In group activity recognition, the temporal dynamics of the whole activity can be inferred
based on the dynamics of the individual people representing the activity. We build a deep …

Activity recognition has become an important function in many emerging computer vision
applications eg automatic video surveillance system, human-computer interaction …

Group activity recognition, a challenging task that a number of individuals occur in the scene
of activity while only a small subset of them participate in, has received increasing attentions …

This work is about recognizing human activities occurring in videos at distinct semantic
levels, including individual actions, interactions, and group activities. The recognition is …

This paper presents a deep neural-network-based hierarchical graphical model for
individual and group activity recognition in surveillance scenes. Deep networks are used to …

We present an end-to-end deep Convolutional Neural Network called Convolutional
Relational Machine (CRM) for recognizing group activities that utilizes the information in …

In this paper, we propose a Semantics-Preserving Teacher-Student (SPTS) model for group
activity recognition in videos, which aims to mine the semantics-preserving attention to …

Group activity recognition plays a fundamental role in a variety of applications, eg sports
video analysis and intelligent surveillance. How to model the spatio-temporal contextual …

Modeling of high order interactional context, eg, group interaction, lies in the central of
collective/group activity recognition. However, most of the previous activity recognition …

Rich semantic relations are important in a variety of visual recognition problems. As a
concrete example, group activity recognition involves the interactions and relative spatial …