Human interaction recognition method based on parallel multi-feature fusion network

Human activity recognition is a key technology in intelligent video surveillance and an important research direction in the field of computer vision. However, the complexity of human interaction features and the differences in motion characteristics at different time periods have always existed. In this paper, a human interaction recognition algorithm based on parallel multi-feature fusion network is proposed. First of all, in view of the different amount of information provided by the different time periods of action, an improved time-phased video down sampling method based on Gaussian model is proposed. Second, the Inception module uses different scale convolution kernels for feature extraction. It can improve network performance and reduce the amount of network parameters at the same time. The ResNet module mitigates degradation problem due to increased depth of neural networks and achieves higher classification accuracy. The amount of information provided in the motion video in different stages of motion time is also different. Therefore, we combine the advantages of the Inception network and ResNet to extract feature information, and then we integrate the extracted features. After the extracted features are merged, the training is continued to realize parallel connection of the multi-feature neural network. In this paper, experiments are carried out on the UT dataset. Compared with the traditional activity recognition algorithm, this method can accomplish the recognition tasks of six kinds of interactive actions in a better way, and its accuracy rate reaches 88.9%.

Scaling Human-Object Interaction Recognition in the Video through Zero-Shot Learning

Recognition of human activities is an essential field in computer vision. The most human activity consists of the interaction between humans and objects. Many successful works have been done on human-object interaction (HOI) recognition and achieved acceptable results in recent years. Still, they are fully supervised and need to train labeled data for all HOIs. Due to the enormous space of human-object interactions, listing and providing the training data for all possible categories is costly and impractical. We propose an approach for scaling human-object interaction recognition in video data through the zero-shot learning technique to solve this problem. Our method recognizes a verb and an object from the video and makes an HOI class. Recognition of the verbs and objects instead of HOIs allows identifying a new combination of verbs and objects. So, a new HOI class can be identified, which is not seen by the recognizer system. We introduce a neural network architecture that can understand and represent the video data. The proposed system learns verbs and objects from available training data at the training phase and can identify the verb-object pairs in a video at test time. So, the system can identify the HOI class with different combinations of objects and verbs. Also, we propose to use lateral information for combining the verbs and the objects to make valid verb-object pairs. It helps to prevent the detection of rare and probably wrong HOIs. The lateral information comes from word embedding techniques. Furthermore, we propose a new feature aggregation method for aggregating extracted high-level features from video frames before feeding them to the classifier. We illustrate that this feature aggregation method is more effective for actions that include multiple subactions. We evaluated our system by recently introduced Charades challengeable dataset, which has lots of HOI categories in videos. We show that our proposed system can detect unseen HOI classes in addition to the acceptable recognition of seen types. Therefore, the number of classes identifiable by the system is greater than the number of classes used for training.

Spiritual Practice & Experience: A Kind of Contemporary Art View Leading to Civilization

As a kind of perceptual sign of human spiritual dynamics and civilization height, “contemporary art” does not pursue the performing “sense of existence” under the spotlight, but leads to civilization and seeks its own “sense of belonging” through the current spiritual practice and exploration of the living noumenon of art — human— to the daily life world. Criticizing and deconstructing the traditional purist view of art, rejecting art for art’s sake, and promoting “art noumenon” to “existence noumenon” — value significance of Karl Popper’s so-called “Three Worlds”, which are mutually dependent and promoting, mutually opposite and complementary, has been historically awakened and highlighted. Among them, “world two (experiencing world)”, which is characterized by human spiritual practice and behavior experience, has the most life significance and artistic value “from culture to civilization”. Define contemporary art from five key points combined with world two: reflecting the daily state of consciousness or mental state of human and society; highlighting the behavior, interaction, recognition of spiritual activities, and the everydayness of the effect on three worlds; an existing way of perceptually mastering the world; a symbol of apperception, personification, and living humanity world; and an artistic and dynamic world of connecting and driving the three worlds. Its fundamental logic is that: experience is cognition, that is, the continuous unity and dynamic unity of expression; it is the highest belonging and value conversion of culture leading to civilization; it is the true art that pursues truth, discovers possibility and highlights human nature.

Self-Interacting Proteins Prediction from PSSM Based on Evolutionary Information

Self-interacting proteins (SIPs) play an influential role in regulating cell structure and function. Thus, it is critically important to identify whether proteins themselves interact with each other. Although there are some existing experimental methods for self-interaction recognition, the limitations of these methods are both expensive and time-consuming. Therefore, it is very necessary to develop an efficient and stable computational method for predicting SIPs. In this study, we develop an effective computational method for predicting SIPs based on rotation forest (RF) classifier, combined with histogram of oriented gradients (HOG) and synthetic minority oversampling technique (SMOTE). When performing SIPs prediction on yeast and human datasets, the proposed method achieves superior accuracies of 97.28% and 89.41%, respectively. In addition, the proposed approach was compared with the state-of-the-art support vector machine (SVM) classifiers and other different methods on the same datasets. The experimental results demonstrate that our method has good robustness and effectiveness and can be regarded as a useful tool for SIPs prediction.

Working memory enhancement during early childhood based on the utilization of interactive gesture game-based learning technique

<p>The use of human computer interaction is considered to be the most culturally and socially meritorious for the learning and playing activities of children. In this paper, a human interaction recognition system (HIRS) that includes gesture game-based learning is investigated for identifying its suitability and applicability in stimulation of working memory and primitive mathematical skills among the children in the early childhood period that ranges from 5 and 8 years. In the proposed human interaction recognition system, the hand gestures are facilitated by the user for the objective of controlling the computer system based on the information extracted from the user gestures.This proposed research was implemented in three phases using a quasi-experimental design that in turn incorporates pre-test and post-test for investigating the behavior of experimental and control group considered from the respondents. In the first phase, the initial evaluation of the learner’s skill is achieved. The second phase used the developed technology in order to identify diversified parameters in different dimensions that contribute towards the assessment of working memory and primitive mathematical capabilities. Finally, the third phase is responsible for actual evaluation. In the phases of evaluation, four working memory tests such as forward Corsi Blocking-Tapping test, backward Corsi Blocking-Tapping test, Forward Digit Span test and backwardDigit Span test was conducted. In addition, the evaluation was also conducted for assessing primitive mathematical skill of children using TEDI-MATH. The results confirmed that Gesture Interactive Game-Based Learning (GIGL) used by the children exhibited a predominant improvement in the working memory and primitive mathematical skills on par with their usual school activities.</p>