default.
- W4378804941 hasConceptScore W4378804941C154945302 @default.
- W4378804941 hasConceptScore W4378804941C185798385 @default.
- W4378804941 hasConceptScore W4378804941C205649164 @default.
- W4378804941 hasConceptScore W4378804941C2776401178 @default.
- W4378804941 hasConceptScore W4378804941C2780791683 @default.
- W4378804941 hasConceptScore W4378804941C2781238097 @default.
- W4378804941 hasConceptScore W4378804941C31258907 @default.
- W4378804941 hasConceptScore W4378804941C33923547 @default.
- W4378804941 hasConceptScore W4378804941C36503486 @default.
- W4378804941 hasConceptScore W4378804941C41008148 @default.
- W4378804941 hasConceptScore W4378804941C41895202 @default.
- W4378804941 hasConceptScore W4378804941C48044578 @default.
- W4378804941 hasConceptScore W4378804941C62520636 @default.
- W4378804941 hasConceptScore W4378804941C77088390 @default.
- W4378804941 hasFunder F4320322725 @default.
- W4378804941 hasLocation W43788049411 @default.
- W4378804941 hasOpenAccess W4378804941 @default.
- W4378804941 hasPrimaryLocation W43788049411 @default.
- W4378804941 hasRelatedWork W112744582 @default.
- W4378804941 hasRelatedWork W1576801573 @default.
- W4378804941 hasRelatedWork W1992807924 @default.
- W4378804941 hasRelatedWork W2728071886 @default.
- W4378804941 hasRelatedWork W2789601449 @default.
- W4378804941 hasRelatedWork W2999356315 @default.
- W4378804941 hasRelatedWork W3123920941 @default.
- W4378804941 hasRelatedWork W3163866929 @default.
- W4378804941 hasRelatedWork W4304194246 @default.
- W4378804941 hasRelatedWork W4319756016 @default.
- W4378804941 isParatext "false" @default.
- W4378804941 isRetracted "false" @default.
- W4378804941 workType "article" @default.