List your company

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

65.6AccuracyHSCHG
32.42441.03749.6558.263Nov 18, 2024Feb 20, 2025May 25, 2025Aug 27, 2025Nov 29, 2025Mar 3, 2026Jun 5, 2026

Evaluation results

MethodLinks
HSCHG2026.0665.655.748.256.5
fine-tuning baselinestrategy=fine-tuning2024.1164.95547.555.8
OV-AVE2026.0664.95547.555.8
training-free baselinestrategy=training-free2024.1159.847.33447
CLIP & CLAPstrategy=training-free2024.1151.642.231.641.8
Video-LLaMA2strategy=training-free2024.1148.538.52938.6
AVEstrategy=fine-tuning2024.1144.633.22434
AVE2026.0644.633.22434
MM-Pyramidstrategy=fine-tuning2024.1136.82923.829.9
MM-Pyramid2026.0636.82923.829.9
CMRAstrategy=fine-tuning2024.11363126.331.1
CMRA2026.06363126.331.3
PSPstrategy=fine-tuning2024.1133.728.224.228.7
PSP2026.0633.728.224.228.7