search

jayleicn / moment_detr

[NeurIPS 2021] Moment-DETR code and QVHighlights dataset
https://arxiv.org/abs/2107.09609
MIT License
267 stars 44 forks source link

Did the baselines use the same (CLIP + SlowFast) feature extractors as Moment-DETR? #46

Closed yeliudev closed 11 months ago

yeliudev commented 11 months ago

Hi @jayleicn, many thanks for sharing this great work! I was wondering whether your baseline models (e.g., MCN, XML, XML+) in Table 3 used the same feature extractors as Moment-DETR? Thanks!

jayleicn commented 11 months ago

Yes, we used the same features to these models to ensure fair comparisons.

On Nov 5, 2023, at 11:46 PM, Ye Liu @.***> wrote:

Hi @jayleicn https://github.com/jayleicn, many thanks for sharing this great work! I was wondering whether your baseline models (e.g., MCN, XML, XML+) in Table 3 used the same feature extractors as Moment-DETR? Thanks!

— Reply to this email directly, view it on GitHub https://github.com/jayleicn/moment_detr/issues/46, or unsubscribe https://github.com/notifications/unsubscribe-auth/ADYJWVL3IW2SLDCTBX3SBFLYDCIVHAVCNFSM6AAAAAA67B3XMOVHI2DSMVQWIX3LMV43ASLTON2WKOZRHE3TQNJQGIYTCMA. You are receiving this because you were mentioned.

yeliudev commented 11 months ago

I see. Thanks for your reply!