I would like to express my sincere gratitude for your outstanding contribution to the field of event tracking. However, I have a few questions that require clarification.

[YmShan]

After reviewing the code, I notice you have provided methods for processing event voxels. May I ask if the results reported in the original paper, which use only event data for object tracking, are based on data in event voxel format?

When tracking with multimodal data, I noticed your code merges event and RGB data using a script, but this script uses event data in image format. May I inquire if the multimodal results reported in your paper are based on experiments using data processed by this script?

I observed that your code ('AMTTrack/lib/model/amttrack/base_backbone.py') does not contain multimodal fusion operations, which seems to align with my understanding that you perform multimodal fusion via script before inputting the data into the tracker.

I look forward to your response and would like to thank you again for your contribution. This is an exceptionally comprehensive work as it provides tracking results on many mainstream trackers that were previously established, which is crucial for someone new to this field to gain a thorough understanding.