56 hasil
Menampilkan 1–20 · 0,24 detik · RSS
CAAI Artificial Intelligence Research
ISSN 2097-194X · Tsinghua University Press · 56 artikel di indeks
-
Artikel Jurnal
Silhouette-driven contrastive learning with hierarchical neighborhood structure for unsupervised clothes change person re-identification
This paper addresses a highly challenging yet critical task: unsupervised person re-identification (Re-ID) under clothing changes. Unfortunately, existing unsupervised person Re-ID methods are mainly designed for short-term scenarios that rely heavily on RGB cues, thus failing to exploit effective…
-
Artikel Jurnal
A survey on deep learning techniques for image and video feature aggregation
Nowadays, deep learning has demonstrated impressive performance in the area of computer vision and pattern recognition, such as objects recognition, videos classification and image segmentation. In particular, convolutional neural networks (CNNs) an advanced deep-learning technique have achieved…
-
Artikel Jurnal
Optimal strategies of blockchain-enabled platform supply chain with manufacturer’s altruistic preference
This paper investigates a platform supply chain consisting of a manufacturer and a platform and explores the impact of the manufacturer’s altruistic preference on the platform’s decision to introduce blockchain technology in reselling and agency models. The results indicate that, firstly, when the…
-
Artikel Jurnal
Evaluation study on SAM 2 for class-agnostic instance-level segmentation
Segment anything model (SAM) has demonstrated powerful zero-shot segmentation performance in natural scenes. The recently released segment anything model 2 (SAM2) has further heightened researchers’ expectations towards image segmentation capabilities. To evaluate the performance of SAM2 on…
-
Artikel Jurnal
Light2Ray: Lightweight dual-view prohibited item detection model in X-ray images based on Transformer
Using computer vision technology to detect prohibited items in X-ray images is an effective method for realizing intelligent security checking. Dual-view security checking can capture the images from both vertical and horizontal perspectives of the same package at the same time, addressing issues…
-
Artikel Jurnal
A recurrent neural network approach for discrete-form stewart platform control with disturbance rejection
Recurrent neural networks (RNNs) have been employed extensively as intelligent control approaches across various industrial control fields. However, existing research often lacks sufficient focus on discrete-form time-variant problems and disturbance rejection capability. This paper proposes a…
-
Artikel Jurnal
PlantCamo: Plant Camouflage Detection
Camouflaged Object Detection (COD) aims to detect objects with camouflaged properties. Although previous studies have focused on natural (animals and insects) and unnatural (artistic and synthetic) camouflage detection, plant camouflage has been neglected. However, plant camouflage plays a vital…
-
Artikel Jurnal
Dual-Stream IB-Enhanced Framework for Video-Based Person Re-Identification
Person re-identification (ReID) is a desirable yet challenging issue in computer vision, which has numerous potential applications in the public security area. In this paper, the information bottleneck (IB) theory is introduced to filter out the undiscriminating information and noise, and keep the…
-
Artikel Jurnal
GasUpper: Gas-Aware Upsampling for Enhanced Gas Segmentation
Segmenting greenhouse gases from hyperspectral images can provide detailed information regarding their spatial distribution, which is significant for the monitoring of greenhouse gases. However, accurate segmentation of greenhouse gases is a challenging task due to two main reasons: (1) Diversity…
-
Artikel Jurnal
Underwater light field imaging: A survey
Underwater light field (ULF) imaging has emerged as a promising technology for capturing a more comprehensive array of visual information from real-world underwater environments. Unlike conventional underwater photography, which captures a two-dimensional projection of light that integrates over…
-
Artikel Jurnal
Minimize Quantization Output Error with Bias Compensation
Quantization is a promising method that reduces memory usage and computational intensity of Deep Neural Networks (DNNs), but it often leads to significant output error that hinder model deployment. In this paper, we propose Bias Compensation (BC) to minimize the output error, thus realizing…
-
Artikel Jurnal
Interactive Embodied Intelligence of Machines
This paper discusses how intelligent machines have replaced humans in tasks requiring, heavy, and repetitive labor, whilst being better suited to the requirements of these jobs. The increased capacity for brute force computation has facilitated increased collaborative innovation between man and…
-
Artikel Jurnal
Variational Quantum Monte Carlo Solution of the Many-Electron Schrödinger Equation Based on Deep Neural Networks
The solution of Schrödinger equation generates the quantisation properties of the system, which can completely describe the quantum behaviour of microscopic particles in a physical system. However, solving the Schrödinger equation is a non-deterministic polynomial time (NP)-hard problem. Numerical…
-
Artikel Jurnal
Enhancing Hand Rehabilitation Through Interactive Design
The demand for hand rehabilitation services is increasing currently, and there are many choices of hand rehabilitation products available on the market. Here, we report a flexible curvature sensor-based data glove, equipped with a built-in light trigger system, which is expected to provide active…
-
Artikel Jurnal
Object-to-Manipulation Graph for Affordance Navigation
Object navigation, whose goal is to let the agent to reach some places (or objects), has been a popular topic in embodied Artificial Intelligence (AI) researches. However, in our real-world applications, it is more practical to find the targets with particular goals, raising the new requirements of…
-
Artikel Jurnal
ADGAN: Adaptive Domain Medical Image Synthesis Based on Generative Adversarial Networks
Multimodal medical imaging of human pathological tissues provides comprehensive information to assist in clinical diagnosis. However, due to the high cost of imaging, physiological incompatibility, and the harmfulness of radioactive tracers, multimodal medical image data remains scarce. Currently…
-
Artikel Jurnal
A Comprehensive Survey on Embodied Intelligence: Advancements, Challenges, and Future Perspectives
Embodied Intelligence, which integrates physical interaction capabilities with cognitive computation in real-world scenarios, provides a promising path to achieve Artificial General Intelligence (AGI). Recently, the landscape of embodied intelligence has grown profoundly, empowering robotics…
-
Artikel Jurnal
Survey on Collaborative Task Assignment for Heterogeneous UAVs Based on Artificial Intelligence Methods
Heterogeneous unmanned aerial vehicle (UAV) swarms have garnered significant attention from researchers worldwide due to their remarkable flexibility, diverse mission capabilities, and wide-ranging potential applications. Mission planning stands at the core of UAV swarm operations, requiring…
-
Artikel Jurnal
A Multi-Dimensional Evaluation Model for Epidemic Prevention Policies
In recent years, governments of more than 200 countries and regions have enacted measures to control the spread of COVID-19. A precise and comprehensive evaluation of policy effect provides important grounds for policy-making. Since the whole world has entered the post-epidemic era, prevention…
-
Artikel Jurnal
Feature-Centric Video Transmission and Analytics in Large-Scale Internet of Video Things
The interconnection of large-scale visual sensors is called the Internet of Video Things (IoVT), which brings a qualitative leap to the interaction of urban information. However, communication delay and resource allocation have brought challenges to the development of IoVT. In this paper, we…