Dynamic Texture Recognition on UCLA Dataset benchmark leaderboard · SOTA2 Research

Dynamic Texture Recognition on UCLA Dataset

100Accuracy (50-class)MixSHMM

Evaluation Results

Method	Links
MixSHMM2026.04		100	99.6	99.8
DFS2026.04		100	97.5	98.75
HOGF2D2026.04		100	99.2	99.6
HOGF3D2026.04		100	99.55	99.78
DDLBP2026.04		100	98.4	99.2
RUBIG2026.04		100	99.2	99.6
MEMDP2026.04		100	98.9	99.45
DBRF2026.04		100	99	99.5
PI-LBP2026.04		100	98.2	99.1
LP2DH2026.04		100	99.3	99.65
LP2DH2026.04		100	99.6	99.8
OTDL2026.04		99.8	98.2	99
STLS2026.04		99.5	97.4	98.45
MBSIF-TOP2026.04		99.5	98.75	99.13
B3DF SMC2026.04		99.5	98.85	99.18
AlexNet2026.04		99.5	98.05	98.78
DT-GoogleNet2026.04		99.5	98.35	98.93
FDT2026.04		99	97.7	98.35
FD-MAP2026.04		99	99.35	99.18
CVLBC2026.04		99	99.2	99.1
JVDL2026.04		97.83	—	—
DL-PEGASOS2026.04		97.5	95.6	96.55
RNNs2026.04		97.05	98.54	97.8
HEM-DTM2026.04		96.55	—	—
LBP-TOP2026.04		94.5	96	95.25
VLBP2026.04		89.5	96.3	92.9
DNGP2026.04		—	99.6	—