Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Group-level video emotion classification on VGAF (val)
Loading...
81.98
Accuracy
Multimodal fusion (TimeSformer, wav2vec2.0, YOLOv8)
50.0728
58.3564
66.64
74.9236
Mar 31, 2021
Feb 7, 2022
Dec 18, 2022
Oct 28, 2023
Sep 6, 2024
Jul 17, 2025
May 27, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Multimodal fusion (TimeSformer, wav2vec2.0, YOLOv8)
Authors=Kumar et al. [...
2026.05
81.98
Hybrid Network
Modality=A, V, Classes=3
2026.05
74.28
MobileNet-v1
Modality=A, V, Classes=3
2026.05
71.95
Fusion of 14 models
Modality=A, V, Classes=3
2026.05
71.93
EfficientNET
Modality=V, Classes=3
2026.05
70.33
EfficientNet-B2
Modality=Video-only
2021.03
69.84
MobileNet-v1
Modality=Video-only
2021.03
68.92
EfficientNet-B0
Modality=Video-only
2021.03
66.8
K-injection network
Modality=A, V, Classes=3
2026.05
66.19
DenseNet-121 (FER+)
Modality=Video-only
2021.03
64.75
RexNet-150
Modality=Video-only
2021.03
63.58
Activity Recognition Networks
Modality=Video-only
2021.03
62.4
Resnet-50, BiLSTM and fusion SVM
Modality=A, V, Classes=3
2026.05
62.4
Early fusion with LSTM and MLP
Modality=A, V, Classes=3
2026.05
61.61
Deep Spectrum
Modality=A, Classes=3
2026.05
59.4
VGG-19
Modality=Img, Classes=3
2026.05
52.36
Inception+LSTM (baseline)
Modality=Video-only
2021.03
52.09
Inception-V3, CNN-LSTM
Modality=A, V, Classes=3
2026.05
51.3
Feedback
Search any
task
Search any
task