Get started
Author

Guangming Lu

Observed name: Lu, Guangming
Observed institution: Harbin Institute of Technology
ORCID: 0000-0003-1578-2634
Observed ORCID: 0000-0003-1578-2634
OpenAlex ID: A5128868669
SA²VP: Spatially Aligned-and-Adapted Visual Prompt
2024 · Wenjie Pei, Tongqi Xia, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 20
PDF
QFormer: An Efficient Quaternion Transformer for Image Denoising
2024 · Bo Jiang, Yao Lu, et al. · International Joint Conference on Artificial Intelligence · 4
PDF
Prune Redundancy, Preserve Essence: Vision Token Compression in VLMs via Synergistic Importance-Diversity
2026 · Fang, Zhengyao, Lyu, Pengyuan, et al. · arXiv (Cornell University) · 2
PDF
D 2 ST-Adapter: Disentangled-and-Deformable Spatio-Temporal Adapter for Few-Shot Action Recognition
2025 · Wenjie Pei, Qizhong Tan, et al. · IEEE/CVF International Conference on Computer Vision (ICCV) · 2
STA-VPT: SpatioTemporally Aligned Visual Prompt Tuning
2023 · Pei, Wenjie, Xia, Tongqi, et al. · arXiv (Cornell University) · 1
PDF
RCoT-Seg: Reinforced Chain-of-Thought for Video Reasoning and Segmentation
2026 · Wen, Junwei, Miao, Deshui, et al. · arXiv (Cornell University)
PDF
MISA: Mixture of Indexer Sparse Attention for Long-Context LLM Inference
2026 · Zhou, Ruijie, Meng, Fanxu, et al. · arXiv (Cornell University)
PDF
Video-ToC: Video Tree-of-Cue Reasoning
2026 · Tan, Qizhong, Tian, Zhuotao, et al. · arXiv (Cornell University)
PDF
Too Vivid to Be Real? Benchmarking and Calibrating Generative Color Fidelity
2026 · Fang, Zhengyao, Jia, Zexi, et al. · arXiv (Cornell University)
PDF
Exploring the AI Obedience: Why is Generating a Pure Color Image Harder than CyberPunk?
2026 · Li, Hongyu, Liu, Kuan, et al. · arXiv (Cornell University)
PDF
Soft Supervision-Guided Spatial–Temporal Refinement Network for Video-Based Visible-Infrared Person Re-Identification
2026 · Jinxing Li, Chuhao Zhou, et al. · IEEE Transactions on Image Processing
Works count: 12
Citation count: 31
H-index: 2
I10-index: 1
Year
Topic
Type