A Study of Athlete Pose Estimation Techniques in Sports Game Videos Combining Multiresidual Module Convolutional Neural Networks

In this paper, we propose a multiresidual module convolutional neural network-based method for athlete pose estimation in sports game videos. The network firstly designs an improved residual module based on the traditional residual module. Firstly, a large perceptual field residual module is designed to learn the correlation between the athlete components in the sports game video within a large perceptual field. A multiscale residual module is designed in the paper to better solve the inaccuracy of the pose estimation due to the problem of scale change of the athlete components in the sports game video. Secondly, these three residual modules are used as the building blocks of the convolutional neural network. When the resolution is high, the large perceptual field residual module and the multiscale residual module are used to capture information in a larger range as well as at each scale, and when the resolution is low, only the improved residual module is used. Finally, four multiresidual module convolutional neural networks are used to form the final multiresidual module stacked convolutional neural network. The neural network model proposed in this paper achieves high accuracy of 89.5% and 88.2% on the upper arm and lower arm, respectively, so the method in this paper reduces the influence of occlusion on the athlete’s posture estimation to a certain extent. Through the experiments, it can be seen that the proposed multiresidual module stacked convolutional neural network-based method for athlete pose estimation in sports game videos further improves the accuracy of athlete pose estimation in sports game videos.

Research on the Identification and Evaluation of Aerobics Movements Based on Deep Learning

A deep learning approach is used in this study to provide insight into aerobics movement recognition, and the model is used for aerobics movement recognition. The model complexity is significantly reduced, while the multi-scale features of the target at the fine-grained level are extracted, significantly improving the characterization of the target, by embedding lightweight multi-scale convolution modules in 3D convolutional residual networks to increase the local perceptual field range in each layer of the network. Finally, using the channel attention mechanism, the key features are extracted from the multi-scale features. To create a dual-speed frame rate detection model, the fast-slow combination idea is fused into a 3D convolutional network. To obtain spatial semantic information and motion information in the video, the model uses different frame rates, and the two-channel information is fused with features using lateral concatenation. Following the acquisition of all features, the features are fed into a temporal detection network to identify temporal actions and to design a behavior recognition system for the network model to demonstrate the network model's applicability. The average scores of students in the experimental group were significantly higher than those in the control group in seven areas: set accuracy, movement amplitude, movement strength, body coordination, coordination of movement and music, movement expression, and aesthetics; the average scores of movement proficiency and body control in the experimental group were also significantly higher than those in the control group, but the differences were not significant. The differences between the eight indicators in the experimental group were not significant when compared to those in the preexperimental group, indicating that intensive rhythm training for students improves secondary school students' comprehension, proficiency, and presentation of aerobics sets.

Listening to Yourself Listening: The Metaperceptual Approach to Sound Art

<p>This thesis presents a framework for the creation and analysis of metaperceptual sound artworks. Metaperceptual is a term coined herein to describe a range of works that use the perception of the audience as their artistic materials. They provoke their audiences to direct their attention back upon themselves, inviting audiences to observe the nature of their perception and the subjectivity of their experience. A core focus of many contemporary works is the experience of the audience. These works act as ‘experience shapers’, guiding the audience through their materials and creating environments in which the audience can explore on their own terms. Metaperceptual works share this focus by drawing the audience’s attention back upon themselves, provoking them to attend to the subjectivity of their own experience. These works reveal facets of our perception that constantly mediate our experience, yet often go overlooked and unexplored. The framework presents a systematic ordering of different approaches to creating metaperceptual works. Three main categories of works are identified: Deprivation, Perceptual Translation, and Perceptual Hacking. Deprivation works involve the removal, reduction, or denial of the audience’s perceptual field. They intervene in the audience’s everyday modes of interaction by silencing the din of the world, revealing the facets of experience that often go unnoticed or are masked from our awareness. Perceptual Translation works directly interface with the audience’s perceptual apparatus by shifting, extending, and rearranging its orientation and organisation. These works offer the allure of experiencing what it is like to be someone or something else. By allowing us to experience the world through an altered lens, these works give us a new perspective on ourselves and the ways in which our perceptual apparatus mediates our experience. Lastly, Perceptual Hacking works involves a rich variety of perceptual oddities and artefacts. These works creatively misuse facets of the audience’s perceptual apparatus and perceptual processes, and, in doing so, reveal that our perception is not a neutral objective lens through which to perceive the world. Metaperceptual works employ a diversity of materials and techniques, and traverse a variety of media and styles. While these themes have most extensively been explored in the visual arts, their potential for sonic exploration is a key concern subject of this research. The framework maps the artistic terrain of metaperceptual approaches, and speculates on the potential for new metaperceptual works. To this end, a portfolio of new metaperceptual sound artworks is presented. These works test the metaperceptual framework, enacting the artistic avenues identified during its development. The works span a range of the approaches identified in the metaperceptual framework, and are manifestations of the framework as a creative tool.</p>

Listening to Yourself Listening: The Metaperceptual Approach to Sound Art

<p>This thesis presents a framework for the creation and analysis of metaperceptual sound artworks. Metaperceptual is a term coined herein to describe a range of works that use the perception of the audience as their artistic materials. They provoke their audiences to direct their attention back upon themselves, inviting audiences to observe the nature of their perception and the subjectivity of their experience. A core focus of many contemporary works is the experience of the audience. These works act as ‘experience shapers’, guiding the audience through their materials and creating environments in which the audience can explore on their own terms. Metaperceptual works share this focus by drawing the audience’s attention back upon themselves, provoking them to attend to the subjectivity of their own experience. These works reveal facets of our perception that constantly mediate our experience, yet often go overlooked and unexplored. The framework presents a systematic ordering of different approaches to creating metaperceptual works. Three main categories of works are identified: Deprivation, Perceptual Translation, and Perceptual Hacking. Deprivation works involve the removal, reduction, or denial of the audience’s perceptual field. They intervene in the audience’s everyday modes of interaction by silencing the din of the world, revealing the facets of experience that often go unnoticed or are masked from our awareness. Perceptual Translation works directly interface with the audience’s perceptual apparatus by shifting, extending, and rearranging its orientation and organisation. These works offer the allure of experiencing what it is like to be someone or something else. By allowing us to experience the world through an altered lens, these works give us a new perspective on ourselves and the ways in which our perceptual apparatus mediates our experience. Lastly, Perceptual Hacking works involves a rich variety of perceptual oddities and artefacts. These works creatively misuse facets of the audience’s perceptual apparatus and perceptual processes, and, in doing so, reveal that our perception is not a neutral objective lens through which to perceive the world. Metaperceptual works employ a diversity of materials and techniques, and traverse a variety of media and styles. While these themes have most extensively been explored in the visual arts, their potential for sonic exploration is a key concern subject of this research. The framework maps the artistic terrain of metaperceptual approaches, and speculates on the potential for new metaperceptual works. To this end, a portfolio of new metaperceptual sound artworks is presented. These works test the metaperceptual framework, enacting the artistic avenues identified during its development. The works span a range of the approaches identified in the metaperceptual framework, and are manifestations of the framework as a creative tool.</p>

Aircraft Detection for Remote Sensing Images Based on Deep Convolutional Neural Networks

Aircraft detection for remote sensing images, as one of the fields of computer vision, is one of the significant tasks of image processing based on deep learning. Recently, many high-performance algorithms for aircraft detection have been developed and applied in different scenarios. However, the proposed algorithms still have a series of problems; for instance, the algorithms will miss some small-scale aircrafts when applied to the remote sensing image. There are two main reasons for the problem; one reason is that the aircrafts in the remote sensing image are usually small in size, leading to detecting difficulty. The other reason is that the background of the remote sensing image is usually complex, so the algorithms applied to the scenario are easy to be affected by the background. To address the problem of small size, this paper proposes the Multiscale Detection Network (MSDN) which introduces a multiscale detection architecture to detect small-scale aircrafts. With the intention to resist the background noise, this paper proposes the Deeper and Wider Module (DAWM) which increases the perceptual field of the network to alleviate the affection. Besides, to address the two problems simultaneously, this paper introduces the DAWM into the MSDN and names the novel network structure as Multiscale Refined Detection Network (MSRDN). The experimental results show that the MSRDN method has detected the small-scale aircrafts that other algorithms missed and the performance indicators have higher performance than other algorithms.

Getting to What Matters: A Model of Perceptual Guidance

This article outlines a model of perceptual guidance that aims at giving a child with congenital deafblindness perceptual access to the world, and in particular to the social world. It argues that we can closely interact with, and partially direct, a child’s exploration without instructing the child into culturally similar ways of exploring. Perceptual guidance has two facets. The first is a bodily dimension where child and partner interact so that they create a joint bodily orientation to the world. The second is that partner and child show each other ways of organizing their overlapping perceptual field with arms and hands. This showing bears close resemblance to how we judge and discuss aesthetic matters. As in aesthetics, there is not a given correct procedure for exploring and judging, but an effort at creating community through showing each other how we experience the world. This gives the child access to the social world without purporting that this is the only correct way of exploring. The article ends with two practice examples of perceptual guidance, which additionally shows two ways of spatially organizing the perceptual field.

Aspects of the relationship between the processing of stimuli in the peripheral perceptual field and in the perceptual central field

As humans have limited information processing abilities and rely on three fallible mental functions: perception, attention and memory, the driving error is easy to appear. The purpose of this paper is to highlight the male/female differences in processing the perceptive information from the external stimuli in the peripheral visual field and to demonstrate that the mean of the estimate errors in evaluating the speed and distances in the central visual perceptual field is in inverse ratio to the reaction time value at the visual stimuli from the peripheral driving tasks simulation. Between the variables number of wrong reactions and number of omissions there has been obtained a relatively high negative correlation (r=-0.728, p<0.001). The result has a strong implication in visual stimuli processing during driving tasks.

Cross-cultural differences in visual perception

According to recent cross-cultural studies there exist culturally based differences between visual perception and the related cognitive processes (attention, memory). According to current research, East Asians and Westerners percieve and think about the world in very different ways. Westerners are inclined to attend to some focal object (a salient object within a perception field that is relatively big in size, fast moving, colourful) focusing on and analyzing its attributes. East Asians on the other hand are more likely to attend to a broad perceptual field, noticing relationships and changes. In this paper we want to describe the recent findings in the field and propose some directions for future research.