Could I get the code of CoT or text_json file? #3
Description
Hello,
First of all, I would like to express my sincere appreciation for your remarkable research. While running your code, I encountered some issues—specifically, the absence of the text_json file, which indicates the objects present in each frame. From what I understand, this file was generated using the CoT technique described in your paper.
To ensure accurate experiments and comparisons, I was wondering if you could kindly share the image captioning code or the text_json file that you used. It would be incredibly helpful for my research.
If you're able to share it, please feel free to send it to my email: sehan@ust.ac.kr. I truly appreciate your time and consideration.
Looking forward to your response.
Best regards,
Seungeun Han