Fusing frozen CLAP and OWL-ViT embeddings via a Cross-Modal Conformer, plus autocorrelation-based features, improves stereo SELD over DCASE 2025 baselines.
Our approach leverages a model that integrates semantically rich feature embeddings from CLAP and OWL-ViT, fused through an adapted Conformer architecture
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
Spatial and Semantic Embedding Integration for Stereo Sound Event Localization and Detection in Regular Videos
Fusing frozen CLAP and OWL-ViT embeddings via a Cross-Modal Conformer, plus autocorrelation-based features, improves stereo SELD over DCASE 2025 baselines.