HMDB51

Dataset Information
Modalities
Videos
Introduced
2011
License
CC BY 4.0
Homepage
Official Website
Contents

Overview

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
Image Source: https://serre-lab.clps.brown.edu/resource/hmdb-a-large-human-motion-database

Variants: HMDB51-skeleton, HMDB51 (finetuned), HMDB51, HMDB-51

Associated Benchmarks

This dataset is used in 3 benchmarks:

Recent Benchmark Submissions

Task Model Paper Date
Zero-Shot Action Recognition TC-CLIP Leveraging Temporal Contextualization for Video … 2024-04-15
Zero-Shot Action Recognition OST OST: Refining Text Knowledge with … 2023-11-30
Zero-Shot Action Recognition OTI(ViT-L/14) Orthogonal Temporal Interpolation for Zero-Shot … 2023-08-14
Action Recognition MSQNet Actor-agnostic Multi-label Action Recognition with … 2023-07-20
Zero-Shot Action Recognition MSQNet Actor-agnostic Multi-label Action Recognition with … 2023-07-20
Zero-Shot Action Recognition IMP-MoE-L Alternating Gradient Descent and Mixture-of-Experts … 2023-05-10
Zero-Shot Action Recognition SPOT Synthetic Sample Selection for Generalized … 2023-04-06
Zero-Shot Action Recognition VicTR (ViT-B/16) VicTR: Video-conditioned Text Representations for … 2023-04-05
Zero-Shot Action Recognition MAXI MAtch, eXpand and Improve: Unsupervised … 2023-03-15
Zero-Shot Action Recognition BIKE Bidirectional Cross-Modal Knowledge Exploration for … 2022-12-31
Zero-Shot Action Recognition VideoCoCa VideoCoCa: Video-Text Modeling with Zero-Shot … 2022-12-09
Zero-Shot Action Recognition X-CLIP Expanding Language-Image Pretrained Models for … 2022-08-04
Zero-Shot Action Recognition MOV (ViT-B/16) Multimodal Open-Vocabulary Video Classification via … 2022-07-15
Zero-Shot Action Recognition MOV (ViT-L/14) Multimodal Open-Vocabulary Video Classification via … 2022-07-15
Zero-Shot Action Recognition Text4Vis Revisiting Classifier: Transferring Vision-Language Models … 2022-07-04
Zero-Shot Action Recognition ResT Cross-modal Representation Learning for Zero-shot … 2022-05-03
Zero-Shot Action Recognition AURL Alignment-Uniformity aware Representation Learning for … 2022-03-29
Zero-Shot Action Recognition ER-ZSAR Elaborative Rehearsal for Zero-shot Action … 2021-08-05
Zero-Shot Action Recognition CLASTER CLASTER: Clustering with Reinforcement Learning … 2021-01-18
Zero-Shot Action Recognition E2E Rethinking Zero-shot Video Classification: End-to-end … 2020-03-03

Research Papers

Recent papers with results on this dataset:

External Links: