Clarification on stable_times assignment in data/main.py

[cyl0000]

Hello, thanks for sharing your work.

I am currently working with your project and I have a question regarding a specific line of code in the data/main.py file. In the file, I noticed the following line:"stable_times = list_idle_im_se_t_tup[chunk_id][chunk_id][0]". I wanted to confirm if this line should actually be:''stable_times = list_idle_im_se_t_tup[chunk_id][chunk_id]''Could you provide some clarification on this?

Additionally, I'm curious about how the list_idle_im_se_t_tup variable is generated and how it ensures that its length matches the length of chunks. Could you please point me to that section of the code or provide some insights on how this synchronization is achieved?

I appreciate your time and assistance. Thank you in advance for your help!

Best regards

[wisdomikezogwo]

Hi,

So this issue is similar to #7 (comment) and #18 (comment) you should check them out, sorry I haven't updated that part of the code yet, I will now.

list_idle_im_se_t_tup is generated from the stable periods within chunks. so get_histo_srt_im_recon gets a bunch of relevant times (scene frame times) for a video and their predictions and using the algo described in Figure 9 of the paper the video is chunked/cut and then for each chunk we look for stable regions (see figure 7 supp) to get representative frames using save_frame_chunks_recon and if there aren't any we take all the scene frames and duplicate them. Hence there isn't any need for synchronization as one process feeds the next, hence they are aligned in time.

If I'm not quite answering your question, do let me know.