Search Results

Face forgery has become more realistic with deep learning in computer vision, posing a significant challenge to trustworthy face identification. Existing works have achieved considerable accuracy within the dataset by formulating the detection as ...

Arbitrary style transfer (AST) plays a pivotal role in image processing, as it can impart the stylistic characteristics of a reference image onto a chosen target content image. However, existing AST methods based on convolutional neural networks (...

3D occupancy prediction based on multi-sensor fusion, crucial for a reliable autonomous driving system, enables fine-grained under- standing of 3D scenes. Previous fusion-based 3D occupancy predictions relied on depth estimation for processing 2D ...

Information spread within social networks is a complex process with broad implications. Predicting information diffusion is crucial for understanding information spread within social networks. However, previous research has primarily focused on ...

Cross-domain sequential recommendation (CDSR) aims to predict user-item interactions from historical sequences across domains. Current CDSR approaches mainly focus on leveraging intrinsic connections among items to capture the dependencies across ...

Bicliques, as a prevalent graph pattern, are of particular interest in graph mining and social network analysis, especially for detecting illegal activities on e-commerce platforms due to their dense structure. Overcoming the challenge of ...

• Developing GPU framework for MBE in large networks, first to solve in real-world.
• GPU-accelerated MBE with efficient APIs for various data analysis needs.
• Our framework outperforms with up to 12x speedup on key graph datasets.

Data-to-Text Generation (D2T), a classic natural language generation problem, aims at producing fluent descriptions for structured input data, such as a table. Existing D2T works mainly focus on describing the superficial associative relations ...

Smart contract, as the representative application of blockchain, has recently fueled extensive research interests from both academia and industry. However, with its wide applications, the weaknesses of smart contract have been gradually revealed. ...

Weak diagram analysis abilities of LLMs or Multimodal LLMs greatly limit their application scenarios for scientific academic paper writing. In this work, towards a more versatile copilot for academic paper writing, we mainly focus on strengthening the ...

Recently, temporal action localization (TAL) methods, especially the weakly-supervised and unsupervised ones, have become a hot research topic. Existing unsupervised methods follow an iterative ''clustering and training'' strategy with diverse model ...

Large Vision-Language Models (LVLMs) exhibit remarkable capabilities but struggle with ''hallucinations''-inconsistencies between images and their descriptions. Previous hallucination evaluation studies on LVLMs have identified hallucinations in terms of ...

Cross-domain recommendation (CDR) aims to suggest items from new domains that align with potential user preferences, based on their historical interactions. Existing methods primarily focus on acquiring item representations by discovering user ...

Image super-resolution (SR) is a crucial task in computer vision that involves reconstructing a low-resolution (LR) image into its high-resolution (HR) counterpart. Transformer-based methods excel at establishing long-range dependency but face ...

Knowledge distillation is a technique that aims to transfer valuable knowledge from a large, well-trained model (the teacher) to a lightweight model (the student), with the primary goal of improving the student's performance on a given task. In ...

• Study knowledge distillation from the teacher's perspective and introduce a novel teacher enhancement method (Generous Teacher).
• The knowledge learned by the Generous Teacher is more conducive to student distillation learning.
• ...

This research aims to verify the direct effect and internal mechanism of digital trade on the upgrading of GVCs and put forward corresponding policy recommendations. The study takes 42 OECD countries from 2005 to 2020 as samples, constructs a digital ...

The industrial digitalization brought about by the digital economy has become an important way for China's manufacturing industry to realize the climb of the value chain. This paper deeply discusses the role mechanism of China's manufacturing ...

Effectively identifying anomalous nodes within networks is crucial for various applications, such as fraud detection, network intrusion prevention, and social network activity monitoring. Existing graph anomaly detection methods based on ...

Predicting epidemics is of vital significance for safeguarding human life, health, and safety. Spatio-temporal graph neural networks have been successfully employed in epidemic forecasting, as they can extract information from both the temporal ...

Log-structured merge tree (LSM-tree) has been widely adopted by modern key-value stores. Deploying LSM-tree across heterogeneous SSD storage which combines the fast but expensive NVMe storage tier with the slow but economical SATA storage tier has ...

In the digital era, the rapid propagation of fake news and rumors via social networks brings notable societal challenges and impacts public opinion regulation. Traditional fake news modeling typically forecasts the general popularity trends of different ...