Taste more, taste better: diverse data and strong model boost semi-supervised crowd counting Jan 1, 2025· Maochen Yang , Zekun Li , Jian Zhang , Lei Qi Yinghuan Shi · 0 min read Cite URL Type Conference paper Publication Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Last updated on Jan 1, 2025 Authors Yinghuan Shi Nanjing University ← Task preference optimization: improving multimodal large language models with vision task alignment Jan 1, 2025 TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning Jan 1, 2025 →
