HMDB51

Introduced by Hildegard Kuehne et al. in HMDB: A large video database for human motion recognition

The HMDB51 dataset is a large collection of realistic videos from various sources, including movies and web videos. The dataset is composed of 6,766 video clips from 51 action categories (such as “jump”, “kiss” and “laugh”), with each category containing at least 101 clips. The original evaluation scheme uses three different training/testing splits. In each split, each action class has 70 clips for training and 30 clips for testing. The average accuracy over these three splits is used to measure the final performance.

Source: Action Recognition with Trajectory-Pooled Deep-Convolutional Descriptors

Homepage

Benchmarks

Add a new result Link an existing benchmark

Task	Dataset Variant	Best Model
Action Recognition	HMDB-51	VideoMAE V2-g
Self-Supervised Action Recognition	HMDB51	MVD
Zero-Shot Action Recognition	HMDB51	MOV
Self-Supervised Action Recognition	HMDB51 (finetuned)	BraVe:V-FA
Self-supervised Video Retrieval	HMDB51	SCE
Few Shot Action Recognition	HMDB51	STRM
Self-Supervised Action Recognition Linear	HMDB51	XKD
Action Recognition	HMDB51	MSQNet
Action Recognition In Videos	HMDB-51	STM
Skeleton Based Action Recognition	HMDB51	Structured Keypoint Pooling
Action Classification	HMDB51	DualPath w/ ViT-B/16 MLPs.