Bo-Lun Cai

Most-cited papers

DehazeNet: An End-to-End System for Single Image Haze Removal
Bo-Lun Cai, Xiang-Min Xu, K. Jia, C. Qing +1 more
2016IEEE Transactions on Image Processing3,174 citations Open access
Semantic Scholar
UP-DETR: Unsupervised Pre-training for Object Detection with Transformers
Zhigang Dai, Bo-Lun Cai, Yugeng Lin, Junying Chen
2020Computer Vision and Pattern Recognition585 citations
Semantic Scholar
A Joint Intrinsic-Extrinsic Prior Model for Retinex
Bo-Lun Cai, Xian-shun Xu, K. Guo, K. Jia +2 more
2017IEEE International Conference on Computer Vision270 citations
Semantic Scholar
Multi-scale convolutional neural networks for crowd counting
Lingke Zeng, Xiang-Min Xu, Bo-Lun Cai, Suo Qiu +1 more
2017International Conference on Information Photonics214 citations Open access
Semantic Scholar
FReLU: Flexible Rectified Linear Units for Improving Convolutional Neural Networks
Suo Qiu, Xiang-Min Xu, Bo-Lun Cai
2018International Conference on Pattern Recognition96 citations Open access
Semantic Scholar
Hierarchical Lifelong Learning by Sharing Representations and Integrating Hypothesis
Tong Zhang, Guoxi Su, C. Qing, Xiang-Min Xu +2 more
2019IEEE Transactions on Systems, Man & Cybernetics. Systems88 citations
Semantic Scholar
Spatiotemporal and frequential cascaded attention networks for speech emotion recognition
Shu-Zhen Li, Xiao-Fen Xing, Weiquan Fan, Bo-Lun Cai +2 more
2021Neurocomputing67 citations
Semantic Scholar
Multi-modality Depression Detection via Multi-scale Temporal Dilated CNNs
Weiquan Fan, Zhi-Wei He, Xiao-Fen Xing, Bo-Lun Cai +1 more
2019AVEC@MM59 citations
Semantic Scholar
BIT: Biologically Inspired Tracker
Bo-Lun Cai, Xiang-Min Xu, Xiao-Fen Xing, K. Jia +2 more
2016IEEE Transactions on Image Processing51 citations Open access
Semantic Scholar
ISNet: Individual Standardization Network for Speech Emotion Recognition
Weiquan Fan, Xiang-Min Xu, Bo-Lun Cai, Xiao-Fen Xing
2022IEEE/ACM Transactions on Audio Speech and Language Processing50 citations
Semantic Scholar
Edge/structure preserving smoothing via relativity-of-Gaussian
Bo-Lun Cai, Xiao-Fen Xing, Xiang-Min Xu
2017International Conference on Information Photonics43 citations
Semantic Scholar
Real-Time Video Dehazing Based on Spatio-Temporal MRF
Bo-Lun Cai, Xiang-Min Xu, D. Tao
2016Pacific Rim Conference on Multimedia37 citations
Semantic Scholar
Unsupervised Pre-Training for Detection Transformers
Zhigang Dai, Bo-Lun Cai, Yugeng Lin, Jun-Ying Chen
2020IEEE Transactions on Pattern Analysis and Machine Intelligence33 citations Open access
Semantic Scholar
Multi-modality Hierarchical Recall based on GBDTs for Bipolar Disorder Classification
Xiao-Fen Xing, Bo-Lun Cai, Yinhu Zhao, Shu-Zhen Li +2 more
2018AVEC@MM22 citations
Semantic Scholar
Perception Preserving Decolorization
Bo-Lun Cai, Xiang-Min Xu, Xiao-Fen Xing
2018International Conference on Information Photonics20 citations
Semantic Scholar
Listwise View Ranking for Image Cropping
Weirui Lu, Xiao-Fen Xing, Bo-Lun Cai, Xiang-Min Xu
2019IEEE Access19 citations Open access
Semantic Scholar
Image and video dehazing using view-based cluster segmentation
Feng Yu, C. Qing, Xiang-Min Xu, Bo-Lun Cai
2016Visual Communications and Image Processing19 citations
Semantic Scholar
MGAT: Multi-Granularity Attention Based Transformers for Multi-Modal Emotion Recognition
Weiquan Fan, Xiao-Fen Xing, Bo-Lun Cai, Xiang-Min Xu
2023IEEE International Conference on Acoustics, Speech, and Signal Processing18 citations
Semantic Scholar
Single Image Super-Resolution Using Multi-Scale Convolutional Neural Network
Xiao-Yi Jia, Xiang-Min Xu, Bo-Lun Cai, K. Guo
2017Pacific Rim Conference on Multimedia18 citations Open access
Semantic Scholar
CorrTalk: Correlation Between Hierarchical Speech and Facial Activity Variances for 3D Animation
Zhaojie Chu, K. Guo, Xiao-Fen Xing, Yilin Lan +2 more
2023IEEE transactions on circuits and systems for video technology (Print)16 citations Open access
Semantic Scholar
Flexible Rectified Linear Units for Improving Convolutional Neural Networks
Suo Qiu, Bo-Lun Cai
2017arXiv.org13 citations
Semantic Scholar
Reflective Learning With Label Noise
L. Wang, Xiang-Min Xu, K. Guo, Bo-Lun Cai +1 more
2023IEEE transactions on circuits and systems for video technology (Print)12 citations
Semantic Scholar
Center Contrastive Loss for Metric Learning
Bo-Lun Cai, Peng-Fei Xiong, Shangxuan Tian
2023arXiv.org11 citations Open access
Semantic Scholar
Attention-aware concentrated network for saliency prediction
Pengqian Li, Xiao-Fen Xing, Xiang-Min Xu, Bo-Lun Cai +1 more
2020Neurocomputing10 citations
Semantic Scholar
Multi-invariance appearance model for object tracking
G. Xu, Xiang-Min Xu, Xiao-Fen Xing, Bo-Lun Cai +1 more
2015International Conference on Digital Signal Processing8 citations
Semantic Scholar
Robust Emotion Navigation: Few-shot Visual Sentiment Analysis by Auxiliary Noisy Data
Lin Wang, Xiang-Min Xu, Fang Liu, Xiao-Fen Xing +2 more
20192019 8th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW)7 citations
Semantic Scholar
UniMoCo: Unsupervised, Semi-Supervised and Full-Supervised Visual Representation Learning
Zhigang Dai, Bo-Lun Cai, Yugeng Lin, Junying Chen
2021arXiv.org6 citations
Semantic Scholar
DCPTalk: Speech-Driven 3D Face Animation With Personalized Facial Dynamic Coupling Properties
Zhaojie Chu, K. Guo, Xiao-Fen Xing, Pengsheng Liu +2 more
2025IEEE transactions on multimedia5 citations
Semantic Scholar
Visual Sentiment Analysis with Noisy Labels by Reweighting Loss
K. Guo, Xiang-Min Xu, L. Wang, Bo-Lun Cai
2018IEEE International Conference on Systems, Man and Cybernetics5 citations
Semantic Scholar
Face Verification Based on Feature Transfer via PCA-SVM Framework
Xiao-Fen Xing, G. Xu, Bo-Lun Cai, C. Qing +1 more
20172017 IEEE International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData)5 citations
Semantic Scholar
UniMoCo: Unsupervised, Semi-Supervised and Fully-Supervised Visual Representation Learning
Zhigang Dai, Bo-Lun Cai, Junying Chen
2022IEEE International Conference on Systems, Man and Cybernetics4 citations
Semantic Scholar
Alleviating One-to-Many Mapping in Talking Head Synthesis With Dynamic Adaptation Context and Style Adapter
Zhaojie Chu, K. Guo, Xiao-Fen Xing, Bo-Lun Cai +2 more
2025IEEE transactions on circuits and systems for video technology (Print)3 citations
Semantic Scholar
Learning Adaptive Selection Network for Real-Time Visual Tracking
Jiang-Feng Xiong, Xiang-Min Xu, Bo-Lun Cai, Xiao-Fen Xing +1 more
2018IEEE International Conference on Multimedia and Expo3 citations
Semantic Scholar
Local-Global Extraction Unit for Person Re-identification
Peng Wang, C. Qing, Xiang-Min Xu, Bo-Lun Cai +2 more
2018International Conference on Advances in Brain Inspired Cognitive Systems2 citations
Semantic Scholar
BIT: Bio-inspired tracker
Bo-Lun Cai, Xiang-Min Xu, Xiao-Fen Xing, C. Qing
2015International Conference on Information Photonics2 citations
Semantic Scholar
EETalk: Expression Enhancement in Speech-Driven 3D Facial Animation
Zhaojie Chu, K. Guo, Xiao-Fen Xing, Bo-Lun Cai +2 more
2026IEEE transactions on multimedia1 citations
Semantic Scholar
Dense Deep Joint Image Filter for Upsampling and Denoising
Shu-Cong Yuan, C. Qing, Xiang-Min Xu, Bo-Lun Cai
2019IEEE Joint International Information Technology and Artificial Intelligence Conference1 citations
Semantic Scholar
Bio-inspired model with dual visual pathways for human action recognition
Bo-Lun Cai, Xiang-Min Xu, C. Qing
2014International Symposium on Communication Systems, Networks and Digital Signal Processing1 citations
Semantic Scholar
EMS-Mixer: Extreme Multi-Scale Mixing for Time Series Forecasting
Jia-Li Deng, Bo-Lun Cai, Yu-Qing Chen, Ying Hao +2 more
2026IEEE International Conference on Acoustics, Speech, and Signal Processing0 citations
Semantic Scholar
LOGIX: Local-Global Mixers for Time Series Representation Learning
Jia-Li Deng, Bo-Lun Cai, Yu-Qing Chen, Ying Hao +2 more
2026IEEE International Conference on Acoustics, Speech, and Signal Processing0 citations
Semantic Scholar
Prototype-Centered Residual Modeling for Federated Wireless Human Activity Recognition
Shu-Yu Luo, Bo-Lun Cai, Zhen-Quan Yu, Jia-Li Deng +2 more
2026IEEE Internet of Things Journal0 citations
Semantic Scholar
M3LLM: Temporal token modeling with LLMs for time series analysis
Jia-Li Deng, Bo-Lun Cai, Yu-Qing Chen, Yen-Cheng Liu +1 more
2026Neurocomputing0 citations
Semantic Scholar
Supplementary Material for Deep Dehazing Powered by Image Processing Network
Bo-Lun Cai, Xiangmin Xu, K. Jia, C. Qing +19 more
20230 citations
Semantic Scholar
Style Transfer at 100+ FPS Via Sub-Pixel Super-Resolution
Hao-Yu Li, Xiang-Min Xu, Bo-Lun Cai, K. Guo +1 more
20182018 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)0 citations
Semantic Scholar
Learning Reduced-Resolution and Super-Resolution Networks in Synch
Bo-Lun Cai, Xiang-Min Xu, K. Guo, K. Jia +1 more
2017arXiv.org0 citations
Semantic Scholar
Deep Sampling Networks
Bo-Lun Cai, Xiang-Min Xu, K. Guo, K. Jia +1 more
20170 citations
Semantic Scholar
Progressive Lifelong Learning by Sharing Representations for Few Labeled Data
Guoxi Su, Xiang-Min Xu, Chao-Yeh Chen, Bo-Lun Cai +1 more
2017International Conference on Internet Multimedia Computing and Service0 citations
Semantic Scholar
Joint Latent Space and Multi-view Feature Learning
K. Guo, Xiang-Min Xu, Bo-Lun Cai, T. Zhang
2017International Conference on Internet Multimedia Computing and Service0 citations
Semantic Scholar
Exploiting Local Feature Fusion for Action Recognition
Jie Miao, Xiang-Min Xu, Xiao-Yi Jia, Haoyu Huang +3 more
2016Pacific Rim Conference on Multimedia0 citations
Semantic Scholar
ビューに基づくクラスタ分割を用いた画像およびビデオぼけ除去【Powered by NICT】
Feng Yu, C. Qing, Xiang-Min Xu, Bo-Lun Cai
20160 citations
Semantic Scholar