Toward Accurate Person-level Action Recognition in Videos of Crowded Scenes

10/16/2020
by   Li Yuan, et al.
1

Detecting and recognizing human action in videos with crowded scenes is a challenging problem due to the complex environment and diversity events. Prior works always fail to deal with this problem in two aspects: (1) lacking utilizing information of the scenes; (2) lacking training data in the crowd and complex scenes. In this paper, we focus on improving spatio-temporal action recognition by fully-utilizing the information of scenes and collecting new data. A top-down strategy is used to overcome the limitations. Specifically, we adopt a strong human detector to detect the spatial location of each frame. We then apply action recognition models to learn the spatio-temporal information from video frames on both the HIE dataset and new data with diverse scenes from the internet, which can improve the generalization ability of our model. Besides, the scenes information is extracted by the semantic segmentation model to assistant the process. As a result, our method achieved an average 26.05 wf_mAP (ranking 1st place in the ACM MM grand challenge 2020: Human in Events).

READ FULL TEXT

page 3

page 4

research
10/16/2020

Towards Accurate Human Pose Estimation in Videos of Crowded Scenes

Video-based human pose estimation in crowded scenes is a challenging pro...
research
06/13/2017

Joint Max Margin and Semantic Features for Continuous Event Detection in Complex Scenes

In this paper the problem of complex event detection in the continuous d...
research
12/14/2018

TAN: Temporal Aggregation Network for Dense Multi-label Action Recognition

We present Temporal Aggregation Network (TAN) which decomposes 3D convol...
research
11/16/2017

Skepxels: Spatio-temporal Image Representation of Human Skeleton Joints for Action Recognition

Human skeleton joints are popular for action analysis since they can be ...
research
07/02/2020

Estimating Blink Probability for Highlight Detection in Figure Skating Videos

Highlight detection in sports videos has a broad viewership and huge com...
research
03/16/2023

Learning Physical-Spatio-Temporal Features for Video Shadow Removal

Shadow removal in a single image has received increasing attention in re...
research
11/28/2018

Unrepresentative video data: A review and evaluation

It is well known that the quality and quantity of training data are sign...

Please sign up or login with your details

Forgot password? Click here to reset