Du Tran

Du Tran 

Dũ Trần
Research Scientist
Facebook Research
1 Facebook Way, Menlo Park, CA 94025
Email: x@y where x=trandu and y=fb.com (official) OR gmail.com (personal)
G-Scholar, Github, DBLP

‘‘The pinnacle of TECHNOLOGY is INNOVATION, that of SCIENCE is DISCOVERY, and more importantly that of EDUCATION is HUMANITY.’’ Du Tran, June 2011.


I am a research scientist at Facebook Applied Machine Learning. My research interests are computer vision, machine learning, and computer graphics, with specific interests in human activity and video event analysis.



  • Du Tran, Heng Wang, Lorenzo Torresani, Jamie Ray, Yann LeCun, and Manohar Paluri, A Closer Look at Spatiotemporal Convolutions for Action Recognition
    Arxiv 2017, code (coming soon), PDF.

  • Du Tran, Jamie Ray, Zheng Shou, Shih-Fu Chang, and Manohar Paluri, ConvNet Architecture Search for Spatiotemporal Feature Learning
    Arxiv 2017, code, PDF.

  • Du Tran, Maksim Bolonkin, Manohar Paluri, and Lorenzo Torresani, VideoMCC: a New Benchmark for Video Comprehension
    Arxiv 2016, Project, PDF.

  • Du Tran, Representations and Models for Large-Scale Video Understanding
    Ph.D. Dissertation, August 2016, PDF
    Thesis Committee: L. Torresani, C. Bailey-Kellogg, Q. Liu, and A. Torralba.

  • Du Tran, Lubomir Bourdev, Rob Fergus, Lorenzo Torresani, and Manohar Paluri, Deep End2End Voxel2Voxel Prediction
    The 3rd Workshop on Deep Learning in Computer Vision 2016, PDF.

  • Du Tran and Lorenzo Torresani, EXMOVES: Mid-level Features for Efficient Action Recognition and Video Analysis
    International Journal on Computer Vision (IJCV) 2016, PDF.

  • Du Tran, Lubomir Bourdev, Rob Fergus, Lorenzo Torresani, and Manohar Paluri, Learning Spatiotemporal Features with 3D Convolutional Networks
    IEEE International Conference on Computer Vision (ICCV) 2015, Santiago, Chile, Project (code available), PDF.

  • Du Tran and Lorenzo Torresani, EXMOVES: Classifier-based Features for Scalable Action Recognition
    International Conference on Learning Representations (ICLR) 2014, Banff, Canada Project, PDF.

  • Du Tran, Junsong Yuan, and David Forsyth, Video Event Detection: from Subvolume Localization to Spatio-Temporal Path Search
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2014, PDF.

  • Du Tran and Junsong Yuan, Max-Margin Structured Output Regression for Spatio-Temporal Action Localization
    Neural Information Processing Systems (NIPS) 2012, Lake Tahoe, NV, USA Project, PDF.

  • Du Tran and Junsong Yuan, Optimal Spatio-Temporal Path Discovery for Video Event Detection
    IEEE Computer Vision and Pattern Recognition (CVPR) 2011, Colorado Springs, CO, USA, Project, PDF.

  • Du Tran and Alexander Sorokin, Human Activity Recognition with Metric Learning
    European Conference on Computer Vision (ECCV) 2008, Marseille, France, Code, PDF.

Recent Talks