L2CS-Net
L2CS-Net copied to clipboard
Ahmednull
The official PyTorch implementation of L2CS-Net for gaze estimation and tracking
Hello, Thank for your great work. I have a question. When I replicated the work, I got a better result than 3.92 on MPIIFaceGaze. However, when I tested your pre-training...
Hello author, first of all, thank you very much for open sourcing your work. My English and code skills are not very good, so here I will briefly talk about...
Hi I am trying to run the demo but not able to find the repo, any idea from where to import it
Hi Ahmed and thanks for sharing this great work! Are you planning to share a code for video demo? Thanks, Carmi
Very interesting research, thanks for publishing the code. I am still a student and inexperienced, so please forgive me if my question is due to my lack of knowledge. According...
Thank you very much for your excellent work, but I found that the data_processing_gaze360. pdf in your laboratory homepage could not be found. Could you please upload a copy when...
First of all thanks Ahmed for the work. Here the question: Why there are 15 MPIIGaze trained models and not just one as with the Gaze360 Dataset? And in this...
In your model, the forward function returns `pre_yaw_gaze` and `pre_pitch_gaze`: https://github.com/Ahmednull/L2CS-Net/blob/a4d8f7fa5436a2b2b9f088471623b552a85811bd/l2cs/model.py#L70 However, in the pipeline, the two variables are assigned as `gaze_pitch` and `gaze_yaw`: https://github.com/Ahmednull/L2CS-Net/blob/a4d8f7fa5436a2b2b9f088471623b552a85811bd/l2cs/pipeline.py#L122 It seems `yaw` and `pitch`...
