Selected Publications

(*equal contribution and co-first authors, †equal advising and co-last authors)

2025

ViT-RefineNet for Directional Signal Radio Map Reconstruction from Sparse Samples
L. Ye, T. Le, and Y. Huang
ACM International Conference on Advances in Geographic Information Systems (SIGSPATIAL), 2025. (Long)
Paper
FUSE-Traffic: Fusion of Unstructured and Structured data for Event-aware Traffic forecasting
C. Yu, X. Xie, Y. Huang, and C. Qiu
ACM International Conference on Advances in Geographic Information Systems (SIGSPATIAL), 2025. (Long)
Paper
EfficientLocNet: High-Performance and Lightweight Radio Source Localization with Multi-Scale Attention
T. Le, S. Yadav, X. Xie, C. Qiu, Y. Huang and X. Li
ACM International Conference on Advances in Geographic Information Systems (SIGSPATIAL), 2025. (Short)
Paper
PRVQL: Progressive Knowledge-guided Refinement for Robust Egocentric Visual Query Localization
B. Fan, Y. Feng, Y. Tian, J. Liang, Y. Lin, Y. Huang, and H. Fan
IEEE/CVF International Conference on Computer Vision (ICCV), 2025.
Paper   Code
GSOT3D: Towards Generic 3D Single Object Tracking in the Wild
Y. Jiao, Y. Li, J. Ding, Q. Yang, S. Fu, H. Fan†, and L. Zhang†
IEEE/CVF International Conference on Computer Vision (ICCV), 2025.
Paper   Code-Data
Attention to Trajectory: Trajectory-Aware Open-Vocabulary Tracking
Y. Li, Y. Jiao, D. Meng, H. Fan†, and L. Zhang†
IEEE/CVF International Conference on Computer Vision (ICCV), 2025.
Paper   Code
Edge-Aware Token Halting for Efficient and Accurate Medical Image Segmentation
Y. Guo, B. Song, H. Fan, and E. Cheng
International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2025.
Paper   Code
Efficient and Accurate Low-Resolution Transformer Tracking
S. Dong, Y. Feng, J. Liang, Q. Yang, Y. Lin, and H. Fan
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2025.
Paper   Code
G3CN: Gaussian Topology Refinement Gated Graph Convolutional Network for Skeleton-Based Action Recognition
H. Ren, Z. Luo, H. Fan, X. Yuan, G. Wang, and L. Zhang
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2025.
Paper   Code
High-Fidelity Image Inpainting with Multimodal Guided GAN Inversion
L. Zhang, Y. Yu, J. Yao, and H. Fan
International Journal of Computer Vision (IJCV), 133: 5788-5805, 2025.
Paper   Code
DAM: Dynamic Attention Mask for Long-Context Large Language Model Inference Acceleration
H. Zhang, H. Fan, K. Sha, Y. Huang, and Y. Feng
Annual Meeting of the Association for Computational Linguistics (ACL Findings), 2025.
Paper   Code
RoLocMe: A Robust Multi-agent Source Localization System with Learning-based Map Estimation
T. Le, L. Ye, and Y. Huang
International Joint Conference on Artificial Intelligence (IJCAI), 2025.
Paper
CorrBEV: Multi-View 3D Object Detection by Correlation Learning with Multi-modal Prototypes
Z. Xue, M. Guo, H. Fan, S. Zhang, and Z. Zhang
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.
Paper
LaMOT: Language-Guided Multi-Object Tracking
Y. Li*, X. Liu*, L. Liu, H. Fan†, and L. Zhang†
IEEE International Conference on Robotics and Automation (ICRA), 2025.
Paper   Code-Data
CGTrack: Cascade Gating Network with Hierarchical Feature Aggregation for UAV Tracking
W. Li, X. Liu, H. Fan†, and L. Zhang†
IEEE International Conference on Robotics and Automation (ICRA), 2025.
Paper   Code
The Devil is in the Quality: Exploring Informative Samples for Semi-Supervised Monocular 3D Object Detection
Z. Zhang, Z. Li, H. Wang, H. Yuan, K. Wang, and H. Fan
IEEE International Conference on Robotics and Automation (ICRA), 2025.
Paper
Knowing Your Target: Target-Aware Transformer Makes Better Spatio-Temporal Video Grounding
X. Gu, Y. Shen, C. Luo, T. Luo, Y. Huang, Y. Lin, H. Fan†, L. Zhang†
International Conference on Learning Representations (ICLR), 2025.
Oral presentation
Paper   Code
AttMOT: Improving Multiple-Object Tracking by Introducing Auxiliary Pedestrian Attributes
Y. Li, Z. Xiao, L. Yang, D. Meng, X. Zhou, H. Fan, and L. Zhang
IEEE Transactions on Neural Networks and Learning Systems (T-NNLS), 36(3): 5454-5468, 2025.
Paper   Code

2024

DAAP: Privacy-Preserving Model Accuracy Estimation on Unlabeled Datasets Through Distribution-Aware Adversarial Perturbation
G. Cao, Z. Wang, Y. Feng, and X. Dong.
The 33rd USENIX Security Symposium (USENIX Security), 2024.
Paper
VastTrack: Vast Category Visual Object Tracking
L. Peng*, J. Gao*, X. Liu*, W. Li*, S. Dong*, Z. Zhang, H. Fan†, and L. Zhang†
Advances in Neural Information Processing Systems (NeurIPS), 2024.
Paper   Poster   Code-Data
Optical Flow as Spatial-Temporal Attention Learners
Y. Lu, C. Han, Q. Wang, H. Fan, Z. Kong, D. Liu, and Y. Chen
IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 46(12): 11491-11506, 2024.
Paper
Cyclic Refiner: Object-Aware Temporal Representation Learning for Multi-View 3D Detection and Tracking
M. Guo, Z. Zhang, L. Jing, Y. He, K. Wang, and H. Fan
International Journal of Computer Vision (IJCV), 132: 6184–6206, 2024.
Paper
Beyond MOT: Semantic Multi-Object Tracking
Y. Li, Q. Li, H. Wang, X. Ma, J. Yao, S. Dong, H. Fan†, and L. Zhang†
European Conference on Computer Vision (ECCV), 2024.
Paper   Code-Data
Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance
L. Lin, H. Fan, Z. Zhang, Y. Wang, Y. Xu, and H. Ling
European Conference on Computer Vision (ECCV), 2024.
Paper   Code
Efficient Multimodal Semantic Segmentation via Dual-Prompt Learning
S. Dong, Y. Feng, Q. Yang, Y. Huang, D. Liu, and H. Fan
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024.
Oral presentation
Paper   Code
SiCP: Simultaneous Individual and Cooperative Perception for 3D Object Detection in Connected and Automated Vehicles
D. Qu, Q. Chen, T. Bai, A. Qin, H. Lu, H. Fan, S. Fu, and Q. Yang
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024.
Oral presentation
Paper   Code
Robust Domain Adaptive Object Detection with Unified Multi-Granularity Alignment
L. Zhang, W. Zhou, H. Fan‡, T. Luo, and H. Ling (‡corresponding author)
IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 46(12): 9161-9178, 2024.
Paper   Code
Divert More Attention to Vision-Language Object Tracking
M. Guo, Z. Zhang, L. Jing, H. Ling, and H. Fan
IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 46(12): 8600-8618, 2024.
Paper   Code
Context-Guided Spatio-Temporal Video Grounding
X. Gu*, H. Fan*, Y. Huang, T. Luo, and L. Zhang
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
Paper   Poster   Code
ProMotion: Prototypes As Motion Learners
Y. Lu, D. Liu, Q. Wang, C. Han, Y. Cui, Z. Cao, X. Zhang, Y. Chen, and H. Fan
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
Paper
Kernel Adaptive Convolution for Scene Text Detection via Distance Map Prediction
J. Zheng, H. Fan, and L. Zhang
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
Paper
CereSZ: Enabling and Scaling Error-bounded Lossy Compression on Cerebras CS-2
S. Song, Y. Huang, P. Jiang, X. Yu, W. Zheng, S. Di, Q. Cao, Y. Feng, Z. Xie, and F. Cappello
ACM International Symposium on High-Performance Parallel and Distributed Computing (HPDC), 2024.
Paper
MaGIC: Multi-modality Guided Image Completion
H. Wang*, Y. Yu*, T. Luo, H. Fan, and L. Zhang
International Conference on Learning Representations (ICLR), 2024.
Paper   Code
Local Compressed Video Stream Learning for Generic Event Boundary Detection
L. Zhang, X. Gu, C. Li, T. Luo, and H. Fan
International Journal of Computer Vision (IJCV), 132: 1187-1204, 2024.
Paper   Code
PreciseDebias: An Automatic Prompt Engineering Approach for Generative AI to Mitigate Image Demographic Biases
C. Clemmer, J. Ding, and Y. Feng.
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024.
Paper   Code
SSPNet: Scale and Spatial Priors Guided Generalizable and Interpretable Pedestrian Attribute Recognition
J. Shen, T. Guo, X. Zuo, H. Fan, and W. Yang
Pattern Recognition (PR), 148: 110194, 2024.
Paper
ICAFusion: Iterative Cross-Attention Guided Feature Fusion for Multispectral Object Detection
J. Shen, Y. Chen, Y. Liu, X. Zuo, H. Fan, and W. Yang
Pattern Recognition (PR), 145: 109913, 2024.
Paper   Code
Task-Free Fairness-Aware Bias Mitigation for Black-Box Deployed Models
G. Cao, Z. Wang, Y. Feng, X. Dong, Z. Zhang, Z. Qin, and K. Ren
IEEE Transactions on Dependable and Secure Computing (TDSC), 21: 3390-3405, 2024.
Paper  
Evidential Mixture Machines: Deciphering Multi-Label Correlations for Active Learning Sensitivity
D Yu, M Li, W Shi, Q Yu
Advances in Neural Information Processing Systems (NeurIPS), 37: 112217-112236, 2024.
Paper  
Balancing Explanations and Adaptation in Offline Continual Learning Systems Using Active Augmented Reply
MA Al Forhad, W Shi
IEEE 7th International Conference on Multimedia Information Processing and Retrieval (MIPR), 484-490, 2024.
Paper  
Unveiling statistical significance of online regression over multiple datasets
M Abu-Shaira, W Shi
IEEE 7th International Conference on Multimedia Information Processing and Retrieval (MIPR), 274-279, 2024.
Paper  
Macro-AUC-Driven Active Learning Strategy for Multi-Label Classification Enhancement
M Li, J Qiu, W Shi
IEEE 7th International Conference on Multimedia Information Processing and Retrieval (MIPR), 280-286, 2024.
Paper  

2023

A Multi-granularity Decade-Long Geo-Tagged Twitter Dataset for Spatial Computing
Y. Feng, Z. Meng, C. Clemmer, H. Fan, and Y. Huang
ACM International Conference on Advances in Geographic Information Systems (SIGSPATIAL), 2023.
Paper   Data
PIDray: A Large-scale X-ray Benchmark for Real-World Prohibited Item Detection
L. Zhang, L. Jiang, R. Ji, and H. Fan
International Journal of Computer Vision (IJCV), 131: 3170-3192, 2023.
Paper   Code-Data
Towards Transferable Targeted Adversarial Examples
Z. Wang, H. Yang, Y. Feng, P. Sun, H. Guo, Z. Zhang, and K. Ren
onference on Computer Vision and Pattern (CVPR), 2023.
Paper  
Addressing Weak Decision Boundaries in Image Classification by Leveraging Web Search and Generative Models
P. Dammu, Y. Feng and C. Shah
International Joint Conference on Artificial Intelligence (IJCAI), 2023.
Paper  
Collaborative Three-Stream Transformers for Video Captioning
H. Wang, L. Zhang, H. Fan, and T. Luo
Computer Vision and Image Understanding (CVIU), 235: 103799, 2023.
Paper   Code
Unsupervised Domain Adaptive Detection with Network Stability Analysis
W. Zhou*, H. Fan*, T. Luo, and L. Zhang
IEEE/CVF International Conference on Computer Vision (ICCV), 2023.
Paper   Code
Two Birds, One Stone: A Unified Framework for Joint Learning of Image and Video Style Transfers
B. Gu, H. Fan, and L. Zhang
IEEE/CVF International Conference on Computer Vision (ICCV), 2023.
Paper   Code
Accurate and Fast Compressed Video Captioning
Y. Shen, X. Gu, K. Xu, H. Fan, L. Wen, and L. Zhang
IEEE/CVF International Conference on Computer Vision (ICCV), 2023.
Paper   Code
PlanarTrack: A Large-scale Challenging Benchmark for Planar Object Tracking
X. Liu*, X. Liu*, Z. Yi*, X. Zhou*, T. Le, L. Zhang, Y. Huang, Q. Yang, and H. Fan
IEEE/CVF International Conference on Computer Vision (ICCV), 2023.
Paper   Code
Towards Fairness-aware Adversarial Network Pruning
L. Zhang, Z. Wang, X. Dong, Y. Feng, X. Pang, Z. Zhang, and K. Ren
IEEE/CVF International Conference on Computer Vision (ICCV), 2023.
Paper  
AnimalTrack: A Benchmark for Multi-Animal Tracking in the Wild
L. Zhang*, J. Gao*, Z. Xiao, and H. Fan
International Journal of Computer Vision (IJCV), 131: 496-513, 2023.
Paper   Code
FZ-GPU: A Fast and High-Ratio Lossy Compressor for Scientific Computing Applications on GPUs
B. Zhang, J. Tian, S. Di, X. Yu, Y. Feng, X. Liang, D. Tao, F. Cappello
ACM International Symposium on High-Performance Parallel and Distributed Computing (HPDC), 2023.
Paper  
Investigating Code Generation Performance of ChatGPT with Crowdsourcing Social Data
Y. Feng, S. Vanam, M. Cherukupally, W. Zheng, M. Qiu and H. Chen
47th IEEE Computer Software and Applications Conference (COMPSAC), 2023.
Best Track Paper Award
Paper   Data
All: Supporting experiential accessibility education and inclusive software development
W Shi, H Moses, Q Yu, S Malachowsky, DE Krutz
ACM Transactions on Software Engineering and Methodology (TOSEM),33:2 1-30, 2023.
Paper  
Actively testing your model while it learns: realizing label-efficient learning in practice
D Yu, W Shi, Q Yu
Advances in Neural Information Processing Systems (NeurIPS),36: 31404-31427, 2023.
Paper  
STARS: spatial-temporal active re-sampling for label-efficient learning from noisy annotations
D Yu, W Shi, Q Yu
Proceedings of the AAAI Conference on Artificial Intelligence (AAAI),37:9 10980-10988, 2023.
Paper  
Discover-then-rank unlabeled support vectors in the dual space for multi-class active learning
D Yu, W Shi
Fortieth International Conference on Machine Learning (pmlr), 2023.
Paper  

2022

SwinTrack: A Simple and Strong Baseline for Transformer Tracking
L. Lin*, H. Fan*, Z. Zhang, Y. Xu, and H. Ling
Advances in Neural Information Processing Systems (NeurIPS), 2022.
Paper   Code
Divert More Attention to Vision-Language Tracking
M. Guo*, Z. Zhang*, H. Fan, and L. Jing
Advances in Neural Information Processing Systems (NeurIPS), 2022.
Paper   Code
High-Fidelity Image Inpainting with GAN Inversion
Y. Yu, L. Zhang, H. Fan, and T. Luo
European Conference on Computer Vision (ECCV), 2022.
Paper
Towards Bridging the Distribution Gap: Instance to Prototype Earth Mover’s Distance for Distribution Alignment
Q. Zhou, R. Wang, G. Zeng, H. Fan, and G. Zheng
Medical Image Analysis (MedIA), 82: 102607, 2022.
Paper
Detection and Tracking Meet Drones Challenge
P. Zhu, L. Wen, D. Du, X. Bian, H. Fan, Q. Hu, and H. Ling
IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 44(11): 7380-7399, 2022.
Paper   Data
GL-GAN: Adaptive Global and Local Bilevel Optimization for Generative Adversarial Network
Y. Liu, H. Fan, X. Yuan, and J. Xiang
Pattern Recognition (PR), 123: 108375, 2022.
Paper
Learning Target-aware Representation for Visual Tracking via Informative Interactions
M. Guo, Z. Zhang, H. Fan, L. Jing, Y. Lyu, B. Li, and W. Hu
International Joint Conference on Artificial Intelligence (IJCAI), 2022.
Oral presentation
Paper   Code
Hierarchical bayesian multi-kernel learning for integrated classification and summarization of app reviews
M Alshangiti, W Shi, E Lima, X Liu, Q Yu
Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC), 558-569, 2022.
Paper

2021

Transparent Object Tracking Benchmark
H. Fan, H. Miththanthaya, Harshit, S. Rajan, X. Liu, Z. Zou, Y. Lin, and H. Ling
IEEE International Conference on Computer Vision (ICCV), 2021.
Paper   Code-Data
CRACT: Cascaded Regression-Align-Classification for Robust Visual Tracking
H. Fan and H. Ling
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021.
Paper   Project