-
Article
Open AccessCross-modal learning using privileged information for long-tailed image classification
The prevalence of long-tailed distributions in real-world data often results in classification models favoring the dominant classes, neglecting the less frequent ones. Current approaches address the issues in ...
-
Chapter and Conference Paper
SSCAN:Structural Graph Clustering on Signed Networks
Structural graph clustering ( \(\textsf{SCAN}\) SCAN ) is a foundational problem about managi...
-
Chapter and Conference Paper
Unsupervised Segmentation of Haze Regions as Hard Attention for Haze Classification
Haze classification plays a crucial role in air quality and visibility assessment. In contrast to traditional image classification, haze classification requires the classifier to capture the characteristics of...
-
Chapter and Conference Paper
Meta-Causal Feature Learning for Out-of-Distribution Generalization
Causal inference has become a powerful tool to handle the out-of-distribution (OOD) generalization problem, which aims to extract the invariant features. However, conventional methods apply causal learners fro...
-
Chapter and Conference Paper
Learning to Fuse Residual and Conditional Information for Video Compression and Reconstruction
With the rapid development of the Internet, video compression and reconstruction have attracted more and more attention as the use and transmission frequency of video data have increased dramatically. Traditio...
-
Chapter and Conference Paper
Make Active Attention More Active: Using Lipschitz Regularity to Improve Long Sequence Time-Series Forecasting
Long-term time series prediction aims to accurately forecast the future by analyzing the prevailing temporal patterns derived from historical data inputs. Commonly used techniques for long-term time series pre...
-
Chapter and Conference Paper
Hierarchical Contrastive Learning for CSI-Based Fingerprint Localization
Fingerprint localization based on Channel State Information (CSI) plays a crucial role in indoor location-based services. Due to the natural compatibility between offline training and online localization of CS...
-
Chapter and Conference Paper
Detformer: Detect the Reliable Attention Index for Ultra-long Time Series Forecasting
Long sequence time-series forecasting is a challenging task that involves all aspects of production and life. This requires establishing a model to efficiently predict the future by using temporal dependencies...
-
Chapter and Conference Paper
Rethink the Top-u Attention in Sparse Self-attention for Long Sequence Time-Series Forecasting
Long time-series forecasting plays a crucial role in production and daily life, covering various areas such as electric power loads, stock trends and road traffic. Attention-based models have achieved signific...
-
Article
Open AccessRecent advances in glinty appearance rendering
The interaction between light and materials is key to physically-based realistic rendering. However, it is also complex to analyze, especially when the materials contain a large number of details and thus exhi...
-
Article
Open AccessIdentification of long non-coding RNAs and microRNAs involved in anther development in the tropical Camellia oleifera
Explored the molecular science of anther development is important for improving productivity and overall yield of crops. Although the role of regulatory RNAs, including long non-coding RNAs (lncRNAs) and micro...
-
Chapter and Conference Paper
VAFA: A Visually-Aware Food Analysis System for Socially-Engaged Diet Management
In this demo, we demonstrate a visually-aware food analysis (VAFA) system for socially-engaged diet management. VAFA is capable of receiving multimedia inputs, such as the images of food with/without a descrip...
-
Chapter and Conference Paper
Clustering-based Curriculum Construction for Sample-Balanced Federated Learning
Federated learning is a distributed machine learning scheme that provides data privacy-preserving solution. A key challenge is data distribution heterogeneity of on different parties in federated learning. Exi...
-
Chapter and Conference Paper
Prompt Learning with Cross-Modal Feature Alignment for Visual Domain Adaptation
Exploring the capacity of pre-trained large-scale models to learn common features of multimodal data and the effect of knowledge transfer on downstream tasks are two major trends in the multimedia field. Howev...
-
Chapter and Conference Paper
Causal Inference with Sample Balancing for Out-of-Distribution Detection in Visual Classification
Image classification algorithms are commonly based on the Independent and Identically Distribution (IID) assumption, but in practice, the Out-Of-Distribution (OOD) problem is widely existing, i.e., the context...
-
Chapter and Conference Paper
Sequential Fusion of Multi-view Video Frames for 3D Scene Generation
3D scene understanding and generation are to reconstruct the layout of the scene and each object from an RGB image, estimate its semantic type in 3D space and generate a 3D scene. At present, the 3D scene gene...
-
Article
Cross-device task interaction framework between the smart watch and the smart phone
Along with the increasing emergence of smart watch devices, new interaction techniques between these devices and smart phones have been proposed to leverage their availability. However, there are few existing ...
-
Article
A 3D sunken-relief generation method of human faces from depth images of feature lines
In this paper, we propose a line-based 3D sunken-relief generation method that considers the influence of light direction on the width and depth of engraved lines. Firstly, the height field of a human face mod...
-
Article
Open AccessThird-generation sequencing and metabolome analysis reveal candidate genes and metabolites with altered levels in albino jackfruit seedlings
Most plants rely on photosynthesis; therefore, albinism in plants with leaves that are white instead of green causes slow growth, dwarfing, and even death. Although albinism has been characterized in annual mo...
-
Article
Third-Generation Sequencing Indicated that LncRNA Could Regulate eIF2D to Enhance Protein Translation Under Heat Stress in Populus simonii
As global temperatures rise, plants are being increasingly exposed to high-temperature stress. Although long non-coding RNAs (lncRNAs) are regulatory elements of gene expression under heat stress in trees, the...
