Question about `eval_moment_retrieval` function

jayleicn / moment_detr

[NeurIPS 2021] Moment-DETR code and QVHighlights dataset

https://arxiv.org/abs/2107.09609

MIT License

258 stars 44 forks source link

Question about `eval_moment_retrieval` function #45

Open yujiangpu20 opened 11 months ago

yujiangpu20 commented 11 months ago

Thank you for your excellent work! I noticed that in the eval_moment_retrieval function https://github.com/jayleicn/moment_detr/blob/main/standalone_eval/eval.py#L136, there are four predefined time ranges corresponding to 'short', 'middle', 'long', and 'full'. I'm wondering about how you chose these four intervals? If I want to evaluate my own dataset, would I need to modify the corresponding time ranges?

jayleicn commented 11 months ago

Hi @yujiangpu20, Thanks for your interest in our work. I set these ranges based on which specific lengths I care about, it is very objective.

yujiangpu20 commented 11 months ago

Got it. Thank you for your reply! And could you please provide more implementation details of the CharadesSTA dataset in Table 6? Like sampling rate, learning rate, number of queries, etc. Are they consistent with QVhighlight or are there some differences?

arkaprabha-bhandari commented 4 months ago

Hi @yujiangpu20, do you still have the feature files for this paper. It would be very helpful if you did and could share them. Thanks in advance.