Courses

I taught at Columbia University from 2013 to 2018.

Columbia E6894 (fall 2018)
Deep Learning for Computer Vision, Speech, and Language
Co-taught with Xiaodong Cui and Kapil Thadani

Columbia E6894 (spring 2017)
Deep Learning for Computer Vision, Speech, and Language
Co-taught with Xiaodong Cui and Kapil Thadani

Columbia EECS 6894 (spring 2015)
Deep Learning for Computer Vision and Natural Language Processing
Co-taught with James Fan

Columbia EECS 6890 (spring 2014)
Visiual recognition and search
Co-taught with Rogerio Feris and Jun Wang

Columbia EECS 6890 (spring 2013)
Visiual recognition and search
Co-taught with Rogerio Feris

Talks and Tutorials

Scale Learning in Image Semantics: A 15-Year Review and A Case Study
Invited talk at IEEE CVPR Workshop on Fair, Data Efficient, Trusted Computer Vision
June 2024


Reducing Longform Errors in End2End Speech Recognition
(an overview of my work in Google Cloud Speech)
Invited talk at Rutgers University
April 2022
An extended version

Visual Search and Question Answering
Tutorial at ICME 2019 (Shanghai, July 8-12)
Co-presented with Lu Jiang and Yannis Kalant

Convolutional Networks and Their Applications Tutorial at Google AI Winter Camp, Beijing 2019

Learning Visual Semantics: Models, Massive Computation, and Innovative Applications Tutorial at CVPR 2014:
Co-presented with Shih-Fu Chang, John R. Smith, and Rogerio Feris

Massive-Scale Multimedia Semantic Modeling
Tutorial at ACM Multimedia 2013:
Co-presented with John R. Smith