Amir  Roshan Zamir

My research interests lie broadly in computer vision and machine learning with a focus on transfer learning, self-supervised/unsupervised learning, and perceptual robotics. I'm passionate about going beyond task-specific models and developing the theoretical and experimental grounds of a comprehensive and generalizable perception. Here are my sample research, teaching, and community works on this topic. As other related tracks, I'm interested in video understanding, structured prediction, and 3D vision.

Feb. 2018: Taskonomy: Disentangling Task Transfer Learning, CVPR'18.
[Best Paper Award] [Oral].
A. Zamir, S. Sax*, W. Shen*, L. Guibas, J. Malik, S. Savarese.
[ Transfer Learning API | Live Demo | Trained Models | Website | Paper].

Feb. 2018: Gibson Env: Real-World Perception for Embodied Agents, CVPR'18, Spotlight.
A. R. Zamir*, F. Xia*, J. He*, S. Sax, J. Malik, S. Savarese.
Real-world learning environments and agents for perceptual robotics.
[ Gibson Environments | Github | Paper].

Mar. 2017: With J. Malik, A. Efros, A. Gupta, and S. Savarese, we started the Beyond Supervised Learning workshop series, to inaugurate in ICCV 2017.

Mar. 2017: Paper in CVPR17: Feedback Networks, A. Zamir*, T. Wu*, L. Sun, WB. Shen, B. Shi, J. Malik, S. Savarese.
[ Project Website | PDF ].

Jun. 2016: Received CVPR Best Student Paper Award for Structural-RNN.

Jun. 2016: Co-organizing The First Workshop on Negative Results in Computer Vision in CVPR 2017, along with A. Torralba, W. Freeman, D. Forsyth, A. Efros, R. Sukthankar, A. Oliva, O. Sener, and J. Malik.

Jun. 2016: Paper in ECCV16: Generic 3D Representation via Pose Estimation and Matching, Zamir et al.
[ 3D Representation Website | PDF | Dataset Repository ]

Jun. 2016: I will be instructing CS331B: Representation Learning in Computer Vision course at Stanford starting autumn 2016 (with Silvio Savarese).
[see Course Webpage | Stanford ExploreCourses ]

Jun. 2016: With A. Hakeem, L. Van Gool, M. Shah, and R. Szeliski, we published the book Large-Scale Visual Geo-Localization, with Springer.
[Front Matter | Cover | Springer Page]

Jun. 2016: Selected as a recipeint of Institute for Computational and Mathematical Engineering seed award for our work on Generic Representation Learning. Thank you Stanford ICME and NVIDIA GPU Center of Excellence!

Mar. 2016: Two papers accepted to CVPR'16:
1) Structural-RNN: Deep Leaning on Spatio-Temporal Graphs
[Best Paper Award] [Oral].
2) 3D Semantic Parsing of Large-Scale Indoor Spaces [Oral]
[see Building Parser website]

Mar. 2016: Invited talk at Google Mountain View on Generic Representation Learning, on May 10th.

Dec. 2015: Invited talk at ICCV'15 Workshop Computer Vision for Converging Perspectives on Low-Level 3D.

Dec. 2015: Will serve as the tutorial and workshop chair of International Conference on 3DVision, 2016.

Aug. 2015: Two papers accepted to ICCV'15:
1) Unsupervised Semantic Parsing of Video Collections
2) Action Recognition by Hierarchical Mid-level Action Elements

Jun. 2015: Invited talk at CVPR15 3D from a Single Image workshop.

May 2015: Talk on June 11 in CVPR15's THUMOS Challenge workshop.

Jun. 2014: Two papers accepted to ECCV'14:
1) DaMN - Discriminative and Mutually Nearest: Exploiting Pairwise Category Proximity for Video Action Recognition
2) GIS-Assisted Object Detection and Geospatial Localization
One minute spotlight videos: [DaMN Classification! | GIS-Assisted Object Detection]

Apr. 2014: Talk on April 24th at Google Research. Title: Visual Geo-localization and Location-aware Image Analysis.

Apr. 2014: Two papers accepted to CVPR'14:
1) GPS-Tag Refinement using Random Walks with an Adaptive Damping Factor
2) Video Classification using Semantic Concept Co-occurrences
One minute spotlight videos: [Tag Refinement | Video Classification]

Apr. 2014: Selected as the recipient of Graduate Research Forum award for research on "Location-aware Image Understanding". [Link]

Dec. 2013: Paper accepted to TPAMI: "Image Geo-localization Based on Multiple Nearest Neighbor Feature Matching using Generalized Graphs", in IEEE Transactions on Pattern Analysis and Machine Intelligence. [PDF]

Sept. 2013: Selected as the recipient of National Geospatial-Intelligence Agency NARP-SW best research poster award.

Sept. 2013: Invited talk at Cornell, Dept. of CS, on Location-aware Image Understanding and Large Scale Image and Video Geo-localization on Sept. 13. [Flyer]

Jul. 2013: Selected as the recipient of UCF Research Excellence Award.

Jun. 2013: talk at Georgia Tech, College of Computing, on Global Multi-object Tracking using Generalized Graphs on July 5.

Jun. 2013: Paper accepted to ACM MM'13: "Visual Business Recognition - A Multimodal Approach". [PDF| Video | Project Page]

Jun. 2013: Will serve as the program co-chair of the ICCV'13 international workshop on Action Recognition with Large Number of Classes (THUMOS). [Workshop Website | Call for Papers]

Mar. 2013: Talk at University of Maryland-College Park, Department of ECE, on Large Scale Image and Video Geo-localization using Street View Imagery on March 26.

Feb. 2013: Serving in the program committee of the CVPR'13 international workshop on Visual Analysis and Geo-Localization of Large-Scale Imagery. [Workshop Website | Call for Papers]

Jun. 2012: Paper accepted to ECCV12: "GMCP-Tracker: Global Multi-object Tracking using Generalized Minimum Clique Graphs". [PDF | Project Page]

Feb. 2012: Paper accepted to CVPR12: "City Scale Geo-spatial Trajectory Estimation of a Moving Camera". [PDF | Project Page]

Jun. 2010: Paper accepted to ECCV10: "Accurate Image Localization Based on Google Maps Street View". [PDF | Project Page]