IGNORANT

  • 首页
  • 索引
        归档
        分类
        标签
  • 友链
  • 关于
首页
索引
归档
分类
标签
友链
关于

[论文粗读][CVPR22workshop]ViTOL: Vision transformer for weakly supervised object localization

2023-2-24

[论文粗读][NIPS21]Low-fidelity video encoder optimization for temporal action localization

2023-2-20

TAL任务存在task discrepancy problem,作者参考object detection task中的思路,探索TAL上的end to end training

[论文简读][CVPR20]Revisiting the Sibling Head in Object Detector

2022-3-28

现有OD处理分类和定位时采用参数共享head,会导致spatial misalignment,作者探索了一种解耦方法来解决此问题

[论文简读][CVPR20]Offset Bin Classification Network for Accurate Object Detection

2022-3-9

[论文简读][NIPS20]Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection

2022-3-6

[论文简读][CVPR19]Distilling Object Detectors with Fine-grained Feature Imitation

2022-3-4

[论文简读][ICLR15]FitNets: Hints for Thin Deep Nets

2022-3-3

初学VAE【01】概念到推导

2021-9-2

初学VAE【01】概念到推导

2021-9-2

《Temporal Interlacing Network》笔记

2020-9-25

《TSM: Temporal Shift Module for Efficient Video Understanding》笔记

2020-9-24

《Temporal Relational Reasoning in Videos》笔记

2020-9-16


© zfhxi
Powered byNotionNext 4.10.8.
渝ICP备2023001150号
CDN is supported by