scholarly journals A Video Descriptor Using Orientation Tensors and Shape-Based Trajectory Clustering

2016 ◽  
Vol 16 (04) ◽  
pp. 1650017
Author(s):  
Felipe Andrade Caetano ◽  
Marcelo Bernardes Vieira ◽  
Rodrigo Luis de Souza da Silva
Keyword(s):  
Human Action Recognition ◽  
Relevant Information ◽  
Human Action ◽  
The Self ◽  
Gradient Field ◽  
Trajectory Clustering ◽  
Motion Patterns ◽  
Orientation Tensors ◽  
The Relationship ◽  
Video Descriptor

Dense trajectories have been shown as a very promising method in the human action recognition field. In this paper, we propose a new kind of video descriptor, generated from the relationship between the trajectory’s optical flow with the gradient field in its neighborhood. Orientation tensors are used to accumulate relevant information over the video, representing the tendency of direction in the descriptor space for that kind of movement. Furthermore, a method to cluster trajectories using their shape is proposed. This method allows us to accumulate different motion patterns in different tensors and easier distinguish trajectories that are created by real movements from the trajectories created by the camera’s movement. The proposed method is capable to achieve the best known recognition rates for methods based on the self-descriptor constraint in popular datasets — Hollywood2 (up to 46%) and KTH (up to 94%).

FASTensor: A tensor framework for spatiotemporal description

2019 ◽  
Author(s):  
Virgı́nia F. Mota ◽  
Jefersson A. dos Santos ◽  
Arnaldo De A. Araújo
Keyword(s):  
Cancer Cell ◽  
Data Augmentation ◽  
Human Action Recognition ◽  
Human Action ◽  
Research Field ◽  
Small Data ◽  
Learning Tools ◽  
Melanoma Cancer ◽  
Orientation Tensors ◽  
Spatiotemporal Representation

Spatiotemporal description is a research field with applications in various areas such as video indexing, surveillance, human-computer interfaces, among others. Big Data problems in large databases are now being treated with Deep Learning tools, however we still have room for improvement in spatiotemporal handcraft description. Moreover, we still have problems that involve small data in which data augmentation and other techniques are not valid. The main contribution of this Ph.D. Thesis 1 is the development of a framework for spatiotemporal representation using orientation tensors enabling dimension reduction and invariance. This is a multipurpose framework called Features As Spatiotemporal Tensors (FASTensor). We evaluate this framework in three different applications: Human Action recognition, Video Pornography classification and Cancer Cell classification. The latter one is also a contribution of this work, since we introduce a new dataset called Melanoma Cancer Cell dataset (MCC). It is a small data that cannot be artificially augmented due the difficulty of extraction and the nature of motion. The results were competitive, while also being fast and simple to implement. Finally, our results in the MCC dataset can be used in other cancer cell treatment analysis.

scholarly journals Interoception modulates the self-prioritization effect

2021 ◽  
Author(s):  
Tatsuru Honda ◽  
Takashi Nakao
Keyword(s):  
Causal Relationship ◽  
Cardiac Cycle ◽  
Relevant Information ◽  
Neutral Stimulus ◽  
The Body ◽  
The Self ◽  
Matching Task ◽  
Study Results ◽  
Interoceptive Accuracy ◽  
The Relationship

Self-relevant information is processed faster and more accurately than non-self-relevant information. Such a bias is developed even for newly associated information with the self, also known as the self-prioritization effect (SPE). Interoception, which refers to the overall processing of information from inside the body, is crucial for self-relevant processing; however, little is known about its role in SPE. In this study, we investigated the relationship between the magnitude of SPE and interoceptive accuracy (IAc), defined as an individual’s ability to accurately perceive one’s own interoceptive state. Additionally, to explore the causal relationship, we measured SPE by presenting self- or non-self-relevant stimuli based on the participant's cardiac cycle in the shape-label matching task. We demonstrated that IAc was negatively correlated with the magnitude of SPE in terms of discrimination of the relevance of the stimuli. In addition, a correlation was observed only when the stimuli were presented during cardiac systole. Furthermore, IAc was negatively correlated with the processing of self-relevant stimuli but not with non-self-relevant stimuli. Our findings suggest that individuals with high IAc were less able to discriminate whether an external neutral stimulus was self-relevant when the stimulus was presented at systole. Our results may reflect the tendency to recognize the self-relevance of stimuli based on interoception in individuals with high IAc. Since the present study used geometric shapes, which are not easily recognized as stimuli that can induce changes in the interoception, individuals with high IAc assigned less self-relevance to the stimuli, resulting in weaker SPE. From this perspective, we further discussed the conditions that lead to stronger SPE in individuals with high IAc, in contrast to the present study results.

Skeleton-based STIP feature and discriminant sparse coding for human action recognition

2020 ◽  
Vol 9 (1) ◽  
pp. 43-61
Author(s):  
Ushapreethi P ◽  
Lakshmi Priya G G
Keyword(s):  
Action Recognition ◽  
Human Action Recognition ◽  
Human Action ◽  
The Self ◽  
Feature Descriptor ◽  
Interest Points ◽  
Linear Action ◽  
Action Classification ◽  
Content Type ◽  
Key Steps

PurposeTo find a successful human action recognition system (HAR) for the unmanned environments.Design/methodology/approachThis paper describes the key technology of an efficient HAR system. In this paper, the advancements for three key steps of the HAR system are presented to improve the accuracy of the existing HAR systems. The key steps are feature extraction, feature descriptor and action classification, which are implemented and analyzed. The usage of the implemented HAR system in the self-driving car is summarized. Finally, the results of the HAR system and other existing action recognition systems are compared.FindingsThis paper exhibits the proposed modification and improvements in the HAR system, namely the skeleton-based spatiotemporal interest points (STIP) feature and the improved discriminative sparse descriptor for the identified feature and the linear action classification.Research limitations/implicationsThe experiments are carried out on captured benchmark data sets and need to be analyzed in a real-time environment.Practical implicationsThe middleware support between the proposed HAR system and the self-driven car system provides several other challenging opportunities in research.Social implicationsThe authors’ work provides the way to go a step ahead in machine vision especially in self-driving cars.Originality/valueThe method for extracting the new feature and constructing an improved discriminative sparse feature descriptor has been introduced.

Combining Orientation Tensors for Human Action Recognition

2013 ◽  
Author(s):  
Virginia F. Mota ◽  
Jessica I.C. Souza ◽  
Arnaldo de A. Araujo ◽  
Marcelo Bernardes Vieira
Keyword(s):  
Action Recognition ◽  
Human Action Recognition ◽  
Human Action ◽  
Orientation Tensors

scholarly journals Classifying Normal and Abnormal Status Based on Video Recordings of Epileptic Patients

2014 ◽  
Vol 2014 ◽  
pp. 1-6 ◽  
Author(s):  
Jing Li ◽  
Xiantong Zhen ◽  
Xianzeng Liu ◽  
Gaoxiang Ouyang
Keyword(s):  
Human Action Recognition ◽  
Human Action ◽  
Human Robot Interaction ◽  
Support Vector ◽  
Motion Patterns ◽  
Assistive Robots ◽  
Socially Assistive Robots ◽  
Video Recordings ◽  
Epileptic Patients ◽  
Patients With Epilepsy

Based on video recordings of the movement of the patients with epilepsy, this paper proposed a human action recognition scheme to detect distinct motion patterns and to distinguish the normal status from the abnormal status of epileptic patients. The scheme first extracts local features and holistic features, which are complementary to each other. Afterwards, a support vector machine is applied to classification. Based on the experimental results, this scheme obtains a satisfactory classification result and provides a fundamental analysis towards the human-robot interaction with socially assistive robots in caring the patients with epilepsy (or other patients with brain disorders) in order to protect them from injury.

From Container to Claustrum: Projective Identification in Couples

2014 ◽  
Vol 4 (2) ◽  
Author(s):  
Tamara Feldman
Keyword(s):  
Psychological Health ◽  
Projective Identification ◽  
The Self ◽  
The Other ◽  
Intimate Partners ◽  
And Control ◽  
The Relationship ◽  
As If

This paper is a contribution to the growing literature on the role of projective identification in understanding couples' dynamics. Projective identification as a defence is well suited to couples, as intimate partners provide an ideal location to deposit unwanted parts of the self. This paper illustrates how projective identification functions differently depending on the psychological health of the couple. It elucidates how healthier couples use projective identification more as a form of communication, whereas disturbed couples are inclined to employ it to invade and control the other, as captured by Meltzer's concept of "intrusive identification". These different uses of projective identification affect couples' capacities to provide what Bion called "containment". In disturbed couples, partners serve as what Meltzer termed "claustrums" whereby projections are not contained, but imprisoned or entombed in the other. Applying the concept of claustrum helps illuminate common feelings these couples express, such as feeling suffocated, stifled, trapped, held hostage, or feeling as if the relationship is killing them. Finally, this paper presents treatment challenges in working with more disturbed couples.

The Relationship between Seeker and Spiritual Guide as portrayed in contemporary Western Sufi Autobiographies

2011 ◽  
Vol 5 (2) ◽  
pp. 297-332
Author(s):  
Kate Zebiri
Keyword(s):  
Life Writing ◽  
New Age ◽  
The Self ◽  
Individual Autonomy ◽  
Religious Authority ◽  
The Face ◽  
The Relationship ◽  
Insight Into ◽  
Continuity And Discontinuity

This article aims to explore the Shaykh-mur?d (disciple) or teacher-pupil relationship as portrayed in Western Sufi life writing in recent decades, observing elements of continuity and discontinuity with classical Sufism. Additionally, it traces the influence on the texts of certain developments in religiosity in contemporary Western societies, especially New Age understandings of religious authority. Studying these works will provide an insight into the diversity of expressions of contemporary Sufism, while shedding light on a phenomenon which seems to fly in the face of contemporary social and religious trends which deemphasize external authority and promote the authority of the self or individual autonomy.

Sign in / Sign up

Export Citation Format

Share Document