Visual Speech Recognition on DVSpeaker Matched-scene benchmark leaderboard · SOTA2 Research

Visual Speech Recognition on DVSpeaker Matched-scene

100SI Accuracy (0°)Get

Evaluation Results

Method	Links
Get2026.04		100	100	99.6	99.8
EV-Gait2026.04		100	100	100	100
EST2026.04		100	99.9	100	100
Tin2026.04		100	100	99.8	99.4
Slowonly2026.04		100	100	99.9	100
R2plus1d2026.04		100	99.9	100	100
Tsn2026.04		100	100	100	100
C3d2026.04		100	100	100	100
NeuroLip2026.04		100	100	100	100
Slowfast2026.04		99.9	99.8	99.2	100
Tsm2026.04		99.9	99.5	99.9	99.9
MSTP2026.04		99.8	99.4	99.1	99.8
Tanet2026.04		99.8	99.9	99.8	99.9
C2d2026.04		99.8	98.9	99.1	100
Trn2026.04		97.9	99.3	99.8	97.9
Timesformer2026.04		95	97.5	96.6	89.9
MTGA2026.04		93.85	97.58	96.98	94.56
ANN2026.04		93.3	92.4	96.6	81.8
SpikGRU2+2026.04		88.4	87.5	94.4	85.5
EgoEvGesture2026.04		80.7	83.9	83.6	71.6
Uniformerv22026.04		35	51.9	40.6	25.6