曹毅超(Yichao Cao)，博士，特聘副教授，硕士生导师。在ICCV、NeurIPS、ICML、AAAI、ACMMM等高水平国际会议与期刊上发表论文20余篇，长期担任相关顶级会议和期刊的审稿人和程序委员会委员，授权专利10余项。研究方向包括：多模态大模型、计算机视觉、具身智能等，长期专注于多模态大模型微调、视觉感知与理解、具身机器人控制。企业任职期间，主持林草行业首个多模态大模型“林海思绪(ForestMind)”的研发，主持的“端-边-云协同林火识别引擎及一体化解决方案”获得国际先进成果评价，所主持研发的林火识别解决方案已成功应用于我国20多个省、60多个地市，大幅推动了林草行业智能化发展，建立了一批行业示范性项目，并参与起草了林草、应急行业的多项行业标准。

【代表性论文】

[1] Searching for Better Spatio-temporal Alignment in Few-Shot Action Recognition. Neural Information Processing Systems (NeurIPS, CCF A), 2022.

[2] Re-mine, Learn and Reason: Exploring the Cross-modal Semantic Correlations for Language-guided HOI detection. International Conference on Computer Vision (ICCV, CCF A), 2023

[3] Detecting Any Human-Object Interaction Relationship: Universal HOI Detector with Spatial Prompt Learning on Foundation Models. Advances in Neural Information Processing Systems (NeurIPS, CCF A), 2024

[4] EFFNet: Enhanced Feature Foreground Network for Video Smoke Source Prediction and Detection. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT, 中科院1区TOP), 2022

[5] SmokeAgent: Multimodal Agent for Fine-Grained Smoke Event Analysis in Large-Scale Wild Environments. Pattern Recognition (PR, 中科院1区TOP), 2025

[6] Perturbating, Tuning, and Collaborating: Harnessing Vision Foundation Models for Single Domain Generalization on Medical Imaging. AAAI Conference on Artificial Intelligence (AAAI, CCF A), 2025

[7] Universal Frequency Domain Perturbation for Single-Source Domain Generalization. ACM Multimedia (ACM MM, CCF A), 2024

[8] Coarse2Fine: Local Consistency Aware Re-prediction for Weakly Supervised Object Localization. AAAI Conference on Artificial Intelligence (AAAI, CCF A), 2023

[9] Attributes Grouping and Mining Hashing for Fine-Grained Image Retrieval.  ACM Multimedia (ACM MM, CCF A), 2023

[10] A Novel Image-Graph Heterogeneous Fusion Framework for Static IR Drop Prediction. Design Automation Conference (DAC, CCF A), 2025

[11] Combining the Convolution and Transformer for Classification of Smoke-Like Scenes in Remote Sensing Images. IEEE Transactions on Geoscience and Remote Sensing (IEEE TGRS, 中科院1区TOP), 2022

[12] Variational Feature Imitation Conditioned on Visual Descriptions for Few-Shot Fine-Grained Recognition. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT, 中科院1区TOP), 2025

[13] Debiased Prototype Evolving for Point Cloud Domain Adaptation via 3D Foundation Models. International Conference on Acoustics, Speech, and Signal Processing (ICASSP, CCF B), 2025

【联系方式】

caoyichao@csu.edu.cn