Scholar
Jianghang Lin
Google Scholar ID: hxZ-5AkAAAAJ
Xiamen University
Citations & Impact
Citations
197
H-index
5
i10-index
4
Publications
14
Co-authors
5
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Published 'Active Teacher for Semi-Supervised Object Detection' at CVPR 2022 (co-first author).
- Published 'Weakly Supervised Open-Vocabulary Object Detection' at AAAI 2024.
- Published 'Adaptive Selection based Referring Image Segmentation' at ACM MM 2024 (co-first author).
- Published 'GOI: Find 3D Gaussians of Interest with an Optimizable Open-vocabulary Semantic-space Hyperplane' at ACM MM 2024.
- Published 'EOV-Seg: Efficient Open-Vocabulary Panoptic Segmentation' at AAAI 2025 (co-first author).
- Published 'Exploring Semantic Consistency and Style Diversity for Domain Generalized Semantic Segmentation' at AAAI 2025 (co-first author).
- Published 'U-SAM: Upgrade Segment Anything Model With Semantic-Aware and Memory-Efficient' at ICASSP 2025.
- Published 'What You Perceive Is What You Conceive: A Cognition-Inspired Framework for Open Vocabulary Image Segmentation' at ACM MM 2025.
- Published 'Generate Aligned Anomaly: Region-Guided Few-Shot Anomaly Image-Mask Pair Synthesis for' at ACM MM 2025 (co-first author).
Research Experience
- May 2025 - Present: Research Intern, Medical multimodal large model of ByteDance Soaring Star Talent Program, ByteDance, Shanghai, China.
- Jan 2024 - May 2024: Research Intern, CATL, Ningde, China.
- Dec 2022 - May 2023: Research Intern, CATL, Ningde, China.
- Feb 2022 - Aug 2022: Research Intern under the supervision of Dr. Yunhang Shen, Tencent Youtu Lab, Shanghai, China.
- Jul 2020 - Aug 2020: Development Intern, Ruijie Networks, Fuzhou, China.
Background
- Research Interests: Computer Vision, Multimodal, and Machine Learning. Recently focused on Open Vocabulary Learning and Large Visual-Language Models.
