Graph convolutional networks (GCNs) have been widely used in skeleton-based hand gesture recognition due to strong ability in mining non-Euclidean features. However, GCNs cannot effectively extract long temporal information. To address this issue, ...

Smartphones have become the mainstream terminals in the field of location services due to their low cost, portability, and ubiquity. In highly dynamic situations, the challenging urban environment causes the received Global Navigation Satellite ...

The task of Extractive Question Answering (EQA) involves identifying correct answer spans in response to provided questions and passages. The emergence of Pretrained Language Models (PLMs) has sparked increased interest in leveraging these models ...

The task of Multiple Choice Question Answering (MCQA) aims to identify the correct answer from a set of candidates, given a background passage and an associated question. Considerable research efforts have been dedicated to addressing this task, ...

Graph convolutional networks (GCNs) are widely used in skeleton-based action recognition. It is known that the graph topology is a vital part in GCNs, and different kinds of graph topologies have been proposed for skeleton-based action ...

• Temporal frame-wise and channel-wise topology based GCNs (TC-GCNs) are developed instead of using a predefined topology.
• The proposed TC-GCNs can be integrated with the conventional dynamic graph to improve performance.
• Extensive ...

Multi-modal action recognition methods can be generally classified into two categories: (1) fusing multi-modal features with simple concatenation or fusing the classification scores of individual modalities without considering the interaction ...

• End-to-end trainable deep fusion network (DFN) for action recognition.
• DFN outperforms the commonly used fusion methods.
• DFN performs better than single modality cases when one modality is missing.
• Competitive performance ...

Monocular depth estimation aims to infer a depth map from a single image. Although supervised learning-based methods have achieved remarkable performance, they generally rely on a large amount of labor-intensively annotated data. Self-supervised methods, ...

Fully automatic postural assessment is highly useful, but has been challenging. Conventional methods either require manual assessment by ergonomists or depend on special devices that are intrusive, thus being hardly feasible in daily activities ...

• A novel attention-based CNN for automatic whole-body postural assessment.
• The network works directly on single color images rather than 3D skeletons.
• A new multi-view and multi-modality dataset is created for postural assessment ...

Electronic signatures are widely used in financial business, telecommuting, and identity authentication. Offline electronic signatures are vulnerable to copy or replay attacks. Contact-based online electronic signatures are limited by indirect contact ...

• Considering the dynamic reference in prospect theory to reflect the idea of DMs.

Consensus is an important issue in group decision making to make a reliable and scientific decision, and it has become a hot topic recently. Due to the complexity and uncertainty of decision-making problems, several aspects of ...

This article proposes a network, referred to as Multi-View Stereo TRansformer (MVSTR) for depth estimation from multi-view images. By modeling long-range dependencies and epipolar geometry, the proposed MVSTR is capable of extracting dense features with ...

Mammography is an important screening criterion for breast cancer, one of the major diseases causing numerous deaths among female patients. Meanwhile, manual diagnosis of mammography is a time-consuming and labor-consuming job. ...

Novel view synthesis aims to generate novel views from one or more given source views. Although existing methods have achieved promising performance, they usually require paired views with different poses to learn a pixel transformation. This article ...

Sign languages generally consist of a sequence of upper body gestures and are cooperative processes among various parts such as the hands, arms, and face. Therefore, the dynamics of the parts as well as the holistic appearance of the upper body ...

Zero-Shot Action Recognition (ZSAR) aims to recognize video actions that have never been seen during training. Most existing methods assume a shared semantic space between seen and unseen actions and intend to directly learn a mapping from a ...

Despite great progress achieved by transformer in various vision tasks, it is still underexplored for skeleton-based action recognition with only a few attempts. Besides, these methods directly calculate the pair-wise global self-attention equally ...

There are already some text-based visual question answering (TextVQA) benchmarks for developing machine's ability to answer questions based on texts in images in recent years. However, models developed on these benchmarks cannot work effectively in many ...

Recent contrastive based 3D action representation learning has made great progress. However, the strict positive/negative constraint is yet to be relaxed and the use of non-self positive is yet to be explored. In this paper, a Contrastive Positive ...

Analysis of human interaction is one important research topic of human motion analysis. It has been studied either using first-person vision (FPV) or third-person vision (TPV). However, the joint learning of both types of vision has so far ...

• A consensus model based on endo-confidence is constructed.
• Double hierarchical clustering is introduced in the consensus reaching process. Firstly, the experts are classified according to their evaluations (the numerical evaluations ...

With the development of novel technological and societal paradigms, consensus in multi-attribute large-scale group decision making is of great significance. The confidence derived by evaluation is considered in this paper and it is named as endo-...