Table Of Contents

Previous topic

datasets. Framework for working with different datasets

Next topic

Sports-1M Dataset

HMDB: A Large Human Motion Database

class AR_hmdb

Implements loading dataset:

“HMDB: A Large Human Motion Database”: http://serre-lab.clps.brown.edu/resource/hmdb-a-large-human-motion-database/

Note

Usage

  1. From link above download dataset files: hmdb51_org.rar & test_train_splits.rar.
  2. Unpack them.
  3. To load data run: ./opencv/build/bin/example_datasets_ar_hmdb -p=/home/user/path_to_unpacked_folders/

Benchmark

For this dataset was implemented benchmark with accuracy: 0.107407 (using precomputed HOG/HOF “STIP” features from site, averaging for 3 splits)

To run this benchmark execute:

./opencv/build/bin/example_datasets_ar_hmdb_benchmark -p=/home/user/path_to_unpacked_folders/

(precomputed features should be unpacked in the same folder: /home/user/path_to_unpacked_folders/hmdb51_org_stips/)

References:

[Kuehne11]
  1. Kuehne, H. Jhuang, E. Garrote, T. Poggio, and T. Serre. HMDB: A Large Video Database for Human Motion Recognition. ICCV, 2011
[Laptev08]
  1. Laptev, M. Marszalek, C. Schmid, and B. Rozenfeld. Learning Realistic Human Actions From Movies. CVPR, 2008