Besides the readme file, this folder contains two files, and their explanation is as follows: 

1- 0403-supp.pdf
This file contains additional material that was ready at the time of paper submission but could not be included due to space constraints.
	

2- BoxMask_SELSA_comparison.mp4
This small video depicts the comparison between with and without integration of our proposed BoxMask module in SELSA [1]. The first 3 seconds of the video visualize detection in Orignal SELSA [1], followed by the BoxMask equipped in SELSA.


[1] Wu, H., Chen, Y., Wang, N., & Zhang, Z. (2019). Sequence level semantics aggregation for video object detection. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 9217-9225).

