Search Results for author: Weisi Lin

Found 62 papers, 35 papers with code

Local Distortion Aware Efficient Transformer Adaptation for Image Quality Assessment

no code implementations23 Aug 2023 Kangmin Xu, Liang Liao, Jing Xiao, Chaofeng Chen, HaoNing Wu, Qiong Yan, Weisi Lin

Further, we propose a local distortion extractor to obtain local distortion features from the pretrained CNN and a local distortion injector to inject the local distortion features into ViT.

Image Quality Assessment Inductive Bias +1

Efficient Joint Optimization of Layer-Adaptive Weight Pruning in Deep Neural Networks

1 code implementation21 Aug 2023 Kaixin Xu, Zhe Wang, Xue Geng, Jie Lin, Min Wu, XiaoLi Li, Weisi Lin

On ImageNet, we achieve up to 4. 7% and 4. 6% higher top-1 accuracy compared to other methods for VGG-16 and ResNet-50, respectively.

Combinatorial Optimization

TOPIQ: A Top-down Approach from Semantics to Distortions for Image Quality Assessment

1 code implementation6 Aug 2023 Chaofeng Chen, Jiadi Mo, Jingwen Hou, HaoNing Wu, Liang Liao, Wenxiu Sun, Qiong Yan, Weisi Lin

Our approach to IQA involves the design of a heuristic coarse-to-fine network (CFANet) that leverages multi-scale features and progressively propagates multi-level semantic information to low-level representations in a top-down manner.

Image Quality Assessment Local Distortion

Regression-free Blind Image Quality Assessment

no code implementations18 Jul 2023 Xiaoqi Wang, Jian Xiong, Hao Gao, Weisi Lin

Regression-based blind image quality assessment (IQA) models are susceptible to biased training samples, leading to a biased estimation of model parameters.

Blind Image Quality Assessment regression +2

Advancing Zero-Shot Digital Human Quality Assessment through Text-Prompted Evaluation

1 code implementation6 Jul 2023 ZiCheng Zhang, Wei Sun, Yingjie Zhou, HaoNing Wu, Chunyi Li, Xiongkuo Min, Xiaohong Liu, Guangtao Zhai, Weisi Lin

To address this gap, we propose SJTU-H3D, a subjective quality assessment database specifically designed for full-body digital humans.

You Can Mask More For Extremely Low-Bitrate Image Compression

1 code implementation27 Jun 2023 Anqi Li, Feng Li, Jiaxin Han, Huihui Bai, Runmin Cong, Chunjie Zhang, Meng Wang, Weisi Lin, Yao Zhao

Extensive experiments have demonstrated that our approach outperforms recent state-of-the-art methods in R-D performance, visual quality, and downstream applications, at very low bitrates.

Image Compression

GMS-3DQA: Projection-based Grid Mini-patch Sampling for 3D Model Quality Assessment

1 code implementation9 Jun 2023 ZiCheng Zhang, Wei Sun, Houning Wu, Yingjie Zhou, Chunyi Li, Xiongkuo Min, Guangtao Zhai, Weisi Lin

Model-based 3DQA methods extract features directly from the 3D models, which are characterized by their high degree of complexity.

Point Cloud Quality Assessment

AGIQA-3K: An Open Database for AI-Generated Image Quality Assessment

1 code implementation7 Jun 2023 Chunyi Li, ZiCheng Zhang, HaoNing Wu, Wei Sun, Xiongkuo Min, Xiaohong Liu, Guangtao Zhai, Weisi Lin

With the rapid advancements of the text-to-image generative model, AI-generated images (AGIs) have been widely applied to entertainment, education, social media, etc.

Image Quality Assessment

Towards Explainable In-the-Wild Video Quality Assessment: A Database and a Language-Prompted Approach

1 code implementation22 May 2023 HaoNing Wu, Erli Zhang, Liang Liao, Chaofeng Chen, Jingwen Hou, Annan Wang, Wenxiu Sun, Qiong Yan, Weisi Lin

Though subjective studies have collected overall quality scores for these videos, how the abstract quality scores relate with specific factors is still obscure, hindering VQA methods from more concrete quality evaluations (e. g. sharpness of a video).

Video Quality Assessment Visual Question Answering (VQA)

GCFAgg: Global and Cross-view Feature Aggregation for Multi-view Clustering

1 code implementation CVPR 2023 Weiqing Yan, Yuanyang Zhang, Chenlei Lv, Chang Tang, Guanghui Yue, Liang Liao, Weisi Lin

However, most existing deep clustering methods learn consensus representation or view-specific representations from multiple views via view-wise aggregation way, where they ignore structure relationship of all samples.

Clustering Contrastive Learning +1

Towards Robust Text-Prompted Semantic Criterion for In-the-Wild Video Quality Assessment

2 code implementations28 Apr 2023 HaoNing Wu, Liang Liao, Annan Wang, Chaofeng Chen, Jingwen Hou, Wenxiu Sun, Qiong Yan, Weisi Lin

The proliferation of videos collected during in-the-wild natural settings has pushed the development of effective Video Quality Assessment (VQA) methodologies.

Video Quality Assessment Visual Question Answering (VQA)

Blind Multimodal Quality Assessment: A Brief Survey and A Case Study of Low-light Images

no code implementations18 Mar 2023 Miaohui Wang, Zhuowei Xu, Mai Xu, Weisi Lin

Blind image quality assessment (BIQA) aims at automatically and accurately forecasting objective scores for visual signals, which has been widely used to monitor product and service quality in low-light applications, covering smartphone photography, video surveillance, autonomous driving, etc.

Autonomous Driving Blind Image Quality Assessment

The First Comprehensive Dataset with Multiple Distortion Types for Visual Just-Noticeable Differences

no code implementations5 Mar 2023 Yaxuan Liu, Jian Jin, Yuan Xue, Weisi Lin

To benefit JND modeling, this work establishes a generalized JND dataset with a coarse-to-fine JND selection, which contains 106 source images and 1, 642 JND maps, covering 25 distortion types.

Image Quality Assessment Video Compression

MetaGrad: Adaptive Gradient Quantization with Hypernetworks

no code implementations4 Mar 2023 Kaixin Xu, Alina Hui Xiu Lee, Ziyuan Zhao, Zhe Wang, Min Wu, Weisi Lin

A popular track of network compression approach is Quantization aware Training (QAT), which accelerates the forward pass during the neural network training and inference.


Exploring Opinion-unaware Video Quality Assessment with Semantic Affinity Criterion

2 code implementations26 Feb 2023 HaoNing Wu, Liang Liao, Jingwen Hou, Chaofeng Chen, Erli Zhang, Annan Wang, Wenxiu Sun, Qiong Yan, Weisi Lin

Recent learning-based video quality assessment (VQA) algorithms are expensive to implement due to the cost of data collection of human quality opinions, and are less robust across various scenarios due to the biases of these opinions.

Video Quality Assessment Visual Question Answering (VQA)

JND-Based Perceptual Optimization For Learned Image Compression

no code implementations25 Feb 2023 Feng Ding, Jian Jin, Lili Meng, Weisi Lin

After combining them together, we can better assign the distortion in the compressed image with the guidance of JND to preserve the high perceptual quality.

Image Compression MS-SSIM +2

Lightweight Salient Object Detection in Optical Remote-Sensing Images via Semantic Matching and Edge Alignment

1 code implementation7 Jan 2023 Gongyang Li, Zhi Liu, Xinpeng Zhang, Weisi Lin

Then, semantic kernels are used to activate salient object locations in two groups of high-level features through dynamic convolution operations in DSMM.

object-detection Object Detection +1

Bridging Component Learning with Degradation Modelling for Blind Image Super-Resolution

1 code implementation3 Dec 2022 Yixuan Wu, Feng Li, Huihui Bai, Weisi Lin, Runmin Cong, Yao Zhao

In this paper, we analyze the degradation of a high-resolution (HR) image from image intrinsic components according to a degradation-based formulation model.

Image Super-Resolution

IntegratedPIFu: Integrated Pixel Aligned Implicit Function for Single-view Human Reconstruction

1 code implementation15 Nov 2022 Kennard Yanting Chan, Guosheng Lin, Haiyu Zhao, Weisi Lin

We propose IntegratedPIFu, a new pixel aligned implicit model that builds on the foundation set by PIFuHD.

Human Parsing

Neighbourhood Representative Sampling for Efficient End-to-end Video Quality Assessment

4 code implementations11 Oct 2022 HaoNing Wu, Chaofeng Chen, Liang Liao, Jingwen Hou, Wenxiu Sun, Qiong Yan, Jinwei Gu, Weisi Lin

On the other hand, existing practices, such as resizing and cropping, will change the quality of original videos due to the loss of details and contents, and are therefore harmful to quality assessment.

Ranked #2 on Video Quality Assessment on KoNViD-1k (using extra training data)

Video Quality Assessment Visual Question Answering (VQA)

Blind Quality Assessment of 3D Dense Point Clouds with Structure Guided Resampling

no code implementations31 Aug 2022 Wei Zhou, Qi Yang, Qiuping Jiang, Guangtao Zhai, Weisi Lin

Objective quality assessment of 3D point clouds is essential for the development of immersive multimedia systems in real-world applications.

HVS-Inspired Signal Degradation Network for Just Noticeable Difference Estimation

1 code implementation16 Aug 2022 Jian Jin, Yuan Xue, Xingxing Zhang, Lili Meng, Yao Zhao, Weisi Lin

However, they have a major drawback that the generated JND is assessed in the real-world signal domain instead of in the perceptual domain in the human brain.

Exploring the Effectiveness of Video Perceptual Representation in Blind Video Quality Assessment

1 code implementation8 Jul 2022 Liang Liao, Kangmin Xu, HaoNing Wu, Chaofeng Chen, Wenxiu Sun, Qiong Yan, Weisi Lin

Experiments show that the perceptual representation in the HVS is an effective way of predicting subjective temporal quality, and thus TPQI can, for the first time, achieve comparable performance to the spatial quality metric and be even more effective in assessing videos with large temporal variations.

Video Quality Assessment Visual Question Answering (VQA)

FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Sampling

4 code implementations6 Jul 2022 HaoNing Wu, Chaofeng Chen, Jingwen Hou, Liang Liao, Annan Wang, Wenxiu Sun, Qiong Yan, Weisi Lin

Consisting of fragments and FANet, the proposed FrAgment Sample Transformer for VQA (FAST-VQA) enables efficient end-to-end deep VQA and learns effective video-quality-related representations.

Video Quality Assessment

DisCoVQA: Temporal Distortion-Content Transformers for Video Quality Assessment

1 code implementation20 Jun 2022 HaoNing Wu, Chaofeng Chen, Liang Liao, Jingwen Hou, Wenxiu Sun, Qiong Yan, Weisi Lin

Based on prominent time-series modeling ability of transformers, we propose a novel and effective transformer-based VQA method to tackle these two issues.

Time Series Analysis Video Quality Assessment +1

Minimum Noticeable Difference based Adversarial Privacy Preserving Image Generation

no code implementations17 Jun 2022 Wen Sun, Jian Jin, Weisi Lin

To achieve this, an adversarial loss is firstly proposed to make the deep learning models attacked by the adversarial images successfully.

Face Recognition Image Classification +3

Distilling Knowledge from Object Classification to Aesthetics Assessment

no code implementations2 Jun 2022 Jingwen Hou, Henghui Ding, Weisi Lin, Weide Liu, Yuming Fang

To deal with this dilemma, we propose to distill knowledge on semantic patterns for a vast variety of image contents from multiple pre-trained object classification (POC) models to an IAA model.


SelfReformer: Self-Refined Network with Transformer for Salient Object Detection

1 code implementation23 May 2022 Yi Ke Yun, Weisi Lin

The global and local contexts significantly contribute to the integrity of predictions in Salient Object Detection (SOD).

object-detection Object Detection +2

Automatic Facial Skin Feature Detection for Everyone

no code implementations30 Mar 2022 Qian Zheng, Ankur Purwar, Heng Zhao, Guang Liang Lim, Ling Li, Debasish Behera, Qian Wang, Min Tan, Rizhao Cai, Jennifer Werner, Dennis Sng, Maurice van Steensel, Weisi Lin, Alex C Kot

We present an automatic facial skin feature detection method that works across a variety of skin tones and age groups for selfies in the wild.

Product Recommendation

Adjacent Context Coordination Network for Salient Object Detection in Optical Remote Sensing Images

1 code implementation25 Mar 2022 Gongyang Li, Zhi Liu, Dan Zeng, Weisi Lin, Haibin Ling

As the key component of ACCoNet, ACCoM activates the salient regions of output features of the encoder and transmits them to the decoder.

object-detection Object Detection +1

Full RGB Just Noticeable Difference (JND) Modelling

no code implementations1 Mar 2022 Jian Jin, Dong Yu, Weisi Lin, Lili Meng, Hao Wang, Huaxiang Zhang

Besides, the JND of the red and blue channels are larger than that of the green one according to the experimental results of the proposed model, which demonstrates that more changes can be tolerated in the red and blue channels, in line with the well-known fact that the human visual system is more sensitive to the green channel in comparison with the red and blue ones.

Image Quality Assessment

Lightweight Salient Object Detection in Optical Remote Sensing Images via Feature Correlation

1 code implementation20 Jan 2022 Gongyang Li, Zhi Liu, Zhen Bai, Weisi Lin, and Haibin Ling

Then, following the coarse-to-fine strategy, we generate an initial coarse saliency map from high-level semantic features in a Correlation Module (CorrM).

object-detection Object Detection +1

Auto-Weighted Layer Representation Based View Synthesis Distortion Estimation for 3-D Video Coding

no code implementations7 Jan 2022 Jian Jin, Xingxing Zhang, Lili Meng, Weisi Lin, Jie Liang, Huaxiang Zhang, Yao Zhao

Experimental results show that the VSD can be accurately estimated with the weights learnt by the nonlinear mapping function once its associated S-VSDs are available.

A New Image Codec Paradigm for Human and Machine Uses

no code implementations19 Dec 2021 Sien Chen, Jian Jin, Lili Meng, Weisi Lin, Zhuo Chen, Tsui-Shan Chang, Zhengguang Li, Huaxiang Zhang

Meanwhile, an image predictor is designed and trained to achieve the general-quality image reconstruction with the 16-bit gray-scale profile and signal features.

Decision Making Image Compression +7

Multi-Content Complementation Network for Salient Object Detection in Optical Remote Sensing Images

1 code implementation2 Dec 2021 Gongyang Li, Zhi Liu, Weisi Lin, Haibin Ling

In this paper, we propose a novel Multi-Content Complementation Network (MCCNet) to explore the complementarity of multiple content for RSI-SOD.

object-detection Object Detection +1

Towards Top-Down Just Noticeable Difference Estimation of Natural Images

1 code implementation11 Aug 2021 Qiuping Jiang, Zhentao Liu, Shiqi Wang, Feng Shao, Weisi Lin

Instead of explicitly formulating and fusing different masking effects in a bottom-up way, the proposed JND estimation model dedicates to first predicting a critical perceptual lossless (CPL) counterpart of the original image and then calculating the difference map between the original image and the predicted CPL image as the JND map.

Image Compression Image Reconstruction +1

Low Resolution Information Also Matters: Learning Multi-Resolution Representations for Person Re-Identification

no code implementations26 May 2021 Guoqing Zhang, Yuhao Chen, Weisi Lin, Arun Chandran, Xuan Jing

As a prevailing task in video surveillance and forensics field, person re-identification (re-ID) aims to match person images captured from non-overlapped cameras.

Person Re-Identification Super-Resolution

CMUA-Watermark: A Cross-Model Universal Adversarial Watermark for Combating Deepfakes

1 code implementation23 May 2021 Hao Huang, Yongtao Wang, Zhaoyu Chen, Yuze Zhang, Yuheng Li, Zhi Tang, Wei Chu, Jingdong Chen, Weisi Lin, Kai-Kuang Ma

Then, we design a two-level perturbation fusion strategy to alleviate the conflict between the adversarial watermarks generated by different facial images and models.

Adversarial Attack Face Swapping +1

Voxel Structure-based Mesh Reconstruction from a 3D Point Cloud

1 code implementation21 Apr 2021 Chenlei Lv, Weisi Lin, Baoquan Zhao

Mesh reconstruction from a 3D point cloud is an important topic in the fields of computer graphic, computer vision, and multimedia analysis.

Advanced Geometry Surface Coding for Dynamic Point Cloud Compression

no code implementations11 Mar 2021 Jian Xiong, Hao Gao, Miaohui Wang, Hongliang Li, King Ngi Ngan, Weisi Lin

In video-based dynamic point cloud compression (V-PCC), 3D point clouds are projected onto 2D images for compressing with the existing video codecs.

Just Noticeable Difference for Deep Machine Vision

no code implementations16 Feb 2021 Jian Jin, Xingxing Zhang, Xin Fu, huan zhang, Weisi Lin, Jian Lou, Yao Zhao

Experimental results on image classification demonstrate that we successfully find the JND for deep machine vision.

Image Classification Neural Network Security +1

Collaborative Intelligence: Challenges and Opportunities

no code implementations13 Feb 2021 Ivan V. Bajić, Weisi Lin, Yonghong Tian

This paper presents an overview of the emerging area of collaborative intelligence (CI).

Feature Compression

Progressive Self-Guided Loss for Salient Object Detection

1 code implementation7 Jan 2021 Sheng Yang, Weisi Lin, Guosheng Lin, Qiuping Jiang, Zichuan Liu

We present a simple yet effective progressive self-guided loss function to facilitate deep learning-based salient object detection (SOD) in images.

object-detection Object Detection +1

Adversarial Exposure Attack on Diabetic Retinopathy Imagery

no code implementations19 Sep 2020 Yupeng Cheng, Felix Juefei-Xu, Qing Guo, Huazhu Fu, Xiaofei Xie, Shang-Wei Lin, Weisi Lin, Yang Liu

In this paper, we study this problem from the viewpoint of adversarial attack and identify a totally new task, i. e., adversarial exposure attack generating adversarial images by tuning image exposure to mislead the DNNs with significantly high transferability.

Adversarial Attack

Pasadena: Perceptually Aware and Stealthy Adversarial Denoise Attack

no code implementations14 Jul 2020 Yupeng Cheng, Qing Guo, Felix Juefei-Xu, Wei Feng, Shang-Wei Lin, Weisi Lin, Yang Liu

To this end, we initiate the very first attempt to study this problem from the perspective of adversarial attack and propose the adversarial denoise attack.

Adversarial Attack Common Sense Reasoning +2

GSTO: Gated Scale-Transfer Operation for Multi-Scale Feature Learning in Pixel Labeling

1 code implementation27 May 2020 Zhuoying Wang, Yongtao Wang, Zhi Tang, Yangyan Li, Ying Chen, Haibin Ling, Weisi Lin

Existing CNN-based methods for pixel labeling heavily depend on multi-scale features to meet the requirements of both semantic comprehension and detail preservation.

Pose Estimation Semantic Segmentation

Learning a No-Reference Quality Assessment Model of Enhanced Images With Big Data

no code implementations18 Apr 2019 Ke Gu, DaCheng Tao, Junfei Qiao, Weisi Lin

Given an image, our quality measure first extracts 17 features through analysis of contrast, sharpness, brightness and more, and then yields a measre of visual quality using a regression module, which is learned with big-data training samples that are much bigger than the size of relevant image datasets.

Image Enhancement Image Quality Assessment +2

A Dilated Inception Network for Visual Saliency Prediction

1 code implementation7 Apr 2019 Sheng Yang, Guosheng Lin, Qiuping Jiang, Weisi Lin

In this work, we proposed an end-to-end dilated inception network (DINet) for visual saliency prediction.

Saliency Prediction

Which Has Better Visual Quality: The Clear Blue Sky or a Blurry Animal?

1 code implementation IEEE Transactions on Multimedia 2018 Dingquan Li, Tingting Jiang, Weisi Lin, Ming Jiang

The proposed method, SFA, is compared with nine representative blur-specific NR-IQA methods, two general-purpose NR-IQA methods, and two extra full-reference IQA methods on Gaussian blur images (with and without Gaussian noise/JPEG compression) and realistic blur images from multiple databases, including LIVE, TID2008, TID2013, MLIVE1, MLIVE2, BID, and CLIVE.

Blind Image Quality Assessment Image Classification +2

Intermediate Deep Feature Compression: the Next Battlefield of Intelligent Sensing

no code implementations17 Sep 2018 Zhuo Chen, Weisi Lin, Shiqi Wang, Ling-Yu Duan, Alex C. Kot

The recent advances of hardware technology have made the intelligent analysis equipped at the front-end with deep learning more prevailing and practical.

Data Compression Feature Compression

Robustness Analysis of Pedestrian Detectors for Surveillance

1 code implementation12 Jul 2018 Yuming Fang, Guanqun Ding, Yuan Yuan, Weisi Lin, Haiwen Liu

In this study, we conduct the research on the robustness of pedestrian detection algorithms to video quality degradation.

Pedestrian Detection

Learning Markov Clustering Networks for Scene Text Detection

no code implementations CVPR 2018 Zichuan Liu, Guosheng Lin, Sheng Yang, Jiashi Feng, Weisi Lin, Wang Ling Goh

MCN predicts instance-level bounding boxes by firstly converting an image into a Stochastic Flow Graph (SFG) and then performing Markov Clustering on this graph.

Clustering Scene Text Detection +1

Review of Visual Saliency Detection with Comprehensive Information

no code implementations9 Mar 2018 Runmin Cong, Jianjun Lei, Huazhu Fu, Ming-Ming Cheng, Weisi Lin, Qingming Huang

With the acquisition technology development, more comprehensive information, such as depth cue, inter-image correspondence, or temporal relationship, is available to extend image saliency detection to RGBD saliency detection, co-saliency detection, or video saliency detection.

Co-Salient Object Detection Video Saliency Detection

An Iterative Co-Saliency Framework for RGBD Images

no code implementations4 Nov 2017 Runmin Cong, Jianjun Lei, Huazhu Fu, Weisi Lin, Qingming Huang, Xiaochun Cao, Chunping Hou

In this paper, we propose an iterative RGBD co-saliency framework, which utilizes the existing single saliency maps as the initialization, and generates the final RGBD cosaliency map by using a refinement-cycle model.

Co-Salient Object Detection

Image Quality Assessment Guided Deep Neural Networks Training

3 code implementations13 Aug 2017 Zhuo Chen, Weisi Lin, Shiqi Wang, Long Xu, Leida Li

For many computer vision problems, the deep neural networks are trained and validated based on the assumption that the input images are pristine (i. e., artifact-free).

Data Augmentation Image Classification +1

Cannot find the paper you are looking for? You can Submit a new open access paper.