List your company

Text-to-Video-Audio Retrieval on YouCook2

51.3Recall@1MiCo
13.65223.42633.242.974Oct 7, 2023Nov 17, 2023Dec 29, 2023Feb 9, 2024Mar 21, 2024May 2, 2024Jun 13, 2024

Evaluation results

MethodLinks
MiCo2024.0651.3———
SOTA2024.0631.3———
HowToCaptionVision Encoder=S3D, Input Modality=Text-video+audio, Evaluation Protocol=Zero-shot2023.1025.551.163.65
EAOVision Encoder=S3D, Input Modality=Text-video+audio, Evaluation Protocol=Zero-shot2023.1024.648.360.46
TANVision Encoder=S3D, Input Modality=Text-video only, Evaluation Protocol=Zero-shot2023.1020.145.559.57
AVLNetVision Encoder=ResNet-152+ResNeXt101, Input Modality=Text-video+audio, Evaluation Protocol=Zero-shot2023.1019.936.144.316
MCNVision Encoder=ResNet-152+ResNeXt101, Input Modality=Text-video+audio, Evaluation Protocol=Zero-shot2023.1018.135.545.2—
MIL-NCEVision Encoder=S3D, Input Modality=Text-video only, Evaluation Protocol=Zero-shot2023.1015.13851.210