Stanford University CS231n: Convolutional Neural Networks for Visual Recognition

Note: This page is still being updated as we setup office hours and schedules start to settle.

Office Hours

Time: Check the Calendar at the bottom of this page. We'll generally try to have coverage over the entire week to accomodate all students.
Software: We'll be using Nooks to hold office hours and setup queues.
Staff Information: Each staff member's schedule and areas of expertise are listed in the staff information section below.

Staff information

These are the usual staff members who will be at each session, along with their areas of expertise (which may be useful for finding project advice).

Day	Staff
Mon	Haofeng Detection, segmentation, multiple object tracking, video understanding, interactive annotation	Mandy Action recognition, videos, medical imaging, optimization/learning methods
Tue	Rachel NLP (vision+language), Amazon Mechanical Turk, creating custom datasets, RL, robotics, 3D vision, AI for medical imaging.	Geet Performance (e.g. pruning, quantization), recommendation/embedding, sparse networks, transfer Learning, videos, RNNs
Wed	Chris Generative models (GANs), privacy, fairness & interpretability	Sam Video understanding, action recognition, speech recognition, bias, multi-task learning, medical imaging	Nishant Videos, unsupervised learning, self-supervised learning, 3D vision
Thu	Guanzhi RL, robotics, videos, self-supervised learning	Russell Videos, action recognition, graph neural networks, domain adaptation, image segmentation / denoising	Sean Graphics, image editing, virtual reality, 360 degree videos
Fri	Yichen 3D vision, transfer learning, domain adaptation	JQ Image classification, image augmentation, medical imaging (classification)	Lin Robotics, RL, 3D vision
Sun	Kevin Robotics, self supervised learning