theeighthday Goto Github PK

I'm ✨ Kaibin Tian ✨, an algorithm engineer at Kwai. Email📧 : [email protected].

💼 Experiences

• [2016-2020]🎉 I received my B.E. degree in Software Engineering at University of Electronic Science and Technology of China(UESTC).
• [2020-2023] I received my M.S. in Computer Science at AIMC Lab of Renmin University of China(RUC), advised by Prof. Xirong Li. I have been a Research Intern at SenseTime and Kuaishou Technology.
• [2023-] Now I'm working as a Algorithm Engineer at Kuaishou Technology.

🔭 Research Interests

• 📹 Video Understanding
• 🔍 Cross-Modal Retrieval
• 🔄 Domain Adaptation
• 🔥 Large Language Model
• 🤔 ...

🤺 Competitions

• Alibaba Tianchi: Detection of Tampered Images. Rank 16/1666(Top 1%).
• 2022 NIST TREC Video Retrieval Evaluation: Adhoc Video Search Task. Rank 2. Note.
• 2022 CVPR WorkShop Challenge: SemiSupervised Action Recognition In The Dark. Rank 2. Poster. Code.
• 2022 CVPR WorkShop Challenge：AICITY Naturalistic Driving Action Recognition. Rank 9. Note. Code.

📚 Papers

• Jie Wang, Kaibin Tian, Dayong Ding, Gang Yang and Xirong Li. Unsupervised Domain Expansion for Visual Categorization. In ACM Transactions on Multimedia Computing, Communications and Applications (TOMM)(CCF-B) 2021. Code.
• Kaibin Tian, Qijie Wei, Xirong Li. Co-Teaching for Unsupervised Domain Adaptation and Expansion. In arXiv 2022. Code.
• Aozhu Chen, Ziyuan Wang, Chengbo Dong, Kaibin Tian, Ruixiang Zhao, Xun Liang, Zhanhui Kang, Xirong Li. ChinaOpen: A Dataset for Open-world Multimodal Learning. In ACMMM(CCF-A) 2023. Code.
• Kaibin Tian, Ruixiang Zhao, Hu Hu, Runquan Xie, Fengzong Lian, Zhanhui Kang, Xirong Li. TeachCLIP: Multi-Grained Teaching for Efficient Text-to-Video Retrieval. In CVPR(CCF-A) 2024.
• Kaibin Tian, Yanhua Cheng, Yi Liu, Xinglin Hou, Quan Chen, Han Li. Towards Efficient and Effective Text-to-Video Retrieval with Coarse-to-Fine Visual Representation Learning. In AAAI(CCF-A) 2024. Code