AI Paper Atlas

Research map / Benchmarks / HMDB51

HMDB51 leaderboard

92 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on HMDB51. Best accuracy: 84.6 (SCT-L (K400 pretrain), NeurIPS 2021).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

HMDB51 · accuracy

92 papers, each with its best reported number for its own method; higher is better.

#accuracy ↑MethodPaperTopic
184.6SCT-L (K400 pretrain)Shifted Chunk Transformer for Spatio-Temporal Representational Learning
NeurIPS 2021 · Table 6
Action recognition
284.3SMART + TSN+Kinetics
TSN+Kinetics
SMART Frame Selection for Action Recognition
AAAI 2021 · Table: Extending SMART as a pr
Action recognition
383.4ZeroI2V
CLIP+K400 ViT-L/14
ZeroI2V: Zero-Cost Adaptation of Pre-Trained Transformers from Image to Video
ECCV 2024 · Table 6
Video segmentation and tracking
481.5CVPT SL
ViT-L
Compressed Video Prompt Tuning
NeurIPS 2023 · Table 1
Video segmentation and tracking
581.3STRM
ViT
Spatio-Temporal Relation Modeling for Few-Shot Action Recognition
CVPR 2022 · Table 1
Action recognition
680.4DG-P3D
ResNet-101
Optimization Planning for 3D ConvNets
ICML 2021 · Table: HMDB51 & UCF101 compari
Action recognition
779.7MVD-B
ViT-B
Masked Video Distillation: Rethinking Masked Feature Modeling for Self-Supervised Video Representation Learning
CVPR 2023 · UCF101 and HMDB51 comparison t
Video segmentation and tracking
879.3AWSD (ResNet-101)
ResNet-101
AWSD: Adaptive Weighted Spatiotemporal Distillation for Video Representation
ICCV 2019 · Table 7
Action recognition
978.7R(2+1)D-TwoStream
R(2+1)D-34, Kinetics-pretrained
A Closer Look at Spatiotemporal Convolutions for Action Recognition
CVPR 2018 · Table 6
Action recognition
1078.1I3D Taylor
I3D, Kinetics pretraining
Taylor Videos for Action Recognition
ICML 2024 · Table 1
Action recognition
82 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.