A Cross-Modal Conformer that fuses CLAP audio and OWL-ViT visual embeddings with a CNN-Conformer SELD backbone, trained on large synthetic data, ranks second in DCASE 2025 Task 3 Track B.
STARSS23: An audio-visual dataset of spatial recordings of real scenes with spatiotemporal annotations of sound events,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Integrating Spatial and Semantic Embeddings for Stereo Sound Event Localization in Videos
A Cross-Modal Conformer that fuses CLAP audio and OWL-ViT visual embeddings with a CNN-Conformer SELD backbone, trained on large synthetic data, ranks second in DCASE 2025 Task 3 Track B.