This paper surveys the state of the art on multimodal gesture recognition and introduces the
JMLR special topic on gesture recognition 2011–2015. We began right at the start of the …

In this work we improve training of temporal deep models to better learn activity progression
for activity detection and early detection. Conventionally, when training a Recurrent Neural …

We propose an effective approach for spatio-temporal action localization in realistic videos.
The approach first detects proposals at the frame-level and scores them with a combination …

The ability to analyze the actions which occur in a video is essential for automatic
understanding of sports. Action localization and recognition in videos are two main research …

This paper introduces a state-of-the-art video representation and applies it to efficient action
recognition and detection. We first propose to improve the popular dense trajectory features …

In this paper we target at generating generic action proposals in unconstrained videos. Each
action proposal corresponds to a temporal series of spatial bounding boxes, ie, a spatio …

Can humans fly? Emphatically no. Can cars eat? Again, absolutely not. Yet, these absurd
inferences result from the current disregard for particular types of actors in action …

This paper addresses the problems of both general and also fine-grained human action
recognition in video sequences. Compared with general human actions, fine-grained action …

At present, the development of video action recognition is very rapid in many fields, such as
video understanding, intelligent monitoring, and human-computer interaction. However …

This paper is the first to address the problem of unsupervised action localization in videos.
Given unlabeled data without bounding box annotations, we propose a novel approach that …