Share your thoughts, 1 month free Claude Pro on usSee more

Fingerspelling detection on ChicagoFSWild+ (test)

100AP (IoU=0.1)

GT

Updated 1mo ago

Evaluation Results

Method	Links
GT 2021.04		100	100	100	74.4	70	50.5	63
GT 2021.04		100	100	100	74.4	70	50.5	63
multi-task model 2021.04		59	56.2	44.8	45	41.5	27.7	50.3
Our Model 2021.04		59	56.2	44.8	45	41.5	27.7	50.3
BMN 2021.04		58	54.9	43.7	43.3	40.1	26	47
BMN 2021.04		58	54.9	43.7	43.3	40.1	26	47
Base 3 2021.04		56	52.5	42	42.6	39.6	26.4	47.7
Base 3 2021.04		56	52.5	42	42.6	39.6	26.4	47.7
Base 2 2021.04		44.3	36.6	24.7	32.3	26.5	15.2	39
Base 2 2021.04		44.3	36.6	24.7	32.3	26.5	15.2	39
Base 1 2021.04		27.8	8.2	2.5	21.1	9.3	2.9	26.7
Base 1 2021.04		27.8	8.2	2.5	21.1	9.3	2.9	26.7