Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285603046> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W4285603046 abstract "We present an approach to learn voice-face representations from the talking face videos, without any identity labels. Previous works employ cross-modal instance discrimination tasks to establish the correlation of voice and face. These methods neglect the semantic content of different videos, introducing false-negative pairs as training noise. Furthermore, the positive pairs are constructed based on the natural correlation between audio clips and visual frames. However, this correlation might be weak or inaccurate in a large amount of real-world data, which leads to deviating positives into the contrastive paradigm. To address these issues, we propose the cross-modal prototype contrastive learning (CMPC), which takes advantage of contrastive methods and resists adverse effects of false negatives and deviate positives. On one hand, CMPC could learn the intra-class invariance by constructing semantic-wise positives via unsupervised clustering in different modalities. On the other hand, by comparing the similarities of cross-modal instances from that of cross-modal prototypes, we dynamically recalibrate the unlearnable instances' contribution to overall loss. Experiments show that the proposed approach outperforms state-of-the-art unsupervised methods on various voice-face association evaluation protocols. Additionally, in the low-shot supervision setting, our method also has a significant improvement compared to previous instance-wise contrastive learning." @default.
- W4285603046 created "2022-07-16" @default.
- W4285603046 creator A5053780153 @default.
- W4285603046 creator A5065635383 @default.
- W4285603046 date "2022-07-01" @default.
- W4285603046 modified "2023-10-16" @default.
- W4285603046 title "Unsupervised Voice-Face Representation Learning by Cross-Modal Prototype Contrast" @default.
- W4285603046 doi "https://doi.org/10.24963/ijcai.2022/526" @default.
- W4285603046 hasPublicationYear "2022" @default.
- W4285603046 type Work @default.
- W4285603046 citedByCount "2" @default.
- W4285603046 countsByYear W42856030462023 @default.
- W4285603046 crossrefType "proceedings-article" @default.
- W4285603046 hasAuthorship W4285603046A5053780153 @default.
- W4285603046 hasAuthorship W4285603046A5065635383 @default.
- W4285603046 hasBestOaLocation W42856030461 @default.
- W4285603046 hasConcept C119857082 @default.
- W4285603046 hasConcept C144024400 @default.
- W4285603046 hasConcept C153180895 @default.
- W4285603046 hasConcept C154945302 @default.
- W4285603046 hasConcept C185592680 @default.
- W4285603046 hasConcept C188027245 @default.
- W4285603046 hasConcept C204321447 @default.
- W4285603046 hasConcept C2776502983 @default.
- W4285603046 hasConcept C2779304628 @default.
- W4285603046 hasConcept C28490314 @default.
- W4285603046 hasConcept C36289849 @default.
- W4285603046 hasConcept C41008148 @default.
- W4285603046 hasConcept C64869954 @default.
- W4285603046 hasConcept C71139939 @default.
- W4285603046 hasConceptScore W4285603046C119857082 @default.
- W4285603046 hasConceptScore W4285603046C144024400 @default.
- W4285603046 hasConceptScore W4285603046C153180895 @default.
- W4285603046 hasConceptScore W4285603046C154945302 @default.
- W4285603046 hasConceptScore W4285603046C185592680 @default.
- W4285603046 hasConceptScore W4285603046C188027245 @default.
- W4285603046 hasConceptScore W4285603046C204321447 @default.
- W4285603046 hasConceptScore W4285603046C2776502983 @default.
- W4285603046 hasConceptScore W4285603046C2779304628 @default.
- W4285603046 hasConceptScore W4285603046C28490314 @default.
- W4285603046 hasConceptScore W4285603046C36289849 @default.
- W4285603046 hasConceptScore W4285603046C41008148 @default.
- W4285603046 hasConceptScore W4285603046C64869954 @default.
- W4285603046 hasConceptScore W4285603046C71139939 @default.
- W4285603046 hasLocation W42856030461 @default.
- W4285603046 hasLocation W42856030462 @default.
- W4285603046 hasOpenAccess W4285603046 @default.
- W4285603046 hasPrimaryLocation W42856030461 @default.
- W4285603046 hasRelatedWork W1775397219 @default.
- W4285603046 hasRelatedWork W2011478067 @default.
- W4285603046 hasRelatedWork W2347601237 @default.
- W4285603046 hasRelatedWork W2383164569 @default.
- W4285603046 hasRelatedWork W2897995864 @default.
- W4285603046 hasRelatedWork W2961085424 @default.
- W4285603046 hasRelatedWork W4286629047 @default.
- W4285603046 hasRelatedWork W4306321456 @default.
- W4285603046 hasRelatedWork W4306674287 @default.
- W4285603046 hasRelatedWork W4224009465 @default.
- W4285603046 isParatext "false" @default.
- W4285603046 isRetracted "false" @default.
- W4285603046 workType "article" @default.