VGGSound
PulseAugur coverage of VGGSound — every cluster mentioning VGGSound across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New X-AVDD method boosts audio-visual dataset distillation efficiency
Researchers have developed X-AVDD, a novel method for audio-visual dataset distillation that significantly improves memory efficiency and cross-modal semantic correspondence. This new approach reduces synthesis costs by…
-
AI models analyzed for expressive range in cat vocalizations
Researchers have developed a methodology to analyze the expressive range of text-to-audio models, applying it specifically to cat vocalizations. By generating numerous audio clips from different prompts and models, they…
-
New AVENUE benchmark targets audio-video editing model evaluation
Researchers have introduced AVENUE, a new benchmark and evaluation framework designed to improve audio-video editing models. The AVENUE benchmark includes 1,291 source clips and 7,957 editing instructions, curated from …
-
AV-JEPA model advances audio-visual self-supervised learning
Researchers have introduced AV-JEPA, a new self-supervised learning model that extends LeJEPA to handle both audio and visual data. This model utilizes an early-fusion Vision Transformer and modality dropout for masking…
-
FoleyGenEx framework unifies video-to-audio generation with advanced controls
Researchers have introduced FoleyGenEx, a novel framework for unified video-to-audio generation that addresses limitations in existing methods. FoleyGenEx integrates multi-modal control, frame-level temporal alignment, …