W-talc: Weakly-supervised temporal activity localization and classification
Most activity localization methods in the literature suffer from the burden of frame-wise
annotation requirement. Learning from weak labels may be a potential solution towards …
annotation requirement. Learning from weak labels may be a potential solution towards …
Spatio-temporal attention-based LSTM networks for 3D action recognition and detection
Human action analytics has attracted a lot of attention for decades in computer vision. It is
important to extract discriminative spatio-temporal features to model the spatial and temporal …
important to extract discriminative spatio-temporal features to model the spatial and temporal …
Skeleton-based online action prediction using scale selection network
Action prediction is to recognize the class label of an ongoing activity when only a part of it is
observed. In this paper, we focus on online action prediction in streaming 3D skeleton …
observed. In this paper, we focus on online action prediction in streaming 3D skeleton …
Online human action detection using joint classification-regression recurrent neural networks
Human action recognition from well-segmented 3D skeleton data has been intensively
studied and has been attracting an increasing attention. Online action detection goes one …
studied and has been attracting an increasing attention. Online action detection goes one …
Fast action proposals for human action detection and search
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 …
action proposal corresponds to a temporal series of spatial bounding boxes, ie, a spatio …
A survey on deep learning-based spatio-temporal action detection
Spatio-temporal action detection (STAD) aims to classify the actions present in a video and
localize them in space and time. It has become a particularly active area of research in …
localize them in space and time. It has become a particularly active area of research in …
Tacnet: Transition-aware context network for spatio-temporal action detection
Current state-of-the-art approaches for spatio-temporal action detection have achieved
impressive results but remain unsatisfactory for temporal extent detection. The main reason …
impressive results but remain unsatisfactory for temporal extent detection. The main reason …
Action graphs: Weakly-supervised action localization with graph convolution networks
We present a method for weakly-supervised action localization based on graph
convolutions. In order to find and classify video time segments that correspond to relevant …
convolutions. In order to find and classify video time segments that correspond to relevant …
In defence of negative mining for annotating weakly labelled data
We propose a novel approach to annotating weakly labelled data. In contrast to many
existing approaches that perform annotation by seeking clusters of self-similar exemplars …
existing approaches that perform annotation by seeking clusters of self-similar exemplars …
Spot on: Action localization from pointly-supervised proposals
We strive for spatio-temporal localization of actions in videos. The state-of-the-art relies on
action proposals at test time and selects the best one with a classifier trained on carefully …
action proposals at test time and selects the best one with a classifier trained on carefully …