共计 169 篇文章

---

2024

近期LLM+视觉下游任务方法总结 06-19 论文笔记 UniVTG：Towards Unified Video-Language Temporal Grounding 04-13 论文笔记 Language-conditioned Detection Transformer 04-10 论文笔记 AttrSeg：Open-Vocabulary Semantic Segmentation via Attribute Decomposition-Aggregation 04-06 论文笔记 RWKV：Reinventing RNNs for the Transformer Era 03-27 论文笔记 MLP-Mixer：An all-MLP Architecture for Vision 03-27 论文笔记 Proposal-based Multiple Instance Learning for Weakly-supervised Temporal Action Localization 03-25 论文笔记 ActionFormer：Localizing Moments of Actions with Transformers 03-25 论文笔记 InternVideo：General Video Foundation Models via Generative and Discriminative Learning 03-22 学习笔记 Evidential Deep Learning（EDL）证据深度学习 02-23