COWO: towards real-time spatiotemporal action localization in videos

Purpose The purpose of this paper is to provide a fast and accurate network for spatiotemporal action localization in videos. It detects human actions both in time and space simultaneously in real-time, which is applicable in real-world scenarios such as safety monitoring and collaborative assembly. Design/methodology/approach This paper design an end-to-end deep learning network called collaborator only watch once (COWO). COWO recognizes the ongoing human activities in real-time with enhanced accuracy. COWO inherits from the architecture of you only watch once (YOWO), known to be the best performing network for online action localization to date, but with three major structural modifications: COWO enhances the intraclass compactness and enlarges the interclass separability in the feature level. A new correlation channel fusion and attention mechanism are designed based on the Pearson correlation coefficient. Accordingly, a correction loss function is designed. This function minimizes the same class distance and enhances the intraclass compactness. Use a probabilistic K-means clustering technique for selecting the initial seed points. The idea behind this is that the initial distance between cluster centers should be as considerable as possible. CIOU regression loss function is applied instead of the Smooth L1 loss function to help the model converge stably. Findings COWO outperforms the original YOWO with improvements of frame mAP 3% and 2.1% at a speed of 35.12 fps. Compared with the two-stream, T-CNN, C3D, the improvement is about 5% and 14.5% when applied to J-HMDB-21, UCF101-24 and AGOT data sets. Originality/value COWO extends more flexibility for assembly scenarios as it perceives spatiotemporal human actions in real-time. It contributes to many real-world scenarios such as safety monitoring and collaborative assembly.

Flipping food during grilling tasks, a dataset of utensils kinematics and dynamics, food pose and subject gaze

This paper presents a multivariate dataset of 2866 food flipping movements, performed by 4 chefs and 5 home cooks, with different grilled food and two utensils (spatula and tweezers). The 3D trajectories of strategic points in the utensils were tracked using optoelectronic motion capture. The pinching force of the tweezers, the bending force and torsion torque of the spatula were also recorded, as well as videos and the subject gaze. These data were collected using a custom experimental setup that allowed the execution of flipping movements with freshly cooked food, without having the sensors near the dangerous cooking area. Complementary, the 2D position of food was computed from the videos. The action of flipping food is, indeed, gaining the attention of both researchers and manufacturers of foodservice technology. The reported dataset contains valuable measurements (1) to characterize and model flipping movements as performed by humans, (2) to develop bio-inspired methods to control a cooking robot, or (3) to study new algorithms for human actions recognition.

Intention regulates conflicting desires in human decision making

It is an ancient insight that human actions are driven by desires. This insight inspired the formulation that a rational agent acts to maximize expected utility (MEU), which has been widely used in psychology for modeling theory of mind and in artificial intelligence (AI) for controlling machines’ actions. Yet, it's rather unclear how humans act coherently when their desires are complex and often conflicting with each other. Here we show desires do not directly control human actions. Instead, actions are regulated by an intention — a deliberate mental state that commits to a fixed future rather than taking the expected utilities of many futures evaluated by many desires. Our study reveals four behavioral signatures of human intention by demonstrating how human sequential decision-making deviates from the optimal policy based on MEU in a navigation task: “Disruption resistance” as the persistent pursuit of an original intention despite an unexpected change has made that intention suboptimal; “Ulysses-constraint of freedom” as the proactive constraint of one’s freedom by avoiding a path that could lead to many futures, similar to Ulysses’s self-binding to resist the temptation of the Siren’s song; “Enhanced legibility” as an active demonstration of intention by choosing a path whose destination can be promptly inferred by a third-party observer; “Temporal leap” as committing to a distant future even before reaching the proximal one. Our results showed how the philosophy of intention can lead to discoveries of human decision-making, which can also be empirically compared with AI algorithms. The findings showing that to define a theory of mind, intention should be highlighted as a distinctive mental state in between desires and actions, for quarantining conflicting desires from the execution of actions.

Nalar Politik, Kekuasaan, Dan Etika Jawa Refleksi Konsep Hasta Brata Tatanan Kehidupan Masyarakat Jawa Kontemporer

<p><em>Javanese culture is a noble value order as a form of embodiment of all human actions in overcoming various problems related to life and life, both social, economic, cultural institutions, and even leadership styles. In Javanese political ethics, it is known as the concept of hasta brata which is the essence of the noble values of culture as a form of depicting the ideal leader. The hasta brata teaching is one of the teachings in wayang kulit, its contents are about the eight elements of the nature of bearinga, samirana, candra, solar, ocean, kartika, sky, and dahana, each of which has its own philosophical meaning, namely the teachings of character or ethics. Hasta brata is a political way that prioritizes ethics and social systems created by leaders to provide coolness and peace, eradicate crime, be wise, patient, friendly and gentle, see, understand and live up to all the needs of their people, provide welfare and assistance to people in need. , able to accommodate everything that comes to him, whether pleasant or not, and can provide a lamp for the people.</em></p>

Development of algorithms that simulate the solution of a problem by a person

Some algorithms, which are often based on the use of elements of higher mathematics, possessing high speed and compact coding in algorithmic languages, are poorly mastered by most students. It can be assumed that this is due to the difficulty of presenting the principles of their work in the form of human actions in ordinary situations. Thus, a certain contradiction arises between the way of solving the problem that a person resorts to without using a computer and the way we force our computer to solve this problem. Comparison of the process of explaining algorithms speaks in favor of algorithms imitating human thinking. The discussion of the advantages of the algorithms themselves is beyond the scope of this article and undoubtedly deserves a separate study. If artificial intelligence is created, then its creator or creators will certainly be ranked among the outstanding geniuses in the history of civilization, no matter what algorithms it uses. However, so far there is no one to solve problems for us and create algorithms, so we will use all available means and try to teach this to children.

The Seizure of the Throne by Demetrius I Soter (1 Macc 7:1-4). Theological Interpretation of a Historical Event

The presented biblical material (1 Macc 7:1-4) is one of those texts that describe an event happening far away from the scope of influence exerted by the Maccabean insurgents, yet one which is closely connected with the history of the chosen people. As such, it substantially influences the successive events in the political-religious situation of the Jews. What is particularly worthy of analysis is the historical accuracy of the inspired author in presenting facts as well as the theological conception to which primary importance is given in the book. This way the history of peoples, kingdoms and societies is shown as part of God’s magnificent plans which is implemented by all participants of ongoing scenes. Such a presentation concerns both the main and supporting protagonists. The short passage of 1 Macc 7:1-4 reveals how the hagiographer, who knows the theological conception, consciously accentuates certain parts, chooses appropriate syntax and vocabularyto show God’s action in the presented characters and events. God stands behind the curtain of human actions, yet it is Him who decides about their course.

Novel Machine Learning for Human Actions Classification Using Histogram of Oriented Gradients and Sparse Representation

Recognition of human actions is a trending research topic as it can be used for crucial medical applications like life care and healthcare. In this research, we propose a novel machine learning algorithm for the classification of human actions based on sparse representation theory. In the proposed framework, the input videos are initially partitioned into several temporal segments of a predefined length. From these temporal segments, the key-cuboids are then obtained. These cuboids are obtained based on the locations having maximum variation in orientation. From these regions, key-cuboids are extracted. From the key-cuboids, Histogram of Oriented Gradient (HOG) features are extracted. This new descriptor has the capability to express the dynamic features in the action videos. Using these features, a single shared dictionary is created from the videos belonging to different classes using K-Singular Value Decomposition (K-SVD) algorithm. This dictionary has the combined features of all the action classes. This shared dictionary is generated during the training phase. During the testing phase, the features belonging to a test class is classified using a novel Sparse Representation Modeling based Action Recognition (SRMAR) Algorithm using Orthogonal Matching Pursuit (OMP) and the shared dictionary. The proposed framework was evaluated using popular benchmark action recognition datasets like KTH dataset, Olympic dataset and the Hollywood dataset. The results obtained using these datasets were represented in the form of a confusion matrix. Evaluation was performed using metrics like overall classification accuracy, specificity, precision, recall and F-score that were obtained from the confusion matrix. This system achieved a high specificity of about 99.52%, 99.16% and 96.15% for the KTH dataset, Olympic dataset and the Hollywood datasets, respectively. Similarly, the proposed framework attained very good precision of 97.64%, 90.46% and 73.39% for the KTH dataset, Olympic dataset and the Hollywood datasets, respectively. Also, the average value of recall achieved was 97.58%, 90.86% and 74.09% for the KTH dataset, Olympic dataset and the Hollywood datasets, respectively. It was also observed that the proposed machine learning algorithm achieved outstanding results compared to the existing state-of-the-art human action recognition frameworks in the literature.

What the Ground Says…

Ground, as a body incised by natural and human actions (European Landscape Convention), carries “stories”, going beyond quantitative values. As in a text, it holds the keys to understand what it covers or hides. In its thickness, it shelters “implicit projects”. Understanding its complexity requires a physical and perceptual commitment, challenging the body in space: dimensions gradually forgotten by Environmental Sciences. As a “threshold” between visible and invisible, Underground-Built-Heritage represents the reverse of the emerged world: hollow space, both generator and mirror of open space (cities, landscapes). The focus is on physical and mental relationships between these two worlds. Past and present relationships emerge, allowing hypotheses to reconstitute collective memories, practices, knowledge, and values, which serve territorial development. The “Three Countries Park” is a place for cross-border experimentation to test how UBH can rebuild common links for fragmented environments. The cavities of a geo-park (planned) and the tangles of underground mining architecture are the fragments of a vocabulary whose meaning communities have to relearn. Built undergrounds will, thus, emerge from common stories that revive the imagination of populations who have lost all notion of belonging to a place. UBH will become a vector of new territorial coherence linking the physical and mental perceptions of people.

A Data Augmentation Method for Skeleton-Based Action Recognition with Relative Features

In recent years, skeleton-based human action recognition (HAR) approaches using convolutional neural network (CNN) models have made tremendous progress in computer vision applications. However, using relative features to depict human actions, in addition to preventing overfitting when the CNN model is trained on a few samples, is still a challenge. In this paper, a new motion image is introduced to transform spatial-temporal motion information into image-based representations. For each skeleton sequence, three relative features are extracted to describe human actions. The three relative features are consisted of relative coordinates, immediate displacement, and immediate motion orientation. In particular, the relative coordinates introduced in our paper not only depict the spatial relations of human skeleton joints but also provide long-term temporal information. To address the problem of small sample sizes, a data augmentation strategy consisting of three simple but effective data augmentation methods is proposed to expand the training samples. Because the generated color images are small in size, a shallow CNN model is suitable to extract the deep features of the generated motion images. Two small-scale but challenging skeleton datasets were used to evaluate the method, scoring 96.59% and 97.48% on the Florence 3D Actions dataset and UTkinect-Action 3D dataset, respectively. The results show that the proposed method achieved a competitive performance compared with the state-of-the-art methods. Furthermore, the augmentation strategy proposed in this paper effectively solves the overfitting problem and can be widely adopted in skeleton-based action recognition.

Aerobics Movement Decomposition Action Teaching System Based on Intelligent Vision Sensor

With the development of the times, teaching has not only stayed between people, but also gradually developed into the teaching interaction between man and machine. In the past, the teaching form was relatively single and old. Based on the intelligent visual sensor, this paper develops an auxiliary teaching system for the decomposition of aerobics action and reasonably uses the Internet and algorithms to catalog a series of aerobics action systems into the system. The DTW dynamic motion matching algorithm of the system will recognize human actions more accurately. The system will feed back human actions to the system in real time based on human feature recognition. Then, after comparison, the system will display the standard posture of this action and the aerobics posture in the next step. Therefore, this system develops teaching not only in class, but everywhere. The system not only improves the teaching quality of aerobics, but also strengthens the physical quality of teenagers. It has a new understanding of the standardization of aerobics teaching. After the function of the system is complete, the system will be distributed to aerobics learners. In many feedback information, the average use satisfaction has reached about 80%, which is a good performance index for the performance of the system itself.