List your company

Open-Vocabulary Audio-Visual Event Localization on AVEBench (OV seen)

76.6AccuracyAVE
49.0456.19563.3570.505Nov 18, 2024

Evaluation results

MethodLinks
AVEstrategy=fine-tuning2024.1176.663.65665.4
MM-Pyramidstrategy=fine-tuning2024.1176.566.962.368.6
PSPstrategy=fine-tuning2024.1175.466.86167.7
fine-tuning baselinestrategy=fine-tuning2024.1172.561.854.562.9
CMRAstrategy=fine-tuning2024.1165.258.854.359.4
training-free baselinestrategy=training-free2024.1157.5453445.5
CLIP & CLAPstrategy=training-free2024.1151.441.431.941.6
Video-LLaMA2strategy=training-free2024.1150.140.63240.9