RhyRNN: Rhythmic RNN for Recognizing Events in Long and Complex Videos

Abstract

Though many successful approaches have been proposed for recognizing events in short and homogeneous videos, doing so with long and complex videos remains a challenge. One particular reason is that events in long and complex videos can consist of multiple heterogeneous sub-activities (in terms of rhythms, activity variants, composition order, etc.) within quite a long period. This fact brings about two main difficulties: excessive/varying length and complex video dynamic/rhythm. To address this, we propose Rhythmic RNN (RhyRNN) which is capable of handling long video sequences (up to 3,000 frames) as well as capturing rhythms at different scales. We also propose two novel modules: diversity-driven pooling (DivPool) and bilinear reweighting (BR), which consistently and hierarchically abstract higher-level information. We study the behavior of RhyRNN and empirically show that our method works well even when mphonly event-level labels are available in the training stage (compared to algorithms requiring sub-activity labels for recognition), and thus is more practical when the sub-activity labels are missing or difficult to obtain. Extensive experiments on several public datasets demonstrate that, even mphwithout fine-tuning the feature backbones, our method can achieve promising performance for long and complex videos that contain multiple sub-activities.

Tasks

Reproductions