期刊论文
[1] Haozhe Lin*, Jiangtao Gong*, Yu Wang*, Jinsong Zhang*, et al. AI System Facilitates People with Blindness and Low Vision in Interpreting and Experiencing Unfamiliar Environments. Nature npj AI, 2025.
[2] Xueyang Wang*, Xuecheng Chen*, Puhua Jiang*, Haozhe Lin*, et al. Group Interaction Field for Learning and Explaining Pedestrian Anticipation. Engineering, 2024.
[3] Haozhe Lin, Yushun Fan, Jia Zhang, et al. Toward Knowledge as a Service (KaaS): Predicting Popularity of Knowledge Services Leveraging Graph Neural Networks. IEEE Transactions on Services Computing, 2022.
[4] Ruyu Yan, Haozhe Lin, Yushun Fan, et al. Multi-modal Reciprocal Spatiotemporal Framework for Predicting Usage Trend of Knowledge Services. IEEE Transactions on Services Computing, 2022.
[5] Haozhe Lin, Yushun Fan, Jia Zhang, et al. MSP-RNN: Multi-step Piecewise Recurrent Neural Network for Predicting the Tendency of Services Invocation. IEEE Transactions on Services Computing, 2020.
会议论文：
[6] Haozhe Lin*, Chunyu Wei*, Li He*, et al. GigaTraj: Predicting Long-term Trajectories of Hundreds of Pedestrians in Gigapixel Complex Scenes. CVPR, 2024.
[7] Tao Ma*, Bing Bai*, Haozhe Lin*, et al. When Visual Grounding Meets Gigapixel-level Large-scale Scenes: Benchmark and Approach. CVPR, 2024.
[8] Wenxi Li, Yuchen Guo, Jilai Zheng, Haozhe Lin, et al. Bridging the gap between object detection in close-up and high-resolution wide shots. Computer Vision and Image Understanding, 2024.
[9] Wenxi Li*, Ruxin Zhang*, Haozhe Lin, et al. SaccadeDet: A Novel Dual-Stage Architecture for Rapid and Accurate Detection in Gigapixel Images, ECML PKDD, 2024.
[10] Wenxi Li*, Ruxin Zhang*, Haozhe Lin, et al. SaccadeMOT: Enhancing Object Detection and Tracking in Gigapixel Images via Scale-Aware Density Estimation. ECAI, 2024.
[11] Wenxi Li, Yuchen Guo, Jilai Zheng, Haozhe Lin, et al. SparseFormer: Detecting Objects in HRW Shots via Sparse Vision Transformer. ACM Multimedia, 2024.
[12] Haozhe Lin*, Zequn Chen*, Jinzhi Zhang*, et al. RealGraph: A Multiview Dataset for 4D Real-world Context Graph Generation. ICCV, 2023.
[13] Baowei Jiang*, Bing Bai*, Haozhe Lin*, et al. DartBlur: Privacy Preservation with Detection Artifacts Suppression. CVPR, 2023.
[14] Hao Wen, Jing Huang, Huili Cui, Haozhe Lin, et al. Crowd3D: Towards Hundreds of People Reconstruction from a Single Image. CVPR, 2023.
[15] Haozhe Lin*, Yushun Fan, Jia Zhang, et al. REST: Reciprocal Framework for Spatiotemporal-coupled Predictions. WWW, 2021.
[16] Ruyu Yan, Yushun Fan, Jia Zhang, Junqi Zhang, Haozhe Lin. Service Recommendation for Composition Creation based on Collaborative Attention Convolutional Network. IEEE ICWS, 2021.
[17] Chunyu Wei, Yushun Fan, Jia Zhang, Haozhe Lin. A-HSG Neural Attentive Service Recommendation based on High-order Social Graph. IEEE ICWS, 2021.
[18] Xing Wu, Yushun Fan, Jia Zhang, Haozhe Lin, Junqi Zhang. QF-RNN QI-Matrix Factorization Based RNN for Time-Aware Service Recommendation. IEEE SCC, 2019.
[19] Haozhe Lin, Yushun Fan, Jia Zhang, et al. PRNN: Piecewise Recurrent Neural Networks for Predicting the Tendency of Services Invocation. IEEE ICWS, 2018.
发明专利：
[1] 方璐，林浩哲. 复杂大场景跨模态元语义理解方法与系统.
[2] 方璐，陈泽群，林浩哲，张晋之. 多维光场复杂场景图智能生成方法与系统.
[3] 方璐，郭雨晨，林浩哲. 一种宽视场高分辨视频高效智能检测方法及系统.
[4] 方璐，郭雨晨，林浩哲. 一种基于自适应智能匹配的宽视场高分辨多对象检测方法.
[5] 方璐，董众，戴琼海，李晓飞，袁肖赟，林浩哲，等. 多模融合表情智能感知方法与系统.
[6] 方璐，郭雨晨，戴琼海，袁肖赟，林浩哲，等.一种针对十亿像素的像素块排列方法与系统.
[7] 方璐，董众，戴琼海，李晓飞，袁肖赟，林浩哲，等. 脑启发的表情感知神经网络模型获取方法及系统.
[8] 方璐，李晓飞，戴琼海，董众，袁肖赟，林浩哲，等. 感知驱动多对象检测方法、系统与装置.
[9] 袁肖赟，林浩哲，杨延栋，等. 一种基于图神经网络的电网故障检测方法及装置.
[10] 范玉顺，韦淳于，林浩哲. 一种实现服务推荐的方法、装置、计算机存储介质及终端.
[11] 范玉顺，闫茹钰，林浩哲. 知识服务预测方法、装置、设备及存储介质.
[12] 范玉顺，林浩哲. 网页点击量预测方法、装置、计算机设备及存储介质.
[13] 范玉顺，林浩哲. 网络流量时空预测方法、装置、计算机设备和存储介质.
