Towards understanding action recognition

2013

Conference Paper

ps


Although action recognition in videos is widely studied, current methods often fail on real-world datasets. Many recent approaches improve accuracy and robustness to cope with challenging video sequences, but it is often unclear what affects the results most. This paper attempts to provide insights based on a systematic performance evaluation using thoroughly-annotated data of human actions. We annotate human Joints for the HMDB dataset (J-HMDB). This annotation can be used to derive ground truth optical flow and segmentation. We evaluate current methods using this dataset and systematically replace the output of various algorithms with ground truth. This enables us to discover what is important – for example, should we work on improving flow algorithms, estimating human bounding boxes, or enabling pose estimation? In summary, we find that highlevel pose features greatly outperform low/mid level features; in particular, pose over time is critical, but current pose estimation algorithms are not yet reliable enough to provide this information. We also find that the accuracy of a top-performing action recognition framework can be greatly increased by refining the underlying low/mid level features; this suggests it is important to improve optical flow and human detection algorithms. Our analysis and JHMDB dataset should facilitate a deeper understanding of action recognition algorithms.

Author(s): Hueihan Jhuang and Juergen Gall and Silvia Zuffi and Cordelia Schmid and Michael J. Black
Book Title: IEEE International Conference on Computer Vision (ICCV)
Pages: 3192-3199
Year: 2013
Month: December
Publisher: IEEE

Department(s): Perceiving Systems
Research Project(s): Understanding Action Recognition (JHMDB)
Bibtex Type: Conference Paper (inproceedings)
Paper Type: Conference

Address: Sydney, Australia
DOI: 10.1109/ICCV.2013.396

Links: Website
Errata
Poster
Paper
Slides

BibTex

@inproceedings{Jhuang:ICCV:2013,
  title = {Towards understanding action recognition},
  author = {Jhuang, Hueihan and Gall, Juergen and Zuffi, Silvia and Schmid, Cordelia and Black, Michael J.},
  booktitle = {IEEE International Conference on Computer Vision (ICCV)},
  pages = {3192-3199},
  publisher = {IEEE},
  address = {Sydney, Australia},
  month = dec,
  year = {2013},
  month_numeric = {12}
}