Publications

Read Our Papers
2025

Unleashing the Potential of Hierarchical Region Clues for Open-Vocabulary Multi-Label Classification

Peirong Ma, Wu Ran, Zhiquan He, Jian Pu, and Hong Lu
IEEE Transactions on Multimedia
2025 October
Paper Code

MoME: Mixture of Multi-Domain Experts for Multivariate Long-Term Series Forecasting

Xinyu Li, Zhiheng Yang, Hao Xu, Yunqi Jiang, Hong Lu, Xin Wang, Jin Zhao, Fenglin Qi, and Jiajie Shen
IEEE International Conference on Acoustics, Speech and Signal Processing
2025 April
Paper Code
2024

Rainmer: Learning Multi-view Representations for Comprehensive Image Deraining and Beyond

Wu Ran, Peirong Ma, Zhiquan He, and Hong Lu
ACM International Conference on Multimedia
2024 October
Paper Code

Real-Time Attentive Dilated U-Net for Extremely Dark Image Enhancement

Junjian Huang, Hao Ren, Shulin Liu, Yong Liu, Chuanlu Lv, Jiawen Lu, Changyong Xie, and Hong Lu
ACM Transactions on Multimedia Computing, Communications, and Applications
2024 June
Paper Code

Feature decoupling and reorganization network for single image deraining

Yunrui Cheng, Junjian Huang, Hao Ren, Wu Ran, and Hong Lu
Multimedia Systems
2024 May
Paper Code

Harnessing Joint Rain-/Detail-Aware Representations to Eliminate Intricate Rains

Wu Ran, Peirong Ma, Zhiquan He, Hao Ren, and Hong Lu
International Conference on Learning Representations
2024 April
Paper Code

Buffered Gaussian Modeling For Vectorized HD Map Construction

Anqi Shi, Huaqiu Chen, Hong Lu, and Rui Zhang
IEEE International Conference on Acoustics, Speech and Signal Processing
2024 April
Paper Code

VPL-SLAM: A Vertical Line Supported Point Line Monocular SLAM System

Qi Chen, Yu Cao, Jaiwei Hou, Shoumeng Qiu, Bo Chen, Xiangyang Xue, Hong Lu, and Jian Pu
IEEE Transactions on Intelligent Transportation Systems
2024 March
Paper Code

Leveraging Smooth Deformation Augmentation for LiDAR Point Cloud Semantic Segmentation

Shoumeng Qiu, Jie Chen, Chenghan Lai, Hong Lu, Xiangyang Xue, and Jian Pu
IEEE Transactions on Intelligent Vehicles
2024 January
Paper Code
2023

Context-aware Coarse-to-fine Network for Single Image Desnowing

Yunrui Cheng, Hao Ren, Rui Zhang, and Hong Lu
Multimedia Tools and Applications
2023 December
Paper Code

Fully Unsupervised Domain-Agnostic Image Retrieval

Ziqiang Zheng, Hao Ren, Yang Wu, Weichuan Zhang, Hong Lu, Yang Yang, and Heng Tao Shen
IEEE Transactions on Circuits and Systems for Video Technology
2023 November
Paper Code

A Transferable Generative Framework for Multi-Label Zero-Shot Learning

Peirong Ma, Zhiquan He, Wu Ran, and Hong Lu
IEEE Transactions on Circuits and Systems for Video Technology
2023 October
Paper Code

Instance-Aware Diffusion Implicit Process for Box-Based Instance Segmentation

Hao Ren, Xingson Liu, Junjian Huang, Ru Wan, Jian Pu, and Hong Lu
European Conference on Artificial Intelligence
2023 October
Paper Code

Low-Light Image Enhancement with Multi-Scale Attention and Frequency-Domain Optimization

Zhiquan He, Wu Ran, Shulin Liu, Kehua Li, Jiawen Lu, Changyong Xie, Yong Liu, and Hong Lu
IEEE Transactions on Circuits and Systems for Video Technology
2023 September
Paper Code

Weakly-supervised Temporal Action Localization with Adaptive Clustering and Refining Network

Hao Ren, Wu Ran, Xingson Liu, Haoran Ren, Hong Lu, Rui Zhang, and Cheng Jin
IEEE International Conference on Multimedia and Expo
2023 July
Paper Code

GSFormer: Geometric-Spatial Transformer on Point Cloud Completion

Yijun Long, Zhaoyu Chen, Hong Lu, and Wenqiang Zhang
IEEE International Conference on Multimedia and Expo
2023 July
Paper Code

DaCo: Domain-Agnostic Contrastive Learning for Visual Place Recognition

Hao Ren, Ziqiang Zheng, Yang Wu, and Hong Lu
Applied Intelligence
2023 June
Paper Code

Weakly-Supervised Temporal Action Localization with Regional Similarity Consistency

Haoran Ren, Hao Ren, Hong Lu, and Cheng Jin
International Conference on Multimedia Modeling
2023 March
Paper Code

ACNet: Approaching-and-Centralizing Network for Zero-Shot Sketch-Based Image Retrieval

Hao Ren, Ziqiang Zheng, Yang Wu, Hong Lu, Yang Yang, Ying Shan, and Sai-Kit Yeung
IEEE Transactions on Circuits and Systems for Video Technology
2023 February
Paper Code

TRNR: Task-Driven Image Rain and Noise Removal with a Few Images Based on Patch Analysis

Wu Ran, Bohong Yang, Peirong Ma, and Hong Lu
IEEE Transactions on Image Processing
2023 January
Paper Code
2022

Weakly-supervised Temporal Action Localization with Multi-head Cross-modal Attention

Hao Ren, Haoran Ren, Wu Ran, Hong Lu, and Cheng Jin
Pacific Rim International Conference on Artificial Intelligence
2022 November
Paper Code

Compositional Coding Capsule Network with K-Means Routing for Text Classification

Hao Ren and Hong Lu
Pattern Recognition Letters
2022 August
Paper Code

Semantic-Related Feature Generation for Generalized Zero-Shot Learning

Peirong Ma, Wu Ran, and Hong Lu
IEEE International Conference on Multimedia and Expo
2022 July
Paper Code

Palpation Localization of Radial Artery Based on 3-Dimensional Convolutional Neural Networks

Qiliang Chen, Yulin Huang, Xing Zhu, Hong Lu, Zhongzhi Ji, Jiacheng Yang, and JingJing Luo
EURASIP Journal on Image and Video Processing
2022 July
Paper Code

Energy-Guided Feature Fusion for Zero-Shot Sketch-Based Image Retrieval

Hao Ren, Ziqiang Zheng, and Hong Lu
Neural Processing Letters
2022 May
Paper Code

RARN: A Real-Time Skeleton-based Action Recognition Network for Auxiliary Rehabilitation Therapy

Mengqi Shen and Hong Lu
IEEE International Symposium on Circuits and System
2022 May
Paper Code

SFCN: Spoon Fully Convolutional Networks for Pulse Localization

Bohong Yang, Kai Meng, Hong Lu, Xing Zhu, and Jingjing Luo
IEEE International Symposium on Circuits and System
2022 May
Paper Code

Hybrid Uncalibrated Near-light Photometric Stereo in Realistic Environment

Wu Ran, Xingsong Liu, Wang Feng, Hong Lu, Bohong Yang, Xing Zhu, and Jingjing Luo
IEEE International Symposium on Circuits and System
2022 May
Paper Code

GAN-MVAE: A Discriminative Latent Feature Generation Framework for Generalized Zero-shot Learning

Peirong Ma, Hong Lu, Bohong Yang, and Wu Ran
Pattern Recognition Letters
2022 March
Paper Code
2021

Multi-Classes and Motion Properties for Concurrent Visual-SLAM in Dynamics Environments

Bohong Yang, Wu Ran, Lin Wang, Hong Lu, and Yi-Ping Phoebe Chen
IEEE Transactions on Multimedia
2021 September
Paper Code

Multi-directional Convolution Networks with Spatial-temporal Feature Pyramid Module for Action Recognition

Bohong Yang, Zijian Wang, Wu Ran, Hong Lu, and Yi-Ping Phoebe Chen
IEEE International Conference on Acoustics, Speech and Signal Processing
2021 June
Paper Code

A Fast and Efficient Network for Single Image Deraining

Youzhao Yang and Hong Lu
IEEE International Conference on Acoustics, Speech and Signal Processing
2021 June
Paper Code

Pulse Localization Networks with Infrared Camera

Bohong Yang, Kai Meng, Hong Lu, Xinyao Nie, Guanhao Huang, Jingjing Luo, and Xing Zhu
ACM Multimedia Asia
2021 March
Paper Code
2020

Single Image Rain Removal Boosting via Directional Gradient

Wu Ran, Youzhao Yang, and Hong Lu
IEEE International Conference on Multimedia and Expo
2020 July
Paper Code

RDDAN: A Residual Dense Dilated Aggregated Network for Single Image Deraining

Youzhao Yang, Wu Ran, and Hong Lu
IEEE International Conference on Multimedia and Expo
2020 July
Paper Code

Learning the Game of Go by Scalable Network without Prior Knowledge of Komi

Bohong Yang, Lin Wang, Hong Lu, and Youzhao Yang
IEEE Transactions on Games
2020 May
Paper Code

Learning Cognitive Map Representations for Navigation by Sensory-motor Integration

Dongye Zhao, Zheng Zhang, Hong Lu, Sen Cheng, Bailu Si, and Xisheng Feng
IEEE Transactions on Cybernetics
2020 April
Paper Code

In-classroom Learning Analytics based on Student Behavior, Topic and Teching Characteristic Mining

Bohong Yang, Zeping Yao, Hong Lu, Yaqian Zhou, and Jinkai Xu
Pattern Recognitions Letters
2020 January
Paper Code
2019

L 0 Gradient Smoothing and Bimodal Histogram Analysis: A Robust Method for Sea-sky-line Detection

Jian Jiao, Hong Lu, Zijian Wang, Wenqiang Zhang and Lizhe Qi
ACM Multimedia Asia
2019 December
Paper Code

Single Image Deraining via Recurrent Hierarchy Enhancement Network

Youzhao Yang and Hong Lu
ACM International Conference on Multimedia
2019 October
Paper Code

A Survey on Natural Image Matting with Closed-Form Solutions

Xiaoqiang Li, Jide Li, and Hong Lu
IEEE Access
2019 September
Paper Code

Single Image Deraining using a Recurrent Multi-Scale Aggregation and Enhancement Network

Youzhao Yang and Hong Lu
IEEE International Conference on Multimedia and Expo
2019 July
Paper Code

Weakly Supervised Image Retrieval via Coarse-scale Feature Fusion and Multi-level Attention Blocks

Xinyao Nie, Hong Lu, Zijian Wang, Jingyuan Liu, and Zehua Guo
International Conference on Multimedia and Retrieval
2019 June
Paper Code

Accurate Targeting in Robot-assisted TCM Pulse Diagnosis using Adaptive Sensor Fusion

Jingjing Luo, Chun Ouyang, Xiaokai Nie, Wenjie Yin, Hong Lu, and Yuzhu Guo
International Conference on Communication, Management and Information Technology
2019 June
Paper Code
2018

Deep Fashion Analysis with Feature Map Upsampling and Landmark-driven Attention

Jingyuan Liu and Hong Lu
European Conference on Computer Vision Workshop
2018 September
Paper Code

Learning to Match using Siamese Network for Object Tracking

Chaopeng Li, Hong Lu, Jian Jiao, and Wenqiang Zhang
Pacific-Rim Conference on Multimedia
2018 September
Paper Code

Handwritten Chinese Character Recognition Based on Domain-Specific Knowledge

Qian Liu, Danqing Wang, Hong Lu, and Chaopeng Li
Pacific-Rim Conference on Multimedia
2018 September
Paper Code

A Novel Experience-based Exploration Method for Q-Learning

Bohong Yang, Hong Lu, Baogen Li, Zheng Zhang, and Wenqiang Zhang
International Conference of Pioneering Computer Scientists, Engineering and Educators
2018 September
Paper Code
2017

Automatic Facial Complexion Classification based on Mixture Model

Minjie Xu, Chunrong Guo, Yangyang Hu, Hong Lu, Xue Li, Fufeng Li, and Wenqiang Zhang
Pacific-Rim Conference on Multimedia
2017 September
Paper Code

Fast Circular Object Localization and Pose Estimation for Robotic Bin Picking

Linyao Luo, Yanfei Luo, Hong Lu, Haowei Yuan, Xuehua Tang, and Wenqiang Zhang
Pacific-Rim Conference on Multimedia
2017 September
Paper Code
2016

Leveraging Composition of Object Regions for Aesthetics Assessment of Photographs

Hong Lu, Zeping Yao, Yunhan Bai, Zhibin Zhu, Bohong Yang, Lukun Chen, and Wenqiang Zhang
Pacific-Rim Conference on Multimedia
2016 November
Paper Code

Robust Lip Segmentation Based on Complexion Mixture Models

Yangyang Hu, Hong Lu, Jinhua Cheng, Wenqiang Zhang, Fufeng Li, and Weifei Zhang
Pacific-Rim Conference on Multimedia
2016 November
Paper Code
2015

A FPGA Based High-speed Binocular Active Vision System for Tracking Circle-shaped Target

Zhengyang Du, Hong Lu, Haowei Yuan, Wenqiang Zhang, Chen Chen, and Kongye Xie
Pacific-Rim Conference on Multimedia
2015 September
Paper Code

Teaching Video Analytics Based on Student Spatial and Temporal Behavior Mining

Jinxian Qin, Yaqian Zhou, Hong Lu, and Heqing Ya
International Conference on Multimedia Retrieval
2015 June
Paper Code

A Novel Subpixel Curved Edge Localization Method

Zhengyang Du, Wenqiang Zhang, Jinxian Qin, Hong Lu, Zhong Chen, and Xidian Zheng
International Conference of Young Computer Scientists, Engineers and Educators
2015 January
Paper Code
2014

Leveraging Color Harmony and Spatial Context for Aesthetics Assessment of Photographs

Hong Lu, Jin Lin, Bohong Yang, Yiyi Chang, Yuefei　Guo, and Xiangyang Xue
Pacific-Rim Conference on Multimedia
2014 December
Paper Code

Lip Segmentation Based on Facial Complexion Template

Chenyang Sun, Hong Lu, Wenqiang Zhang, Xiaoxin Qiu, Fufeng Li, and Hongkai Zhang
Pacific-Rim Conference on Multimedia
2014 December
Paper Code

Intelligent Human Fall Detection for Home Surveillance

Hong Lu, Bohong Yang, Rui Zhao, Pengliang Qu, and Wenqiang Zhang
International Symposium on UbiCom Frontiers - Innovative Research, Systems and Technologies
2014 December
Paper Code

Vision Based Mapping and Localization in Unknown Environment for Intelligent Mobile Robot

Xiaoxin Qiu, Hong Lu, Wenqiang Zhang, Yunhan Bai, and Qianzhong Fu
International Symposium on UbiCom Frontiers - Innovative Research, Systems and Technologies
2014 December
Paper Code
2013

An Adaptive Query Prototype Modeling Method for Image Search Reranking

Hong Lu, Guobao Jiang, Bohong Yang, and Xiangyang Xue
IEEE International Conference on Computer Vision Workshop
2013 December
Paper Code

Basic Evaluation of Auditory Temporal Stability (BEATS): A Novel Rationale and Implementation

Zhuohong Cai, Robert J. Ellis, Zhiyan Duan, Hong Lu, and Ye Wang
International Society for Music Information Retrieval Conference
2013 November
Paper Code

A Segmentation and Graph-based Video Sequence Matching Method for Video Copy Detection

Hong Liu, Hong Lu, and Xiangyang Xue
IEEE Transactions on Knowledge and Data Engineering
2013 August
Paper Code
2012

Leveraging Exemplar and Saliency Model for Image Search Reranking

Hong Lu, Kai Chen, Guobao Jiang, Renzhong Wei, and Xiangyang Xue
Pacific-Rim Conference on Multimedia
2012 December
Paper Code

A Novel and Adaptive Method for Image Search Reranking

Hong Lu, Guobao Jiang, Zhuohong Cai, and Xiangyang Xue
International Forum of Digital TV & Wireless Multimedia Communication
2012 November
Paper Code

An Adaptive and Link-Based Method for Video Scene Clustering and Visualization

Hong Lu, Kai Chen, Yingbin Zheng, Zhuohong Cai, and Xiangyang Xue
Pacific-Rim Conference on Multimedia
2012 January
Paper Code
2011

Gradient Ordinal Signature and Fixed-point Embedding for Efficient Near-duplicate Video Detection

Hong Liu, Hong Lu, Zhaohui Wen, and Xiangyang Xue
IEEE Transactions on Circuits and Systems for Video Technology
2011 November
Paper Code

Level Influence of Spatial Pyramid Matching in Object Classification

Hong Lu, Renzhong Wei, Yanran Shen, and Xiangyang Xue
ACM International Conference on Multimedia
2011 November
Paper Code

Refining Local Descriptors by Embedding Semantic Information for Visual Categorization

Yingbin Zheng, Renzhong Wei, Hong Lu, and Xiangyang Xue
ACM International Conference on Multimedia
2011 November
Paper Code

Salient Object Detection using Concavity Context

Yao Lu, Wei Zhang, Hong Lu, and Xiangyang Xue
IEEE International Conference on Computer Vision
2011 November
Paper Code

Real-time, Adaptive, and Locality-Based Graph Partitioning Method for Video Scene Clustering

Hong Lu, Yap-Peng Tan, and Xiangyang Xue
IEEE Transactions on Circuits and Systems for Video Technology
2011 April
Paper Code
2010

Semantic Video Indexing by Fusing Explicit and Implicit Context Spaces

Yingbin Zheng, Renzhong Wei, Hong Lu, and Xiangyang Xue
ACM International Conference on Multimedia
2010 October
Paper Code

SVD-SIFT for Web Near-Duplicate Image Detection

Hong Liu, Hong Lu, and Xiangyang Xue
IEEE International Conference on Image Processing
2010 September
Paper Code

How Context Helps: A Discriminative Codeword Selection Method for Object Detection

Renzhong Wei, Hong Lu, Yingbin Zheng, Lei Cen, Cheng Jin, Xiangyang Xue, and Weiguo Wu
IEEE International Conference on Image Processing
2010 September
Paper Code

Optimization on Motion Estimation and DSP Algorithm Based on AVS Encoding

Ying Liu, Rui Zhang, Hong Lu, and Man Wang
Pacific-Rim Conference on Multimedia
2010 September
Paper Code

An Effective Method for Video Genre Classification

Jian-Feng Chen, Hong Lu, Renzhong Wei, Cheng Jin, and Xiangyang Xue
International Conference on Image and Video Retrieval
2010 July
Paper Code
2009

Incorporating Spatial Correlogram into Bag-of-Features Model for Scene Categorization

Yingbin Zheng, Hong Lu, Cheng Jin, and Xiangyang Xue
Asian Conference on Computer Vision
2009 September
Paper Code

Content and Context-Based Multi-Label Image Annotation

Hong Lu, Yingbin Zheng, Xiangyang Xue, and Yuejie Zhang
International Conference on Computer Vision and Pattern Recognition Workshop
2009 June
Paper Code
2008

Scene Segmentation Based on Video Structure and Spectral Methods

Zhenyuan Zhang, Bin Li, Hong Lu, and Xiangyang Xue
International Conference on Control, Automation, Robotics and Vision
2008 December
Paper Code

Detecting Interesting Regions in Photographs – How Metadata Can Help

Zhong Li, Hong Lu, Xiangyang Xue, and Jianping Fan
Pacific-Rim Conference on Multimedia
2008 December
Paper Code

Metric Learning by Discriminant Neighborhood Embedding

Wei Zhang, Xiangyang Xue, Zichen Sun, Hong Lu, and Yue-Fei Guo
Pattern recognition
2008 June
Paper Code

The Design of Video Segmentation-aided VCR Support for P2P VoD Systems

Xin Wang, Changyi Zheng, Zhenyuan Zhang, Hong Lu, and Xiangyang Xue
IEEE Transactions on Consumer Electronics
2008 May
Paper Code

Multilayer In-place Learning Networks for Modeling Functional Layers in the Laminar Cortex

Juyang Weng, Tianyu Luwang, Hong Lu, and Xiangyang Xue
Neural Networks
2008 January
Paper Code
2007

Local Dual Closed Loop Model and Trajectory Analysis based Bayesian Face Tracking

Dan Yao, Hong Lu, Xiangyang Xue, and Zhongyi Zhou
Pacific-Rim Conference on Multimedia
2007 December
Paper Code

Efficient Feature Extraction for Image Classification

Wei Zhang, Xiangyang Xue, Zichen Sun, Yuefei Guo, Mingmin Chi, and Hong Lu
IEEE International Conference on Computer Vision
2007 October
Paper Code

Semantic Information Extraction of Video Based on Ontology and Inference

Jie Ma, Jing Zhang, Hong Lu, and Xiangyang Xue
International Conference on Semantic Computing
2007 September
Paper Code

The Multilayer In-Place Learning Network for the Development of General Invariances and Multi-Task Learning

Juyang Weng, Tianyu Luwang, Hong Lu, and Xiangyang Xue
International Joint Conference on Neural Networks
2007 August
Paper Code

Optimal Dimensionality of Metric Space for Classification

Wei Zhang, Xiangyang Xue, Zichen Sun, Yuefei Guo, and Hong Lu
International Conference on Machine Learning
2007 June
Paper Code
2006

Hierarchical Indexing Structure for Efficient Similarity Search in Video Retrieval

Hong Lu, Beng Chin Ooi, Heng Tao Shen, and Xiangyang Xue
IEEE Transactions on Knowledge and Data Engineering
2006 November
Paper Code

Null Foley–Sammon Transform

Yue-Fei Guo, Lide Wu, Hong Lu, Zhe Feng, and Xiangyang Xue
Pattern Recognition
2006 November
Paper Code

Discriminant Neighborhood Embedding for Classification

Wei Zhang, Xiangyang Xue, Hong Lu, and Yuefei Guo
Pattern Recognition
2006 November
Paper Code
2005

An Effective Post-Refinement Method for Shot Boundary Detection

Hong Lu and Yap-Peng Tan
IEEE Transactions on Circuits and Systems for Video Technology
2005 October
Paper Code

Shot Boundary Classification by Temporal Pattern Discovery from Laplacian Eigenmap

Linjun Yang, Hong Lu, Bei Wang, Xiangyang Xue, and Yap-Peng Tan
IEEE Electronics Letters
2005 August
Paper Code

Enhanced Shot Boundary Detection Using Video Text Information

Liuhong Liang, Yang Liu, Hong Lu, Xiangyang Xue, and Yap-Peng Tan
IEEE Transactions on Consumer Electronics
2005 May
Paper Code

Effective Shot Boundary Classification Using Video Spatial-Temporal Information

Hong Lu, Bei Wang, Xiangyang Xue, and Yap-Peng Tan
IEEE International Symposium on Circuits and Systems
2005 May
Paper Code

Program Segmentation for TV Videos

Liuhong Liang, Hong Lu, Xiangyang Xue, and Yap-Peng Tan
IEEE International Symposium on Circuits and Systems
2005 May
Paper Code

Efficient Rate Control for MPEG-2 to H.264/AVC Transcoding

You-Neng Xiao, Hong Lu, Xiangyang Xue, Viet-Anh Nguyen, and Yap-Peng Tan
IEEE International Symposium on Circuits and Systems
2005 May
Paper Code
2004

Video Scene Segmentation Using Sequential Change Detection

Zhenyan Li, Hong Lu, and Yap-Peng Tan
Pacific-Rim Conference on Multimedia
2004 November
Paper Code

Shot Boundary Detection using Unsupervised Clustering and Hypothesis Testing

Hong Lu, Yap-Peng Tan, Xiangyang Xue, and Lide Wu
International Conference on Communications, Circuits, and Systems
2004 June
Paper Code

Video Segmentation Based on Sequential Change Detection

Zhenyan Li, Hong Lu, and Yap-Peng Tan
IEEE International Conference on Multimedia and Expo
2004 June
Paper Code

Model-based Video Scene Clustering with Noise Analysis

Hong Lu, Zhenyan Li, and Yap-Peng Tan
IEEE International Symposium on Circuits and Systems
2004 May
Paper Code
2003

Unsupervised Clustering of Dominant Scenes in Sports Video

Hong Lu and Yap-Peng Tan
Pattern Recognition Letters
2003 November
Paper Code

Modified Kolmogorov-Smirnov Metric for Shot Boundary Detection

Yap-Peng Tan, Jayaratchagan Nagamani, and Hong Lu
IEE Electronics Letters
2003 September
Paper Code

Video Scene Clustering by Graph Partitioning

Yap-Peng Tan and Hong Lu
IEE Electronics Letters
2003 May
Paper Code