Search Results

Pedestrian attribute recognition has achieved high accuracy by exploring the relations between image regions and attributes. However, existing methods typically adopt features directly extracted from the backbone or utilize a single structure (e.g., ...

With the rapid development of knowledge graphs (KG), enhancing the performance of knowledge graph completion has become a critical research challenge. Traditional methods for KG completion rely heavily on entity and relation embeddings, often neglecting ...

Tensor Robust Principal Component Analysis (TRPCA) aims to recover clean tensor data corrupted with noise. This method finds significant application in recovering multidimensional data. However, the majority of existing methods rely solely on ...

We propose GS-LRM, a scalable large reconstruction model that can predict high-quality 3D Gaussian primitives from 2–4 posed sparse images in $\sim$0.23 s on single A100 GPU. Our model features a very simple transformer-based architecture; we patchify ...

Differential cryptanalysis and linear cryptanalysis are two classic analytical methods for block ciphers, and they are of great significance for evaluating the security of block ciphers. In practical security evaluations, a commonly used approach is to ...

In this paper, a global probability distribution structure-sparsity filter pruning is proposed to address the problem of difficult deployment of diagnostic models in resource constrained wireless sensor networks (WSNs) for edge fault diagnosis. ...

• A global probability distribution weight sparsity is proposed. Sparse boundary is derived to identify unimportant weights.
• The computational acceleration sensing is proposed to tackle that low-importance estimates consume unnecessary ...

The cockpit of modern commercial aircraft has a complex interface layout and the complex human-machine interaction interfaces can impose a cognitive load on the flight crew. A cockpit interface that meets human factors engineering requirements can ...

In Level 3 (L3) autonomous driving, the system issues a take-over request to the driver if the Automated Driving System (ADS) fails or operates outside its design domain. The driver must takeover control and resume vehicle operation. This study ...

With the development of mobile communication technology and geographic information technology, in-vehicle navigation has become more and more intelligent and convenient, and has become an important aid for people’s daily traveling. It is necessary ...

In recent years, the escalating prominence of health issues has heightened public awareness regarding healthcare. Consequently, there has been a discernible surge in the utilization of home medical products. In this paper, we will delve into how ...

Cracks on bridge surfaces represent a significant defect that demands accurate and efficient inspection methods. However, current approaches for segmenting cracks suffer from low accuracy and slow detection speed, particularly when dealing with ...

Deep neural networks (DNN) exhibit powerful feature extraction capabilities, making them highly advantageous in numerous tasks. DNN-based techniques have become widely adopted in the field of speaker recognition. However, imperceptible adversarial ...

Adversarial attacks have been posing significant security concerns to intelligent systems, such as speaker recognition systems (SRSs). Most attacks assume the neural networks in the systems are known beforehand, while black‐box attacks are ...

Vision-Language Models (VLMs) such as CLIP have demonstrated remarkable generalization capabilities to downstream tasks. However, existing prompt tuning based frameworks need to parallelize learnable textual inputs for all categories, suffering from ...

In this research, we employ a deep learning approach to extract features from an apple image dataset, enabling precise counting and localization of apples. We address challenges like low resolution and small targets by optimizing the network and ...

Indoor understanding is currently a topic that is widely studied in the field of machine learning. Furniture is the most common object in indoor scenes, just as various vehicles are most commonly seen in street scenes. Any object is made up of a ...

The vulnerability of deep neural networks (DNNs) to adversarial attacks has attracted attention in many fields, and researchers have sought methods to improve the robustness of DNNs. Most existing methods are empirical defenses that can only cope ...

In the real world, a large amount of high-order tensor data (order>3) exists, such as color videos, multispectral videos, and light-field images. However, these data often face challenges in transportation, storage, and susceptibility to damage. ...

This paper presents a novel transformer architecture for graph representation learning. The core insight of our method is to fully consider the information propagation among nodes and edges in a graph when building the attention module in the transformer ...

User experience (UX) evaluation can improve product quality, which has been confirmed in many studies. In recent years, the Chinese government has continued to promote the digitalization, intelligence and standardization of automobiles and the ...