Book ChapterDOI
Modeling sense disambiguation of human pose: recognizing action at a distance by key poses
Snehasis Mukherjee,Sujoy Kumar Biswas,Dipti Prasad Mukherjee +2 more
- pp 244-255
Reads0
Chats0
TLDR
A methodology for recognizing actions at a distance by watching the human poses and deriving descriptors that capture the motion patterns of the poses and shows the efficacy of this approach when compared to the present state of the art.Abstract:
We propose a methodology for recognizing actions at a distance by watching the human poses and deriving descriptors that capture the motion patterns of the poses. Human poses often carry a strong visual sense (intended meaning) which describes the related action unambiguously. But identifying the intended meaning of poses is a challenging task because of their variability and such variations in poses lead to visual sense ambiguity. From a large vocabulary of poses (visual words) we prune out ambiguous poses and extract key poses (or key words) using centrality measure of graph connectivity [1]. Under this framework, finding the key poses for a given sense (i.e., action type) amounts to constructing a graph with poses as vertices and then identifying the most "important" vertices in the graph (following centrality theory). The results on four standard activity recognition datasets show the efficacy of our approach when compared to the present state of the art.read more
Citations
More filters
Pattern Recognition and Machine Learning
TL;DR: Probability distributions of linear models for regression and classification are given in this article, along with a discussion of combining models and combining models in the context of machine learning and classification.
Journal ArticleDOI
Selecting Key Poses on Manifold for Pairwise Action Recognition
TL;DR: A novel approach for key poses selection is proposed, which models the descriptor space utilizing a manifold learning technique to recover the geometric structure of the descriptors on a lower dimensional manifold and develops a PageRank-based centrality measure.
Journal ArticleDOI
Recognizing Human Action at a Distance in Video by Key Poses
TL;DR: A graph theoretic technique for recognizing human actions at a distance in a video by modeling the visual senses associated with poses and introduces a “meaningful” threshold on centrality measure that selects key poses for each action type.
Proceedings ArticleDOI
Recognizing interaction between human performers using 'key pose doublet'
TL;DR: A graph theoretic approach for recognizing interactions between two human performers present in a video clip and applies the same centrality measure on all possible combinations of the key poses of the two performers to select the set of 'key pose doublets' that best represent the corresponding action.
Journal ArticleDOI
Region-based Mixture Models for human action recognition in low-resolution videos
TL;DR: The Layered Elastic Motion Tracking (LEMT) method is adopted, a hybrid feature representation is presented to integrate both of the shape and motion features, and a Region-based Mixture Model (RMM) is proposed to be utilized for action classification.
References
More filters
Book
In the Wild
TL;DR: This is a collection of fun, riddle-like poems about naturally camouflaging animals and insects such as the coyote, gray tree frog, fawn, and even the weasel whose camouflage helps them to either escape predators or attack prey.
Journal ArticleDOI
Human Action Recognition by Semilatent Topic Models
Yang Wang,Greg Mori +1 more
TL;DR: Two new models for human action recognition from video sequences using topic models differ from previous latent topic models for visual recognition in two major aspects: first of all, the latent topics in the models directly correspond to class labels; second, some of the latent variables in previous topic models become observed in this case.
Journal ArticleDOI
An Experimental Study of Graph Connectivity for Unsupervised Word Sense Disambiguation
Roberto Navigli,Mirella Lapata +1 more
TL;DR: This paper introduces a graph-based WSD algorithm which has few parameters and does not require sense-annotated data for training, and investigates several measures of graph connectivity with the aim of identifying those best suited for WSD.
Proceedings ArticleDOI
Notice of Violation of IEEE Publication Principles The Anatomy of a Large-Scale Hyper Textual Web Search Engine
TL;DR: Google as mentioned in this paper is a prototype of a large-scale search engine which makes heavy use of the structure present in hypertext and is designed to crawl and index the Web efficiently and produce much more satisfying search results than existing systems.
Journal ArticleDOI
Tracking and recognizing actions of multiple hockey players using the boosted particle filter
TL;DR: A system that can automatically track multiple hockey players and simultaneously recognize their actions given a single broadcast video sequence, where detection is complicated by a panning, tilting, and zooming camera is presented.