dataset

Action-recognition-BagOfWords-Early-Late-Fusion

Spareman

or hover any field below to flag it

Overview

Name
Action-recognition-BagOfWords-Early-Late-Fusion
Source
Spareman
Episodes
0
Robot count
0
Format
other
Description
Video classification using the UCF101 dataset for action recognition. We extract SIFT, MFCC and STIP features from the videos, we encode them using the Bag of Words framework and we implement early and late feature fusion using different combinations of the feature types available.
Robots used
null

Links

HuggingFace dataset
null