Prompt learning has emerged as an effective strategy for adapting vision-language models (VLMs) which injects learnable semantic prompts into VLMs to guide the alignment between visual and textual representations. Although existing methods have shown strong performance across various tasks, they usually focus on the representative class-level samples and overlook the atypical and hard samples in visual feature space, which hinders generalization of VLMs. To address this issue, we propose the concept of dynamic boundary prototype, which highlights ambiguous samples that are far from the class centroid and is updated at each epoch. Accordingly, we propose a Distribution-Aware Prompt Learning (DAPL) framework to calibrate the distribution of visual feature space via the definition, optimization, and updating of dynamic boundary prototypes. Firstly, we introduce Boundary-Centroid Pulling to optimize the intra-class distribution by progressively reducing the distance between boundary and centroid prototypes, thereby enhancing structural consistency within each class. Secondly, to further enhance inter-class separability, a distance-weighted contrastive loss that places greater emphasis on distinguishing adjacent classes is designed, facilitating more effective fine-grained discrimination. Thirdly, we apply Low-Rank Adaptation Fine-Tuning to adapt the vision encoder through targeted modifications to its self-attention layers. Additionally, we adopt a progressive training strategy for stable optimization. DAPL is compatible with mainstream prompt learning methods such as CoOp, CoCoOp and PromptKD, and consistently improves their average performance across 11 benchmark datasets.

Many real-world applications contain data in the form of multivariate time series (TS) with the hierarchical structure, where classic methods forecasting each TS independently are inadequate for coherency (i.e., satisfying the hierarchical aggregation constraints).Furthermore, the discrepancies between statistical properties of different levels can be huge, exacerbated by non-Gaussian distributions and non-linear correlations.In this paper, we propose a novel end-to-end hierarchical TS forecasting model, i.e., a Flow-based Reconcile Transformer (FRT).FRT employs a conditional normalizing flow-based autoregressive transformer, to represent complex data distribution, while simultaneously reconciling the forecasts to ensure coherency.Go beyond other state-of-the-art methods, FRT accomplishes forecasting and reconciliation simultaneously, while avoiding any post-processing steps.Moreover, FRT is a deep model that does not rely on any strong assumptions such as unbiased estimates or Gaussian distribution.Our experiments are conducted on four real-world hierarchical datasets from different industrial domains (three public ones and a dataset from the application servers of our company's data center) and the results demonstrate the efficacy of our proposed method.Our method has been implemented extensively within the production environments of a prominent global payment company.It has emerged as a cornerstone for workload forecasting within their data center and plays a critical role in the optimization of cloud computing resource allocation across * Both authors contributed equally to this research.

Prompt learning has made significant progress in vision-language models (VLMs), enabling pre-trained models like CLIP to perform cross-domain tasks with few-shot or even zero-shot learning. However, existing methods tend to overfit the training data after fine-tuning on the target domain, leading to a decline in generalization ability and limiting their performance on unseen categories.To address these challenges, we propose a multi-regularization guided knowledge distillation towards generalizable prompt learning. This approach enhances the model's adaptability and generalization through different stages of regularization while mitigating performance degradation caused by target domain training. Specifically, within the image encoder of CLIP, we introduce Residual Regularization, which binds additional residual connections to certain transformer blocks. This design provides greater flexibility, allowing the model to adjust to new data distributions when adapting to the target domain.Furthermore, during training, we impose Self-distillation Regularization to ensure that while adapting to the target domain, the model preserves its prior generalization knowledge. Specifically, we regularize the intermediate layer outputs of Transformer Blocks to prevent the model from excessively favoring target domain data. Additionally, we employ an unsupervised knowledge distillation strategy to enforce multi-level alignment between the teacher and student models by Direction Distillation Regularization. This ensures that both models maintain consistent visual feature orientations under the same textual features, thereby enhancing overall model stability and cross-domain adaptability.Experimental results demonstrate that our method achieves more stable classification performance in both cross-domain few-shot classification and domain adaptation settings.

Olfactory-enhanced virtual reality (OVR) creates a complex and rich emotional experience, thus promoting a new generation of human-computer interaction experiences in real-world scenarios. However, with the rise of virtual reality (VR) as a mood induction procedure (MIP), few studies have incorporated olfactory stimuli into emotion induction in three-dimensional (3D) environments. Considering the differences in electroencephalography (EEG) dynamics between sensory stimuli, all previous two-dimensional (2D) and 3D emotional studies have been less effective in reality because they only use visual and audio senses. To overcome these limitations, we developed a novel EEG signal dataset based on OVR. We systematically analyzed the influence of olfactory stimuli on emotion induction in a VR environment from a neurophysiological perspective. Specifically, synchronous EEG signals were collected from 65 participants as they watched positive and negative videos in traditional VR and OVR. Their power spectral densities (PSDs) were then calculated to compare the differences in brain activation between their VR and OVR modes during the induction of positive and negative emotions, while their brain states were classified after feature selection. The results showed that olfactory stimuli enhanced EEG responses for positive emotions, but the opposite was true for negative emotions. Additionally, the recognition rate of brain emotional states was more than 90% under both positive and negative emotions, while the high-frequencyβandγbands could effectively distinguish VR and OVR modes. This study introduced the olfaction into the field of human-computer interaction, which could promote research on emotion induction and recognition in real-world environments.

Convolutional neural networks (CNNs) are commonly employed for image emotion recognition owing to their ability to extract local features; however, they have difficulty capturing the global representations of images. In contrast, self-attention modules in a visual transformer network can capture long-range dependencies as global features. Some studies have shown that an image's local and global features determine the emotions of the image and that some local regions can generate an emotional prioritization effect. Therefore, we proposed combining global self-attention features and a local multiscale features network (CGLF-Net) to recognize an image's emotion, extracting image features from global and local perspectives. Specifically, the cross-scale transformer network is employed instead of convolution operations in the global feature branch to enhance its model feature representation. In the local feature branch, the improved feature pyramid module is applied to extract features from different sensory fields, thereby combining semantic information with different scales. Furthermore, the local attention module based on class activation maps guides the network to focus on locally salient regions. In addition, using multibranch loss functions, local and global feature branches are combined to enhance the ability to capture a comprehensive set of features. Consequently, the proposed network achieves recognition accuracies of 75.61% and 65.01% on the FI-8 benchmark dataset and Emotion-6 benchmark dataset, respectively. These results show that the proposed CGLF-Net reliably address the difficulty of extracting global features using CNNs, representing the classification performance of the state-of-the-art.

Emotion is a human attitude experience and corresponding behavioral response to objective things. Effective emotion recognition is important for the intelligence and humanization of brain-computer interface (BCI). Although deep learning has been widely used in emotion recognition in recent years, emotion recognition based on electroencephalography (EEG) is still a challenging task in practical applications. Herein, we proposed a novel hybrid model that employs generative adversarial networks to generate potential representations of EEG signals while combining graph convolutional neural networks and long short-term memory networks to recognize emotions from EEG signals. Experimental results on DEAP and SEED datasets show that the proposed model achieved the promising emotion classification performance compared with the state-of-the-art methods.