Related papers: Correlation-Attention Masked Temporal Transformer …

Skeleton-based human action recognition has achieved a great interest in recent years, as skeleton data has been demonstrated to be robust to illumination changes, body scales, dynamic camera views, and complex background. Nevertheless, an…

Recent work on encoder-decoder models for sequence-to-sequence mapping has shown that integrating both temporal and spatial attention mechanisms into neural networks increases the performance of the system substantially. In this work, we…

Multimodal time series (MTS) anomaly detection is crucial for maintaining the safety and stability of working devices (e.g., water treatment system and spacecraft), whose data are characterized by multivariate time series with diverse…

Transformers have achieved great success in machine translation, but transformer-based NMT models often require millions of bilingual parallel corpus for training. In this paper, we propose a novel architecture named as attention link (AL)…

Transformer has been widely used for self-supervised pre-training in Natural Language Processing (NLP) and achieved great success. However, it has not been fully explored in visual self-supervised learning. Meanwhile, previous methods only…

This paper introduces a novel approach for multimodal sentiment analysis on social media, particularly in the context of natural disasters, where understanding public sentiment is crucial for effective crisis management. Unlike conventional…

Previous stance detection studies typically concentrate on evaluating stances within individual instances, thereby exhibiting limitations in effectively modeling multi-party discussions concerning the same specific topic, as naturally…

Facial Action Unit (AU) detection is a crucial task for emotion analysis from facial movements. The apparent differences of different subjects sometimes mislead changes brought by AUs, resulting in inaccurate results. However, most of the…

Supervised person re-identification methods rely heavily on high-quality cross-camera training label. This significantly hinders the deployment of re-ID models in real-world applications. The unsupervised person re-ID methods can reduce the…

Trajectory-User Linking (TUL) is a relatively new mobility classification task in which anonymous trajectories are linked to the users who generated them. With applications ranging from personalized recommendations to criminal activity…

Structured dropout approaches, such as attention dropout and DropHead, have been investigated to regularize the multi-head attention mechanism in Transformers. In this paper, we propose a new regularization scheme based on token-level…

Recent advances in transformer architectures have revolutionised natural language processing, but their application to healthcare domains presents unique challenges. Patient timelines are characterised by irregular sampling, variable…

Various Transformer-based models have been proposed for time series forecasting. These models leverage the self-attention mechanism to capture long-term temporal or variate dependencies in sequences. Existing methods can be divided into two…

Person re-identification aims at identifying a certain pedestrian across non-overlapping camera networks. Video-based re-identification approaches have gained significant attention recently, expanding image-based approaches by learning…

Neural NLP models are often miscalibrated and overconfident, assigning high confidence to incorrect predictions and failing to express uncertainty during internal evidence aggregation. This undermines selective prediction and high-stakes…

Skeleton-based gesture recognition methods have achieved high success using Graph Convolutional Network (GCN). In addition, context-dependent adaptive topology as a neighborhood vertex information and attention mechanism leverages a model…

Currently, convolutional neural networks (CNN) (e.g., U-Net) have become the de facto standard and attained immense success in medical image segmentation. However, as a downside, CNN based methods are a double-edged sword as they fail to…

The inherent instability and noise in user interaction data challenge sequential recommendation systems. Prevailing masked attention models, relying on a single query from the most recent item, are sensitive to this noise, reducing…

In recent years, deep neural networks are yielding better performance in image classification tasks. However, the increasing complexity of datasets and the demand for improved performance necessitate the exploration of innovative…

Accurate recognition of sign language in healthcare communication poses a significant challenge, requiring frameworks that can accurately interpret complex multimodal gestures. To deal with this, we propose FusionEnsemble-Net, a novel…