Weisi Lin

IPM-FM: A Foundation Model with Consensus Feature Selection for Industrial Process Monitoring

Liang Cao, Weide Liu, Yan Qin, Jun Cheng et autres

Industrial process monitoring is fundamental to the safety and economic performance of modern process plants. Current practice remains a one-task-one-model paradigm that is label-inefficient and prone to degradation under operating drift. Foundation models have reshaped language, vision, and generic time-series forecasting, but …

Rethinking Objective Image Quality Assessment With Federated Learning

Shishun Tian, Yonghong Zheng, Guanghui Yue, Weisi Lin et autres

cn, sg, fr (code pays fourni par la source)

From Global to Granular: Revealing IQA Model Performance via Correlation Surface

Baoliang Chen, Danni Huang, Hanwei Zhu, Lingyu Zhu et autres

Evaluation of Image Quality Assessment (IQA) models has long been dominated by global correlation metrics, such as Pearson Linear Correlation Coefficient (PLCC) and Spearman Rank-Order Correlation Coefficient (SRCC). While widely adopted, these metrics reduce performance to a single scalar, failing to capture …

cn, sg, hk, gb (code pays fourni par la source)

You can mask more for extremely low-bitrate image compression

Anqi Li, Feng Li, Jiaxin Han, Runmin Cong et autres

cn, sg (code pays fourni par la source)

MUGSQA: Novel Multi-Uncertainty-based Gaussian Splatting Quality Assessment Method, Dataset, and Benchmarks

Shilv Cai, Zhuangzi Li, Weisi Lin

Gaussian Splatting (GS) has recently emerged as a promising technique for 3D object reconstruction, delivering high-quality rendering results with significantly improved reconstruction speed. As variants continue to appear, assessing the perceptual quality of 3D objects reconstructed with different GS-based methods remains an …

sg (code pays fourni par la source)

Scaling Audio-Visual Quality Assessment Dataset via Crowdsourcing

Renyu Yang, Jian Jin, Lili Meng, Meiqin Liu et autres

Audio-visual quality assessment (AVQA) research has been stalled by limitations of existing datasets: they are typically small in scale, with insufficient diversity in content and quality, and annotated only with overall scores. These shortcomings provide limited support for model development and multimodal …

sg, cn, us (code pays fourni par la source)

Diffusion-Driven RGB-D Salient Object Detection With Temporal Modulation

Shixiang Shi, Gongyang Li, Runmin Cong, Shunxin Xiao et autres

Existing RGB-D Salient Object Detection (SOD) methods are primarily built on the end-to-end prediction paradigm. Although these methods have achieved remarkable progress, they still struggle to generate accurate predictions in some complex scenes due to their lack of error correction capability. In …

cn, sg (code pays fourni par la source)

Incomplete-scan CT reconstruction via deep learning: a review

Jinpeng An, Xu Fan, Yue Liu, Xi Zhang et autres

Computed tomography (CT) is a significant clinical detection method without invasive procedures. However, high-dose radiation is associated with elevated risk of cancer. Low-dose CT reconstruction techniques have the potential to significantly reduce this risk. These techniques reduce radiation dose by two means: …

cn, sg (code pays fourni par la source)

Symmetric Entropy-Constrained Video Coding for Machines

Yuxiao Sun, Meiqin Liu, Chao Yao, Jian Jin et autres

As video transmission increasingly serves machine vision systems (MVS) instead of human vision systems (HVS), video coding for machines (VCM) has become a critical research topic. Existing VCM methods often bind codecs to specific downstream models, requiring retraining or supervised data, thus …

cn, sg, fr (code pays fourni par la source)

Ghost-Free HDR Imaging via Latent Low-Frequency Priors and Deformable Attention Alignment

Tao Hu, Qingsen Yan, Jian Jin, Wei Dong et autres

Recovering ghost-free High Dynamic Range (HDR) images from multiple Low Dynamic Range (LDR) images becomes challenging when the LDR images exhibit saturation and significant motion. Recent Diffusion Models (DMs) have been introduced in HDR imaging field, showing promising performance, particularly in achieving …

cn, sg, au (code pays fourni par la source)

LB-PTQ: Effective Low-Bit Post-Training Quantization for Vision Transformers

Zhe Wang, Kaixin Xu, Xue Geng, Jie Lin et autres

Recently, Vision Transformers (ViTs) have become the state-of-the-art architecture on various computer vision tasks including image classification, object detection and semantic segmentation. However, such success in high-accuracy performance comes at the price of high computational complexity, with typically tens of millions of …

sg (code pays fourni par la source)

A Prototype Feature Representation-Guided Multitask Learning Framework for Image-Based PM 2.5 Concentration Monitoring

Guangcheng Wang, Jifan Yang, Kui Jiang, Ke Gu et autres

With rapid industrialization, air pollution has emerged as a critical societal problem. Particulate matter (PM2:5) poses severe threats to public health and ecosystems, making it paramount to establish accurate and scalable monitoring solutions to safeguard the health of humans and animals as …

cn, my, sg (code pays fourni par la source)