search

wjun0830 / QD-DETR

Official pytorch repository for "QD-DETR : Query-Dependent Video Representation for Moment Retrieval and Highlight Detection" (CVPR 2023 Paper)
https://arxiv.org/abs/2303.13874
Other
183 stars 13 forks source link

About ablation study #38

Closed youngprogrammerBee closed 2 months ago

youngprogrammerBee commented 3 months ago

Thanks for your work, I have some questions on the ablation study.

  1. In the Table4 in the paper, which is the Ablation study on QVHighlights val split, is the (a) row Moment-detr? and if so, is the (b) row that Moment-detr simply with cross-attentive transformer encoder ?
  2. What should I do If I want to do the same ablation experiment like （b） row , that is only using CATE？
wjun0830 commented 3 months ago
  1. You are right
  2. if you want to apply cross attn on top of moment detr it would be easier if you simply add cross atten layer on top of moment detr implementation