| 2026 | ICPR | Eliminating Object Hallucination in MLLMs via Convex Potential Flow Intervention. | Ziqiang Shi, Rujie Liu, Shanshan Yu, Koichi Shirahata |
| 2026 | WACV | Scalpel: Fine-Grained Alignment of Attention Activation Manifolds via Mixture Gaussian Bridges to Mitigate Multimodal Hallucination. | Ziqiang Shi, Rujie Liu, Shanshan Yu, Satoshi Munakata, Koichi Shirahata |
| 2025 | ICASSP | Attribute Conditional Diffusion-Augmented Person Re-Identification. | Shijie Nie, Ziqiang Shi, Rujie Liu, Song Guo, Meng Zhang, Mengjiao Wang, Kazuki Osamura, Lina Septiana, Narishige Abe |
| 2025 | SMC | Selective-SAM: Memory Optimization for Segment Anything Model 2 with Application in Self-Checkout Product Counting. | Zhongling Liu, Liu Liu, Ziqiang Shi, Rujie Liu, Jun Takahashi, Shan Jiang |
| 2025 | SMC | AugCount: Test-Time Semantic Augmentation via Diffusion for General Open-World Object Counting. | Ziqiang Shi, Rujie Liu, Jun Takahashi, Shan Jiang |
| 2025 | WACV | Bayesian Optimal Latent Projection for Noisy Image Restoration. | Ziqiang Shi, Rujie Liu, Jun Takahashi, Takuma Yamamoto |
| 2024 | ICASSP | Noisy Image Restoration Based on Conditional Acceleration Score Approximation. | Ziqiang Shi, Rujie Liu |
| 2024 | ICASSP | Langwave: Realistic Voice Generation Based on High-Order Langevin Dynamics. | Ziqiang Shi, Rujie Liu |
| 2024 | ICIP | Project, Skate, and Refresh: Improved Schrdinger Bridge Sampler for Image Restoration. | Ziqiang Shi, Rujie Liu |
| 2024 | SMC | Self-Checkout Product Detection with Occlusion Layer Prediction and Intersection Weighting. | Zhongling Liu, Ziqiang Shi, Rujie Liu, Liu Liu, Takuma Yamamoto, Daisuke Uchida |
| 2024 | WACV | Conditional Velocity Score Estimation for Image Restoration. | Ziqiang Shi, Rujie Liu |
| 2023 | CVPR | CheckSORT: Refined Synthetic Data Combination and Optimized SORT for Automatic Retail Checkout. | Ziqiang Shi, Zhongling Liu, Liu Liu, Rujie Liu, Takuma Yamamoto, Xiaoyu Mi, Daisuke Uchida |
| 2023 | ICASSP | Semi-Supervised Contrastive Learning with Soft Mask Attention for Facial Action Unit Detection. | Zhongling Liu, Rujie Liu, Ziqiang Shi, Liu Liu, Xiaoyu Mi, Kentaro Murase |
| 2022 | ICASSP | ItWave: It Stochastic Differential Equation is all You Need for Wave Generation. | Shoule Wu, Ziqiang Shi |
| 2020 | Interspeech | Speech Separation Based on Multi-Stage Elaborated Dual-Path Deep BiLSTM with Auxiliary Identity Loss. | Ziqiang Shi, Rujie Liu, Jiqing Han |
| 2020 | Interspeech | ATReSN-Net: Capturing Attentive Temporal Relations in Semantic Neighborhood for Acoustic Scene Classification. | Liwen Zhang, Jiqing Han, Ziqiang Shi |
| 2020 | MMM | FurcaNeXt: End-to-End Monaural Speech Separation with Dynamic Gated Dilated Temporal Convolutional Networks. | Liwen Zhang, Ziqiang Shi, Jiqing Han, Anyan Shi, Ding Ma |
| 2019 | ICASSP | Furcax: End-to-end Monaural Speech Separation Based on Deep Gated (De)convolutional Neural Networks with Adversarial Example Training. | Ziqiang Shi, Huibin Lin, Liu Liu, Rujie Liu, Shoji Hayakawa, Jiqing Han |
| 2019 | ICMLA | Robustness Evaluation of Deep Learning Models Based on Local Prediction Consistency. | Ziqiang Shi, Chaoliang Zhong, Yasuto Yokota, Wensheng Xia, Jun Sun |
| 2019 | Interspeech | End-to-End Monaural Speech Separation with Multi-Scale Dynamic Weighted Gated Dilated Convolutional Pyramid Network. | Ziqiang Shi, Huibin Lin, Liu Liu, Rujie Liu, Shoji Hayakawa, Shouji Harada, Jiqing Han |
| 2019 | Interspeech | Deep Attention Gated Dilated Temporal Convolutional Networks with Intra-Parallel Convolutional Modules for End-to-End Monaural Speech Separation. | Ziqiang Shi, Huibin Lin, Liu Liu, Rujie Liu, Jiqing Han, Anyan Shi |
| 2018 | Interspeech | Double Joint Bayesian Modeling of DNN Local I-Vector for Text Dependent Speaker Verification with Random Digit Strings. | Ziqiang Shi, Huibin Lin, Liu Liu, Rujie Liu |
| 2018 | Interspeech | Joint Learning of J-Vector Extractor and Joint Bayesian Model for Text Dependent Speaker Verification. | Ziqiang Shi, Liu Liu, Huibin Lin, Rujie Liu |
| 2018 | Interspeech | Latent Factor Analysis of Deep Bottleneck Features for Speaker Verification with Random Digit Strings. | Ziqiang Shi, Huibin Lin, Liu Liu, Rujie Liu |
| 2017 | ASRU | Multi-view (Joint) probability linear discrimination analysis for J-vector based text dependent speaker verification. | Ziqiang Shi, Liu Liu, Mengjiao Wang, Rujie Liu |
| 2017 | ICMLA | Better Worst-Case Complexity Analysis of the Block Coordinate Descent Method for Large Scale Machine Learning. | Ziqiang Shi, Rujie Liu |
| 2015 | PAKDD | Online and Stochastic Universal Gradient Methods for Minimizing Regularized Hlder Continuous Finite Sums in Machine Learning. | Ziqiang Shi, Rujie Liu |
| 2013 | IJCAI | Guarantees of Augmented Trace Norm Models in Tensor Recovery. | Ziqiang Shi, Jiqing Han, Tieran Zheng, Ji Li |
| 2012 | Interspeech | Low-rank Audio Signal Classification Under Soft Margin and Trace Norm Constraints. | Ziqiang Shi, Tieran Zheng, Jiqing Han, Shiwen Deng |
| 2011 | ICONIP | A Novel Framework Based on Trace Norm Minimization for Audio Event Detection. | Ziqiang Shi, Jiqing Han, Tieran Zheng |
| 2011 | Interspeech | Real-World Speech/Non-Speech Audio Classification Based on Sparse Representation Features and GPCs. | Ziqiang Shi, Jiqing Han, Tieran Zheng |