The extensive spread of DeepFake images on the internet has emerged as a significant challenge, with applications ranging from harmless entertainment to harmful acts like blackmail, misinformation, and spreading false...
详细信息
Physical exercise affects many facets of life, including mental health, social interaction, physical fitness, and illness prevention, among many others. Therefore, several AI-driven techniques have been developed in t...
详细信息
Physical exercise affects many facets of life, including mental health, social interaction, physical fitness, and illness prevention, among many others. Therefore, several AI-driven techniques have been developed in the literature to recognize human physical activities. However, these techniques fail to adequately learn the temporal and spatial features of the data patterns. Additionally, these techniques are unable to fully comprehend complex activity patterns over different periods, emphasizing the need for enhanced architectures to further increase accuracy by learning spatiotemporal dependencies in the data individually. Therefore, in this work, we develop an attention-enhanced dual-stream network (PAR-Net) for physical activity recognition with the ability to extract both spatial and temporal features simultaneously. The PAR-Net integrates convolutional neural networks (CNNs) and echo state networks (ESNs), followed by a self-attention mechanism for optimal feature selection. The dual-stream feature extraction mechanism enables the PAR-Net to learn spatiotemporal dependencies from actual data. Furthermore, the incorporation of a self-attention mechanism makes a substantial contribution by facilitating targeted attention on significant features, hence enhancing the identification of nuanced activity patterns. The PAR-Net was evaluated on two benchmark physical activity recognition datasets and achieved higher performance by surpassing the baselines comparatively. Additionally, a thorough ablation study was conducted to determine the best optimal model for human physical activity recognition.
Continual Learning (CL) plays a crucial role in enhancing learning performance for both new and previous tasks in continuous data streams, thus contributing to the advancement of cognitive computing. However, CL faces...
详细信息
Continual Learning (CL) plays a crucial role in enhancing learning performance for both new and previous tasks in continuous data streams, thus contributing to the advancement of cognitive computing. However, CL faces a fundamental challenge known as the stability -plasticity quandary. In this research, we present an innovative and effective CL algorithm called Primary Null Space Projection (PNSP) to strike a balance between network plasticity and stability. PNSP consists of three main components. Firstly, it leverages the NSP-LRA algorithm to project the gradient of network parameters from previous tasks into a meticulously designed null space. NSP-LRA harnesses high -dimensional geometric information extracted from the feature covariance matrix through low -rank approximation algorithm to obtain the basis of null space dynamically. This process constructs an innovation null space and ensures the continuous updating of orthonormal bases to accommodate changes in the input data. Secondly, we propose a Consistency -guided Task -specific Feature Learning (CTFL) mechanism to tackle the issue of catastrophic forgetting and facilitate continual learning. CTFL achieves this by aligning feature vectors and maintaining consistent feature learning directions, thereby preventing the loss of previously acquired knowledge. Lastly, we introduce Label Guided Self -Distillation (LGSD), a technique that utilizes true labels to guide the distillation process and incorporates a dynamic temperature mechanism to enhance performance. To evaluate the effectiveness of our proposed method, we conduct experiments on the CIFAR100 and TinyImageNet datasets. The results demonstrate significant improvements over state-of-the-art methods. We have made the implementation code of our approach available for reference.
Full remote scientific operation of the DIII-D National Fusion Facility is now possible through significant advances in the computer science hardware and software infrastructure made over the last decade. Capabilities...
详细信息
Full remote scientific operation of the DIII-D National Fusion Facility is now possible through significant advances in the computer science hardware and software infrastructure made over the last decade. Capabilities around information visualization, data movement, and communication have all been enhanced. The level of capability deployed to remotely operate DIII-D required an infrastructure advancement over what had previously been achieved in the fusion community. The large quantity of real-time data that is automatically displayed on DIII-D's control room screens can now be visualized by remote participants via web-based applications. New audio/video solutions using the VoIP and instant messaging application Discord have been implemented to mimic the dynamic and ad-hoc scientific conversations that are critical in successfully operating an experimental campaign. Discord's ability for a user to rapidly move between audio channels, text with images, and share screens is a significant enhancement over traditional videoconferencing tools. In addition, multiple combinations of broadcast audio are made available via a web-based application to allow remote participants to simultaneously listen to general announcements/sounds while conducting their own specific conversations. Secure methodologies have been put into place to allow remote control of hardware including DIII-D's plasma control system application. Secure methods also included the ability of the on-site team to closely coordinate their work with remote team members which has been enhanced through extensions to the wireless network and the use of tablet computers for audio/video/screen sharing. However, no amount of software can fully replace the need for 'hands on hardware.' This infrastructure was severely stress tested during the COVID-19 pandemic where occupancy of the DIII-D control room was restricted. Operational efficiency during the pandemic, measured in discharges per hour, remained high (3.8 +/- 0.8
The rapid development of unmanned technology has brought new opportunities for mobile sensing in different fields. Naturally, traditional mobile crowdsensing (MCS) based on mobile device users and unmanned vehicle sen...
详细信息
Activity recognition is an important task in video analysis, which can be used in accident monitoring and other daily applications. Traditional activity recognition methods are mainly based on the pixel-level analysis...
详细信息
Fully capturing contextual information and analyzing the association between entity semantics and type is helpful for joint extraction task: 1) The context can reflect the part of speech and semantics of entity. 2) Th...
详细信息
Manipulated images are flooding our daily lives, which poses a threat to social security. Recently, many studies have focused on image tampering detection. However, they have poor performance on independent validation...
详细信息
More recently, unsupervised domain adaptation has been introduced to text image recognition tasks for serious domain shift problem, which can transfer knowledge from source domains to target ones. Moreover, in unsuper...
详细信息
More recently, unsupervised domain adaptation has been introduced to text image recognition tasks for serious domain shift problem, which can transfer knowledge from source domains to target ones. Moreover, in unsupervised domain adaptation for text recognition, there is no label information in the target domain to supervise the domain adaptation, especially at the character. Several existing methods regard a text image as a whole and perform only on global feature adaptation, neglecting local-level feature adaptation, i.e., characters. Others methods only focus their attention on word-level feature alignment while ignoring the categories of local-level characters. To address these issues, we propose a text recognition model via Dual adaptatiOn and Clustering, DOC for short. Regarding word-level, we construct a Global Discriminator for global feature adaptation to reduce text layout bias between source and target domains. Regarding character-level, we propose an Adaptive Feature Clustering (AFC) module, which can extract invariant character features through a local-level discriminator for adaptation. Moreover, it enhances the local-feature adaptation by a clustering scheme, which evaluates the feature adaptation by leveraging the knowledge from the source domain as much as possible. In this way, it can pay more attention to the differences in fine-grained characters. Extensive experiments on benchmark datasets demonstrate that our framework can achieve state-of-the-art performance.
Real-time collaborative programming enables a group of programmers to edit shared source code at the same time, which significantly complements the traditional non-real-time collaborative programming supported by vers...
详细信息
暂无评论