Prof. Elhamifar’s research areas are machine learning, computer vision and optimization. He is interested in developing scalable, robust and provable algorithms that can address challenges of complex and massive high-dimensional data. He works on applications of these tools in computer vision and robotics among others. Specifically, he uses tools from convex, nonconvex and submodular optimization, sparse and low-rank modeling, deep learning, high-dimensional statistics and graph theory to develop algorithms and theory and applies them to solve real-world challenging problems, including Big Data summarization, procedure learning from instructional data, large-scale recognition with small labeled data and active learning for visual data.

• Two papers on Procedural Task Learning (Oral Presentation) and Human Trajectory Prediction are accepted to CVPR 2021.

• Congratulations to my PhD student Dat Huynh for receiving the J.P. Morgan PhD Fellowship Award.

• New paper on Compositional Zero-Shot Learning is accepted to NeurIPS 2020. The code is also released.

• The code of the ECCV20 paper on Self-Supervised Multi-Task Procedure Learning is released.

• New paper on Procedure Completion by Learning from Partial Summaries is accepted (oral presentation) to BMVC 2020.

• New paper on Self-Supervised Multi-Task Procedure Learning from Instructional Videos is accepted to ECCV 2020.

• The codes of the three CVPR20 papers are release now.

• THREE papers, including an oral presentation, are accepted to CVPR 2020.

• Dr. Elhamifar is organizing the “Workshop on Learning from Instructional Videos” in CVPR 2020 in Seattle, Washington. In addition to invited speakers, we are accepting regular paper submissions (best paper award sponsored by MIT-IBM Watson AI Lab) and extended abstracts that will be presented in the workshop.

• The ProceL Dataset for instructional video understanding and procedure learning is released.

• Dr. Elhamifar is serving as the Editor of the 25th International Conference on Pattern Recognition (ICPR) 2020.

• New paper on Deep Supervised Subset Selection with Applications to Learning from Instructions accepted to NeurIPS 2019.

• New paper on Unsupervised Procedure Learning via Joint Dynamic Summarization accepted for Oral Presentation at ICCV 2019.

• Gave a talk on Dynamic Subset Selection and Applications to Procedure Learning in the CVPR tutorial on Recent Advances in Visual Data Summarization.

• New paper on Sequential Facility Location: Approximate Submodularity and Greedy Algorithm accepted to ICML 2019.

• Dr. Elhamifar’s MCADS Lab is home to the DGX1 Deep Learning Server from NVIDIA.

• Dr. Elhamifar received the Young Faculty Award (YFA) from the Defense Advanced Research Projects Agency (DARPA).

• Dr. Elhamifar organized and instructed the tutorial on “Big Data Summarization: Algorithms and Applications”, with Amin Karbasi and Amit Roy Chowdhury, in CVPR 2018 in Salt Lake City, UT.

• New paper on “High-Rank Matrix Completion with Side Information” accepted to AAAI 2018.

• Dr. Elhamifar served as a Senior Program Committee of AAAI 2018.

• Dr. Elhamifar received the CISE Career Research Initiation Initiative Award from the National Science Foundation (NSF).

• Prospective PhD Students: I am always looking for strong PhD students who are excited about doing research in machine learning, computer vision and optimization. If you are interested in joining my Lab, please send me an email with the subject “PhD Application to Northeastern” and attach your CV.