Learning Latent Spatio-Temporal Compositional Model for Human Action Recognition

02/01/2015
by   Xiaodan Liang, et al.
0

Action recognition is an important problem in multimedia understanding. This paper addresses this problem by building an expressive compositional action model. We model one action instance in the video with an ensemble of spatio-temporal compositions: a number of discrete temporal anchor frames, each of which is further decomposed to a layout of deformable parts. In this way, our model can identify a Spatio-Temporal And-Or Graph (STAOG) to represent the latent structure of actions e.g. triple jumping, swinging and high jumping. The STAOG model comprises four layers: (i) a batch of leaf-nodes in bottom for detecting various action parts within video patches; (ii) the or-nodes over bottom, i.e. switch variables to activate their children leaf-nodes for structural variability; (iii) the and-nodes within an anchor frame for verifying spatial composition; and (iv) the root-node at top for aggregating scores over temporal anchor frames. Moreover, the contextual interactions are defined between leaf-nodes in both spatial and temporal domains. For model training, we develop a novel weakly supervised learning algorithm which iteratively determines the structural configuration (e.g. the production of leaf-nodes associated with the or-nodes) along with the optimization of multi-layer parameters. By fully exploiting spatio-temporal compositions and interactions, our approach handles well large intra-class action variance (e.g. different views, individual appearances, spatio-temporal structures). The experimental results on the challenging databases demonstrate superior performance of our approach over other competing methods.

READ FULL TEXT

page 2

page 3

page 4

page 5

page 7

page 8

page 9

research
11/02/2021

Revisiting spatio-temporal layouts for compositional action recognition

Recognizing human actions is fundamentally a spatio-temporal reasoning p...
research
10/06/2021

SAIC_Cambridge-HuPBA-FBK Submission to the EPIC-Kitchens-100 Action Recognition Challenge 2021

This report presents the technical details of our submission to the EPIC...
research
03/20/2022

Point3D: tracking actions as moving points with 3D CNNs

Spatio-temporal action recognition has been a challenging task that invo...
research
02/03/2015

Incorporating Structural Alternatives and Sharing into Hierarchy for Multiclass Object Recognition and Detection

This paper proposes a reconfigurable model to recognize and detect multi...
research
02/03/2015

Dynamical And-Or Graph Learning for Object Shape Modeling and Detection

This paper studies a novel discriminative part-based model to represent ...
research
05/17/2019

Neural Message Passing on Hybrid Spatio-Temporal Visual and Symbolic Graphs for Video Understanding

Many problems in video understanding require labeling multiple activitie...
research
10/21/2014

Compositional Structure Learning for Action Understanding

The focus of the action understanding literature has predominately been ...

Please sign up or login with your details

Forgot password? Click here to reset