Will the model automatically truncate the video if the video duration is greater than 150 seconds?

[ffiioonnaa]

Hi,thanks for your work！
I have two questions：

1. I tried to input a video longer than 150s, and set query feature to be zeros([77,512]) ,then I found that the value of d_emb [150:] in this line

   UMT/models/model.py

   Line 51 in bde05e3

   d_emb = self.query_dec(q_emb, r_emb)

   is the same, how can the model be adjusted to accommodate the longer video duration? Even if I give a query, the saliency score of the post-150s section will be relatively smaller, and the high scores will basically appear in the first 150s
2. If I want to use weights trained on the QVhighlights dataset and don't use query for testing, how do I adjust it?