Matches in SemOpenAlex for { <https://semopenalex.org/work/W4300574098> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4300574098 abstract "The increasing amount of online videos brings several opportunities for training self-supervised neural networks. The creation of large scale datasets of videos such as the YouTube-8M allows us to deal with this large amount of data in manageable way. In this work, we find new ways of exploiting this dataset by taking advantage of the multi-modal information it provides. By means of a neural network, we are able to create links between audio and visual documents, by projecting them into a common region of the feature space, obtaining joint audio-visual embeddings. These links are used to retrieve audio samples that fit well to a given silent video, and also to retrieve images that match a given a query audio. The results in terms of Recall@K obtained over a subset of YouTube-8M videos show the potential of this unsupervised approach for cross-modal feature learning. We train embeddings for both scales and assess their quality in a retrieval problem, formulated as using the feature extracted from one modality to retrieve the most similar videos based on the features computed in the other modality." @default.
- W4300574098 created "2022-10-03" @default.
- W4300574098 creator A5000613714 @default.
- W4300574098 creator A5019293578 @default.
- W4300574098 creator A5039375454 @default.
- W4300574098 creator A5051863471 @default.
- W4300574098 creator A5084718812 @default.
- W4300574098 date "2018-01-07" @default.
- W4300574098 modified "2023-10-16" @default.
- W4300574098 title "Cross-modal Embeddings for Video and Audio Retrieval" @default.
- W4300574098 doi "https://doi.org/10.48550/arxiv.1801.02200" @default.
- W4300574098 hasPublicationYear "2018" @default.
- W4300574098 type Work @default.
- W4300574098 citedByCount "0" @default.
- W4300574098 crossrefType "posted-content" @default.
- W4300574098 hasAuthorship W4300574098A5000613714 @default.
- W4300574098 hasAuthorship W4300574098A5019293578 @default.
- W4300574098 hasAuthorship W4300574098A5039375454 @default.
- W4300574098 hasAuthorship W4300574098A5051863471 @default.
- W4300574098 hasAuthorship W4300574098A5084718812 @default.
- W4300574098 hasBestOaLocation W43005740981 @default.
- W4300574098 hasConcept C138885662 @default.
- W4300574098 hasConcept C153180895 @default.
- W4300574098 hasConcept C154945302 @default.
- W4300574098 hasConcept C185592680 @default.
- W4300574098 hasConcept C188027245 @default.
- W4300574098 hasConcept C23123220 @default.
- W4300574098 hasConcept C2776401178 @default.
- W4300574098 hasConcept C2780226545 @default.
- W4300574098 hasConcept C3017588708 @default.
- W4300574098 hasConcept C41008148 @default.
- W4300574098 hasConcept C41895202 @default.
- W4300574098 hasConcept C49774154 @default.
- W4300574098 hasConcept C50644808 @default.
- W4300574098 hasConcept C59404180 @default.
- W4300574098 hasConcept C71139939 @default.
- W4300574098 hasConcept C81669768 @default.
- W4300574098 hasConcept C83665646 @default.
- W4300574098 hasConceptScore W4300574098C138885662 @default.
- W4300574098 hasConceptScore W4300574098C153180895 @default.
- W4300574098 hasConceptScore W4300574098C154945302 @default.
- W4300574098 hasConceptScore W4300574098C185592680 @default.
- W4300574098 hasConceptScore W4300574098C188027245 @default.
- W4300574098 hasConceptScore W4300574098C23123220 @default.
- W4300574098 hasConceptScore W4300574098C2776401178 @default.
- W4300574098 hasConceptScore W4300574098C2780226545 @default.
- W4300574098 hasConceptScore W4300574098C3017588708 @default.
- W4300574098 hasConceptScore W4300574098C41008148 @default.
- W4300574098 hasConceptScore W4300574098C41895202 @default.
- W4300574098 hasConceptScore W4300574098C49774154 @default.
- W4300574098 hasConceptScore W4300574098C50644808 @default.
- W4300574098 hasConceptScore W4300574098C59404180 @default.
- W4300574098 hasConceptScore W4300574098C71139939 @default.
- W4300574098 hasConceptScore W4300574098C81669768 @default.
- W4300574098 hasConceptScore W4300574098C83665646 @default.
- W4300574098 hasLocation W43005740981 @default.
- W4300574098 hasLocation W43005740982 @default.
- W4300574098 hasLocation W43005740983 @default.
- W4300574098 hasOpenAccess W4300574098 @default.
- W4300574098 hasPrimaryLocation W43005740981 @default.
- W4300574098 hasRelatedWork W2036586713 @default.
- W4300574098 hasRelatedWork W2052253960 @default.
- W4300574098 hasRelatedWork W2095834362 @default.
- W4300574098 hasRelatedWork W2147802381 @default.
- W4300574098 hasRelatedWork W2509918103 @default.
- W4300574098 hasRelatedWork W2783457476 @default.
- W4300574098 hasRelatedWork W2785535669 @default.
- W4300574098 hasRelatedWork W2970216048 @default.
- W4300574098 hasRelatedWork W3197541072 @default.
- W4300574098 hasRelatedWork W4300574098 @default.
- W4300574098 isParatext "false" @default.
- W4300574098 isRetracted "false" @default.
- W4300574098 workType "article" @default.