Featureless: Bypassing feature extraction in action categorization

Silvia Pintea, Pascal Mettes, Jan van Gemert, AWM Smeulders

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

2 Citations (Scopus)
15 Downloads (Pure)


This method introduces an efficient manner of learning action categories without the need of feature estimation. The approach starts from low-level values, in a similar style to the successful CNN methods. However, rather than extracting general image features, we learn to predict specific video representations from raw video data. The benefit of such an approach is that at the same computational expense it can predict 2D video representations as well as 3D ones, based on motion. The proposed model relies on discriminative Wald-boost, which we enhance to a multiclass formulation for the purpose of learning video representations. The suitability of the proposed approach as well as its time efficiency are tested on the UCF11 action recognition dataset.
Original languageEnglish
Title of host publication2016 IEEE International Conference on Image Processing (ICIP)
Subtitle of host publicationProceedings
Place of PublicationPiscataway
Number of pages5
ISBN (Electronic)978-1-4673-9961-6
ISBN (Print)978-1-4673-9962-3
Publication statusPublished - 2016
Event2016 IEEE International Conference on Image Processing (ICIP) - Phoenix, United States
Duration: 25 Sept 201628 Sept 2016


Conference2016 IEEE International Conference on Image Processing (ICIP)
Country/TerritoryUnited States


  • Multiclass Waldboost
  • video representations
  • action recognition
  • feature learning


Dive into the research topics of 'Featureless: Bypassing feature extraction in action categorization'. Together they form a unique fingerprint.

Cite this