共计 87 篇文章
2023
论文笔记 Deformable ConvNet v1+v2+DETR 论文笔记 Segment Anything 论文笔记 Segment Any Anomaly without Training via Hybrid Prompt Regularization 论文笔记 Streaming Video Model 论文笔记 FLIP Scaling Language-Image Pre-training via Masking论文笔记 论文笔记 FILIP Fine-grained Interactive Language-Image Pre-training 论文笔记 LiT Zero-Shot Transfer with Locked-image text Tuning 论文笔记 Image Captioners Are Scalable Vision Learners Too 论文笔记 Towards Diverse Paragraph Captioning for Untrimmed Videos 多模态语言模型发展观察