Discriminatively Trained Latent Ordinal Model for Video Classification
This work addresses video classification problems in facial analysis and human action recognition, representing an incremental advancement over existing methods.
The paper tackles video classification for facial analysis and human action recognition by proposing a weakly supervised learning method that models videos as sequences of discriminative sub-events, achieving consistent improvements over competitive baselines on multiple challenging datasets.
We study the problem of video classification for facial analysis and human action recognition. We propose a novel weakly supervised learning method that models the video as a sequence of automatically mined, discriminative sub-events (eg. onset and offset phase for "smile", running and jumping for "highjump"). The proposed model is inspired by the recent works on Multiple Instance Learning and latent SVM/HCRF -- it extends such frameworks to model the ordinal aspect in the videos, approximately. We obtain consistent improvements over relevant competitive baselines on four challenging and publicly available video based facial analysis datasets for prediction of expression, clinical pain and intent in dyadic conversations and on three challenging human action datasets. We also validate the method with qualitative results and show that they largely support the intuitions behind the method.