Proceedings ArticleDOI
Unsupervised Temporal Segmentation of Human Action Using Community Detection
Hiteshi Jain,Gaurav Harit +1 more
- pp 1892-1896
Reads0
Chats0
TLDR
This work presents a novel community detection-based human action segmentation algorithm that marks the existence of community structures in human action videos where the consecutive frames around the key poses group together to form communities similar to social networks.Abstract:
Temporal segmentation of complex human action videos into action primitives plays a pivotal role in building models for human action understanding Studies in the past have introduced unsupervised frameworks for deriving a known number of motion primitives from action videos Our work focuses towards answering a question: Given a set of videos with humans performing an activity, can the action primitives be derived from them without specifying any prior knowledge about the count for the constituting sub-actions categories? To this end, we present a novel community detection-based human action segmentation algorithm Our work marks the existence of community structures in human action videos where the consecutive frames around the key poses group together to form communities similar to social networks We test our proposed technique over the stitched Weizmann dataset and MHADI01-s motion capture dataset and our technique outperforms the state-of-the-art techniques of complex action segmentation without the count of actions being pre-specifiedread more
Citations
More filters
Posted Content
Action Shuffle Alternating Learning for Unsupervised Action Segmentation
Jun Li,Sinisa Todorovic +1 more
TL;DR: This paper addresses unsupervised action segmentation with a new self-supervised learning (SSL) of a feature embedding that accounts for both frame- and action-level structure of videos.
Proceedings ArticleDOI
Action Shuffle Alternating Learning for Unsupervised Action Segmentation
Jun Li,Sinisa Todorovic +1 more
TL;DR: In this article, a self-supervised learning of a feature embedding that accounts for both frame and action-level structure of videos is proposed, where action segments are sampled from videos, where the sampled action segments respect their time ordering in the video, and in the latter they are shuffled.
Journal ArticleDOI
Detecting action-relevant regions for action recognition using a three-stage saliency detection technique
Xiaofang Wang,Chun Qi +1 more
TL;DR: Experimental results on four benchmark datasets demonstrate that the proposed three-stage saliency detection technique to recover action-relevant regions performs better than the conventional dense tracking and competitively with its improved versions.
Book ChapterDOI
Action Segmentation for RGB Video Frames Using Skeleton 3D Data of NTURGB+D
TL;DR: In this paper , a 3D skeleton information on RGB videos of NTURGB+D has been used for action segmentation and the experimental results have shown the performance and it test results on five random action videos.
Proceedings ArticleDOI
Leveraging information from imperfect examples: Common action sequence mining from a mix of incorrect performances
Hiteshi Jain,Gaurav Harit +1 more
TL;DR: This work introduces a novel Community Detection based unsupervised framework that provides mechanisms to interpret video data and address its limitations to produce better action representation and proposes a technique to learn the temporal order of these key poses from these imperfect videos.
References
More filters
Journal ArticleDOI
Fast unfolding of communities in large networks
Vincent D. Blondel,Jean-Loup Guillaume,Jean-Loup Guillaume,Renaud Lambiotte,Renaud Lambiotte,Etienne Lefebvre +5 more
TL;DR: This work proposes a heuristic method that is shown to outperform all other known community detection methods in terms of computation time and the quality of the communities detected is very good, as measured by the so-called modularity.
Journal ArticleDOI
Finding and evaluating community structure in networks.
TL;DR: It is demonstrated that the algorithms proposed are highly effective at discovering community structure in both computer-generated and real-world network data, and can be used to shed light on the sometimes dauntingly complex structure of networked systems.
Journal ArticleDOI
Fast unfolding of communities in large networks
Vincent D. Blondel,Jean-Loup Guillaume,Jean-Loup Guillaume,Renaud Lambiotte,Renaud Lambiotte,Etienne Lefebvre +5 more
TL;DR: In this paper, the authors proposed a simple method to extract the community structure of large networks based on modularity optimization, which is shown to outperform all other known community detection methods in terms of computation time.
Proceedings Article
On Spectral Clustering: Analysis and an algorithm
TL;DR: A simple spectral clustering algorithm that can be implemented using a few lines of Matlab is presented, and tools from matrix perturbation theory are used to analyze the algorithm, and give conditions under which it can be expected to do well.
Journal ArticleDOI
Community detection algorithms: a comparative analysis.
TL;DR: Three recent algorithms introduced by Rosvall and Bergstrom and Ronhovde and Nussinov have an excellent performance, with the additional advantage of low computational complexity, which enables one to analyze large systems.