Taste more, taste better: diverse data and strong model boost semi-supervised crowd countingApr 20, 2025·Maochen Yang,Zekun Li,Jian Zhang,Lei QiYinghuan Shi· 0 min read Cite URLTypeConference paperPublicationProceedings of the IEEE/CVF Conference on Computer Vision and Pattern RecognitionLast updated on Apr 20, 2025AuthorsYinghuan ShiNanjing University← Task preference optimization: improving multimodal large language models with vision task alignment Apr 20, 2025Tra-MoE: learning trajectory prediction model from multiple domains for adaptive policy conditioning Apr 20, 2025 →
