Diss. Stockholm : Handelshögsk., 2001.

<p dir="ltr">Human action recognition stands as a cornerstone in the domain of computer vision, with its utility spanning across emergency response, sign language interpretation, and the burgeoning fields of augmented and virtual reality. The transition from conventional video-based recognition to skeleton-based methodologies has been a transformative shift, offering a robust alternative less susceptible to environmental noise and more focused on the dynamics of human movement.</p><p dir="ltr">This body of work encapsulates the evolution of action recognition, emphasizing the pivotal role of Graph Convolution Network (GCN) based approaches, particularly through the innovative InfoGCN framework. InfoGCN has set a new precedent in the field by introducing an information bottleneck-based learning objective, a self-attention graph convolution module, and a multi-modal representation of the human skeleton. These advancements have collectively elevated the accuracy and efficiency of action recognition systems.</p><p dir="ltr">Addressing the prevalent challenge of occlusions, particularly in single-camera setups, the Pose Relation Transformer (PORT) framework has been introduced. Inspired by the principles of Masked Language Modeling in natural language processing, PORT refines the detection of occluded joints, thereby enhancing the reliability of pose estimation under visually obstructive conditions.</p><p dir="ltr">Building upon the foundations laid by InfoGCN, the Skeleton ODE framework has been developed for online action recognition, enabling real-time inference without the need for complete action observation. By integrating Neural Ordinary Differential Equations, Skeleton ODE facilitates the prediction of future movements, thus reducing latency and paving the way for real-time applications.</p><p dir="ltr">The implications of this research are vast, indicating a future where real-time, efficient, and accurate human action recognition systems could significantly impact various sectors, including healthcare, autonomous vehicles, and interactive technologies. Future research directions point towards the integration of multi-modal data, the application of transfer learning for enhanced generalization, the optimization of models for edge computing, and the ethical deployment of action recognition technologies. The potential for these systems to contribute to healthcare, particularly in patient monitoring and disease detection, underscores the need for continued interdisciplinary collaboration and innovation.</p>

In this thesis we study deep learning architectures for the problem of human action recognition in image sequences, i.e. the problem of automatically recognizing what people are doing in a given video. As unlabeled video data is easily accessible these days, we first explore models that can learn meaningful representations of sequences without actually having to know what is happening in the sequences at hand. More specifically, we first explore the convolutional restricted Boltzmann machine (RBM) and show how a stack of convolutional RBMs can be used to learn and extract features from sequences in an unsupervised way. Using the classical Fisher vector pipeline to encode the extracted features we apply them on the task of action classification. We move on to feature extraction using larger, deep convolutional neural networks and propose a novel architecture which expresses the processing steps of the classical Fisher vector pipeline as network layers. By contrast to other methods where these steps are performed consecutively and the corresponding parameters are learned in an unsupervised manner, defining them as a single neural network allows us to refine the whole model discriminatively in an end to end fashion. We show that our method achieves significant improvements in comparison to the classical Fisher vector extraction chain and results in a comparable performance to other convolutional networks, while largely reducing the number of required trainable parameters. Finally, we explore how the proposed architecture can be modified into a hybrid network that combines the benefits of both unsupervised and supervised training methods, resulting in a model that learns a semi-supervised Fisher vector descriptor of the input data. We evaluate the proposed model at image classification and action recognition problems and show how the model's classification performance improves as the amount of unlabeled data increases during training.

Human-Computer Interaction (HCI) in tradition is narrow defined the communication of information between human and machines. Because the limited of the HCI's speed and the natural level, it needs to use the medium form such as symbol instructions and buttons to express the intent of human. In recent year, the trend of HCI development will be focused on human, with directly computing, determining, and displaying technologies progress, and constantly innovation. Somatosensory equipment not only breaks through the limit of HCI but also the mode of interaction of traditional equipment. Somatosensory equipment can retrieve images through the infrared projector or visible camera, capture the human motion and action, and increase its interaction for natural and intuition. But unfortunately, most of systems are limited to a unique application for special areas, and only detected specific sequences of actions. Once changing the interaction of applications then users have to rewrite the action sequences recognition program to satisfy the somatosensory demands. System cannot be defined human action sequences flexible according the applications request of users, the production process is complex and the scope of application is narrow. This thesis presents an Authoring Tool of Vision-based Somatosensory Action (ATVISA) to improve the drawback. Users can define the human action sequences by the graphical interface, customize the visual detection quickly and recognize correspond to the Somatosensory Action. Till the Somatosensory equipment detects the defined action sequences, triggering the correspond event and dealing with the event request. This thesis employs ATVISA applied to the action sequences and three rehabilitation projects, that with the flexibility and diversification. Users also can compile human action sequences with professional expertise to application to area of education, game, rehabilitation, and so on.

The purpose of the study is to increase understanding of how political decisions are implemented in public organizations. The focus of the study is on the impact of human action on organizational structures. The empirical material consists of interviews with politicians and civil servants working in the public organization. The material is analyzed primarily using Ahrne's theory of organizational centenaries. The theories of disconnection and inertia are also used in the analysis. The study's findings show that the human action is important in an implementation process. Crucial interpretations, based on human actions, are made at politicians and civil servants level. This results in people's own interests having a decisive role in the implementation process. The political structure gives the officials space to interpret political decisions, which leads to an interest-driven way of working. With sociological knowledge, it can be shown that man has a need for human interpretation because we are social beings. The present study shows that we can´t ignore the human action of organizations when the organization is made up of people.

The volitional theory of action has recently been assailed as an outmoded account of human action, while attempts have been made to preserve the theory on grounds which side-step the traditional difficulties. Both approaches to the theory have left it without a coherent expression. This thesis is an attempt to give a coherent theoretical foundation to the theory and to effect its critical evaluation. Preceding a discussion of the theory is a historical appreciation of its tradition, and this is used as a backdrop for viewing two aspects of the theory which serve today as its paradigms. The one is an analysis of human action in terms of a volition which is considered as something which an agent performs, and the other is an analysis of human action in terms of a volition connected causally to an item of behavior, The incompatibility of these aspects is indicated, and an attempt is made to locate them within a wider theoretical structure. This is done by distinguishing between atomic actions and instrumental actions and by attributing to the theory two definitions of an individual human action which preserve these paradigms and which account for both sorts of actions. The final segment of the thesis is concerned with a critical dismissal of the theory. The stock arguments against the theory are first defeated, end it is then argued that one aspect of the theory fails to account for forbearances and that the other aspect does not provide an adequate account of atomic actions. / Thesis / Master of Arts (MA)

No description available.

In this dissertation, we address the problem of understanding human activities in videos by developing a two-pronged approach: coarse level modeling of scene activities and fine level modeling of individual activities. At the coarse level, where the resolution of the video is low, we rely on person tracks. At the fine level, richer features are available to identify different parts of the human body, therefore we rely on the body joint tracks. There are three main goals of this dissertation: (1) identify unusual activities at the coarse level, (2) recognize different activities at the fine level, and (3) predict the behavior for synthesizing and tracking activities at the fine level. The first goal is addressed by modeling activities at the coarse level through two novel and complementing approaches. The first approach learns the behavior of individuals by capturing the patterns of motion and size of objects in a compact model. Probability density function (pdf) at each pixel is modeled as a multivariate Gaussian Mixture Model (GMM), which is learnt using unsupervised expectation maximization (EM). In contrast, the second approach learns the interaction of object pairs concurrently present in the scene. This can be useful in detecting more complex activities than those modeled by the first approach. We use a 14-dimensional Kernel Density Estimation (KDE) that captures motion and size of concurrently tracked objects. The proposed models have been successfully used to automatically detect activities like unusual person drop-off and pickup, jaywalking, etc. The second and third goals of modeling human activities at the fine level are addressed by employing concepts from theory of chaos and non-linear dynamical systems. We show that the proposed model is useful for recognition and prediction of the underlying dynamics of human activities. We treat the trajectories of human body joints as the observed time series generated from an underlying dynamical system. The observed data is used to reconstruct a phase (or state) space of appropriate dimension by employing the delay-embedding technique. This transformation is performed without assuming an exact model of the underlying dynamics and provides a characteristic representation that will prove to be vital for recognition and prediction tasks. For recognition, properties of phase space are captured in terms of dynamical and metric invariants, which include the Lyapunov exponent, correlation integral, and correlation dimension. A composite feature vector containing these invariants represents the action and will be used for classification. For prediction, kernel regression is used in the phase space to compute predictions with a specified initial condition. This approach has the advantage of modeling dynamics without making any assumptions about the exact form (polynomial, radial basis, etc.) of the mapping function. We demonstrate the utility of these predictions for human activity synthesis and tracking.

It is proven that locations of internal body joints are sufficient visual cues to characterize human motion. In this dissertation I propose that locations of human extremities including heads, hands and feet provide powerful approximation to internal body motion. I propose detection of precise extremities from contours obtained from image segmentation or contour tracking. Junctions of medial axis of contours are selected as stars. Contour points with a local maximum distance to various stars are chosen as candidate extremities. All the candidates are filtered by cues including proximity to other candidates, visibility to stars and robustness to noise smoothing parameters. I present my applications of using precise extremities for fast human action detection and recognition. Environment specific features are built from precise extremities and feed into a block based Hidden Markov Model to decode the fence climbing action from continuous videos. Precise extremities are grouped into stable contacts if the same extremity does not move for a certain duration. Such stable contacts are utilized to decompose a long continuous video into shorter pieces. Each piece is associated with certain motion features to form primitive motion units. In this way the sequence is abstracted into more meaningful segments and a searching strategy is used to detect the fence climbing action. Moreover, I propose the histogram of extremities as a general posture descriptor. It is tested in a Hidden Markov Model based framework for action recognition. I further propose detection of probable extremities from raw images without any segmentation. Modeling the extremity as an image patch instead of a single point on the contour helps overcome the segmentation difficulty and increase the detection robustness. I represent the extremity patches with Histograms of Oriented Gradients. The detection is achieved by window based image scanning. In order to reduce computation load, I adopt the integral histograms technique without sacrificing accuracy. The result is a probability map where each pixel denotes probability of the patch forming the specific class of extremities. With a probable extremity map, I propose the histogram of probable extremities as another general posture descriptor. It is tested on several data sets and the results are compared with that of precise extremities to show the superiority of probable extremities. / text

This study suggests that tragedy sees human action as synonymous with language and that it uses a method similar to that of a hermeneutic phenomenology to portray man as experiencing spirituality in a confrontation with expression. This confrontation takes the form of a pattern that leads to a revelation that all human action springs from the spirit. Word as action is thus placed into a spiritual context, containing in itself the key to the divine significance of the human experience. As a cultural manifestation, this pattern exists not only in literary tragedy, but also in the Hebrew Scriptures as narratives and poetry. This study examines this tragic pattern in Genesis, the Book of Job, Oedipus, and King Lear.