研究兴趣1：自动驾驶/智能驾驶/无人驾驶/自主智能/无人系统

   自动驾驶是一个典型的技术聚集体和应用辐射体。项目团队聚焦的研究问题包括：2D目标检测、2D目标分割、2D目标重要性预测；激光SLAM；车道线检测；3D目标检测、语义分割；3D目标轨迹预测；传统路径规划；智能体自主探索；多智能体路径规划等

研究兴趣2：具身智能/人机交互/人机共融/人机协同

  未来社会是人与机器高度融合、协作、共生的社会。项目团队聚焦的研究问题包括：视觉语言模型（VLM）、视觉语言导航（VLN）、语言行动模型（LA）、具身智能导航、多智能体任务协同等

 科研动态

•     [2026] 祝贺陆**（研二）的论文被深度学习、机器学习顶会 NIPS 2026接收！

•     [2026] 祝贺曾*（研三）的论文被多媒体顶刊TMM接收！
  

•     [2025] 祝贺李**获硕士生国家奖学金。

•     [2025] 祝贺李**（研二）的论文被计算机视觉顶会 CVPR 2025接收！该论文提出联合目标检测与实例分割模型MI-DETR，获得SOTA性能。GitHub链接：https://github.com/CQU-ADHRI-Lab/MI-DETR

•     [2024] 祝贺贾**（研二）的论文被图像处理顶刊T-IP 2024接收

•     [2024] 祝贺陈**获硕士生国家奖学金。

•     [2024] 祝贺李**（研二）的论文被深度学习、机器学习顶会 NIPS 2024接收！该论文提出联合目标检测与实例分割模型DI-MaskDINO，获得SOTA性能。 GitHub链接：https://github.com/CQU-ADHRI-Lab/DI-MaskDINO

•     [2024] 祝贺陈**（研三）的论文被深度学习、机器学习顶会 NIPS 2024接收！

•     [2023] 祝贺陈**（研一）的论文被计算机视觉顶会 ICCV 2023接收！
  

•     [2023] 祝贺向**（研一）的论文被机器人顶会IROS 2023接收！
  

代表性论文

[1] Zhixiong Nan, Haoyu Lu, Tao Xiang*, and Yiwei Wang. SCTI: Self-Calibrated Trident Identification of Black-Box LLM Watermarks. Neural Information Processing Systems(NeurIPS), 2026. (CCF-A)

[2] Zhixiong Nan, Hang Zeng, Tao Xiang∗, Fulin Luo, Hang Li, and Jindong Gu. FairGEN: Gender-Fair Video Generation with Adaptive Spatio-Temporal Inference Steering. IEEE Transactions on Multimedia (TMM), 2026. (CCF-A)

[3] Hongyang Pan, Tao Xiang, Zhixiong Nan*. Video Backdoor Attack on Deep Video Compression Models. IEEE Transactions on Multimedia (TMM), 2026. (CCF-A)

[4] Zhixiong Nan†, Wanying Xu†, Zhe Yang, Fulin Luo, Tao Xiang*. A Lane Detection Model with Knowledge Guided Anchor Feature Enhancement Mechanism.Pattern Recognition(PR), 2026. (1区)

[5] Zhe Yang , Kunyu Song , Bo Zheng , and Zhixiong Nan*. ADR-LIO: Adaptive Degradation-Resilient LiDAR-Inertial Odometry for Urban Environments. IEEE Transactions on Instrumentation and Measurement (T-IM), 2026.  (1区)

[6] Jiahao_Xu, Sheng Huang, Xin Zhang, Zhixiong Nan, Jiajun Dong, Nankun Mu. MUSE: Harnessing Precise and Diverse Semantics for Few-Shot Whole Slide Image Classification. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026. (CCF-A)

[7] Boyu Chang, Qi Wang, Xi Guo, Zhixiong Nan, Yazhou Yao, Tianfei Zhou. AbductiveMLLM: Boosting Visual Abductive Reasoning within MLLMs. AAAI Conference on Artificial Intelligence (AAAI), 2026. (CCF-A, Oral)

[8] Zijun Tan, Chuan Fu, Tan Guo, Zhixiong Nan, Pengzhan Zhou, Xinggan Peng, Fulin Luo. PGMamba: A Physical Model-Guided Global Mamba for Underwater Image Enhancement. AAAI Conference on Artificial Intelligence (AAAI), 2026. (CCF-A)

[9] Zijun Tan , Chuan Fu, Tan Guo, Zhixiong Nan, Tao Xiang, Fulin Luo*.Learning a physical model-guided global mamba for underwater image restoration.Pattern Recognition (PR),2026. (1区)

[10] Fulin Luo, Yan Guan , Chuan Fu, Tan Guo, Zhixiong Nan, Tao Xiang, Bo Du. SCFDet: Selective Cross-Modal Fusion Network for RGB-Infrared Object Detection in Remote Sensing.IEEE Transactions on Geoscience and Remote Sensing (TGRS),2026. (1区)

[11] Zhixiong Nan, Xianghong Li, Jifeng Dai, Tao Xiang. MI-DETR: An Object Detection Model with Multi-Time Inquiries Mechanism. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025. (CCF-A)

[12] Zhixiong Nan, Leiyu Jia, and Bin Xiao*. HEOI: Human Attention Prediction in Natural Daily Life with Fine-Grained Human-Environment-Object Interaction Model. IEEE Transactions on Image Processing(T-IP), 2025. (CCF-A)

[13] Zhixiong Nan, Junhong Xiang, Fulin Luo and Tao Xiang. Map-free Multi-agent Trajectory Prediction in Traffic Scenario. IEEE Transactions on Vehicular Technology, (T-VT), 2025. (1区)

[14] Zhixiong Nan, Yilong Chen, Tianfei Zhou, and Tao Xiang. On-Road Object Importance Estimation: A New Dataset and A Model with Multi-Fold Top-Down Guidance. Neural Information Processing Systems(NeurIPS), 2024. (CCF-A)

[15] Zhixiong Nan, Xianghong Li, Tao Xiang, and Jifeng Dai. DI-MaskDINO: A Joint Object Detection and Instance Segmentation Model. Neural Information Processing Systems(NeurIPS), 2024. (CCF-A)

[16] Tao Xiang, Hongyan Pan, Zhixiong Nan*. Video Violence Rating: A Large-scale Public Database and A Multimodal Rating Model. IEEE Transactions on Multimedia (TMM), 2024. (CCF-A)

[17] Fulin Luo, Yi Liu, Xiuwen Gong, Zhixiong Nan, Tan Guo. EMVCC: Enhanced Multi-View Contrastive Clustering for Hyperspectral Images. ACM Mulitimedia(ACM-MM), 2024. (CCF-A)

[18] Yilong Chen, Zhixiong Nan*, Tao Xiang. FBLNet: FeedBack Loop Networ for Driver Attention Prediction. IEEE/CVF International Conference on Computer Vision(ICCV), 2023. (CCF-A)

[19] Zhixiong Nan, Tao Xiang. Third-Person View Attention Prediction in Natural Scenarios with Weak Information Dependency and Human-Scene Interaction Mechanism. IEEE Transactions on Circuits and Systems for Video Technology(T-CSVT), 2023. (1区)

[20] Junhong Xiang†, Zhixiong Nan†*, Zhe Song†, Jun Huang and Lingxi Li. Map-free Trajectory Prediction in Traffic with Multi-level Spatial-temporal Modeling. IEEE Transactions on Intelligent Vehicle(T-IV), 2023. (1区)

[21] Zhixiong Nan, Jingjing Jiang, Xiaofeng Gao, Sanping Zhou, Weiliang Zuo, Ping Wei, Nanning Zheng*. Predicting Task-driven Attention via Integrating Bottom-up Stimulus and Top-down Guidance. IEEE Transactions on Image Processing(T-IP), 2021. (CCF A)

[22] Jingjing Jiang, Ziyi Liu, Yifan Liu, Zhixiong Nan, Nanning Zheng*. X-GGM: Graph Generative Modeling for Out-of-Distribution Generalization in Visual Question Answering. ACM Mulitimedia(ACM-MM), 2021. (CCF-A)

[23] Zhixiong Nan, Tianmin Shu, Ran Gong, Shu Wang, Ping Wei*, Song-Chun Zhu, Nanning Zheng. Learning to Infer Human Attention in Daily Activities. Pattern Recognition(PR), 2020. (1区)

[24] Zhixiong Nan†, Yang Liu†, Nanning Zheng, Song-Chun Zhu. Recognizing unseen attribute-object pair with generative model. AAAI Conference on Artificial Intelligence(AAAI), 2019. (#共同一作) (CCF-A)