Our new X account is live! Follow @wizwand_team for updates

Video-grounded Dialogue Generation on VSTAR (test)

0.092BLEU-1

AVDT ViT

Updated 3d ago

Evaluation Results

Method	Links
AVDT ViT 2023.05		0.092	0.041	0.023	0.014	0.041	0.082	0.144
AVDT w/o seg (3 frames) 2023.05		0.09	0.04	0.022	0.014	0.041	0.081	0.139
AVDT 2023.05		0.089	0.04	0.022	0.014	0.041	0.082	0.145
AVDT Faster-RCNN 2023.05		0.089	0.04	0.022	0.014	0.04	0.08	0.137
AVDT w/o seg (1 frame) 2023.05		0.087	0.039	0.021	0.013	0.039	0.077	0.126
AVDT w/o seg text-only 2023.05		0.085	0.037	0.021	0.013	0.037	0.075	0.126
AVDT w/o seg query-only 2023.05		0.082	0.035	0.019	0.011	0.037	0.073	0.119
OpenViDial coarse 2023.05		0.075	0.026	0.013	0.006	0.035	0.063	0.066
RLM 2023.05		0.072	0.032	0.017	0.01	0.032	0.061	0.079