共计 180 篇文章
2024
The Platonic Representation Hypothesis 近期LLM+视觉下游任务方法总结 论文笔记 UniVTG：Towards Unified Video-Language Temporal Grounding 论文笔记 Language-conditioned Detection Transformer 论文笔记 AttrSeg：Open-Vocabulary Semantic Segmentation via Attribute Decomposition-Aggregation 论文笔记 RWKV：Reinventing RNNs for the Transformer Era 论文笔记 MLP-Mixer：An all-MLP Architecture for Vision 论文笔记 Proposal-based Multiple Instance Learning for Weakly-supervised Temporal Action Localization 论文笔记 ActionFormer：Localizing Moments of Actions with Transformers 论文笔记 InternVideo：General Video Foundation Models via Generative and Discriminative Learning