Hassan Akbari

About

I’m a 4th-year PhD candidate in DVMM Lab, Columbia University, under supervision of Prof. Shih-Fu Chang. My areas of interest include Computer Vision, Deep Learning, Modality Bridging, Visual Reasoning, and Multimodal Understanding

 

 

—————————————————————————————— 

I am looking for a student to work on cutting-edge computer vision projects during Spring 2020 semester. A 3-point research course would be credited. Please send me your CV if interested. 

Projects

Multi-level Multimodal Common Semantic Space for Image-Phrase Grounding

Nov 2018

Reconstructing intelligible speech from the human auditory cortex 

APR 2018

Lip2AudSpec: Speech reconstruction from silent lip movements video

APR 2017

Fetal ECG extraction using πTucker decomposition

Nov 2015

Publications

[1] Multi-level Multimodal Common Semantic Space for Image-Phrase Grounding

Hassan Akbari, Svebor Karaman, Surabhi Bhargava, Brian Chen, Carl Vondrick, Shih-Fu Chang

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2019

[pdf], [code

[2] Towards reconstructing intelligible speech from the human auditory cortex

Hassan Akbari, Bahar Khalighinejad, Jose Herrero, Ashesh Mehta, Nima Mesgarani

Nature Scientific Reports, 2018

[pdf], [code], [news]

[3] Lip2AudSpec: Speech reconstruction from silent lip movements video

Hassan Akbari, Himani Arora, Nima Mesgarani, Liangliang Cao

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018

[pdf], [code]

[4] GAIA – A Multi-media Multi-lingual Knowledge Extraction and Hypothesis Generation System

Tongtao Zhang, Ananya Subburathinam, Ge Shi, Lifu Huang, Di Lu, Xiaoman Pan, Manling Li, Boliang Zhang, Qingyun Wang, Spencer Whitehead, Heng Ji, Alireza Zareian, Hassan Akbari, Brian Chen, Ruiqi Zhong, Steven Shao, Emily Allaway, Shih-Fu Chang, Kathleen McKeown, Dongyu Li, Xin Huang, Xujun Peng, Ryan Gabbard, Marjorie Freedman, Ali Sadeghian, Mayank Kejriwal, Ram Nevatia, Pedro Szekely, Ali Sadeghian and Daisy Zhe Wang

Proceedings of Text Analysis Conference (TAC), 2018

[pdf]

[5] A robust FCM algorithm for image segmentation based on spatial information and total variation

Hassan Akbari, Hamed Mohebbi Kalkhoran and Emad Fatemizadeh

IEEE 9th Iranian Conference on Machine Vision and Image Processing, 2015, Best paper award

[Link]

[6] FCM-based image segmentation with bias field and intensity inhomogeneity correction

Hassan Akbari, Hamed Mohebbi Kalkhoran and Emad Fatemizadeh

The 15th IEEE International Symposium on Signal Processing and Information Technology (ISSPIT), 2015

[pdf]

[7] Fetal ECG extraction usingπTucker decomposition

Hassan Akbari, Mohammad B. Shamsollahi and Ronald Phlypo

IEEE International Conference on Systems, Signals and Image Processing (IWSSIP), 2015

[Link]

News

01/02/20: I accepted research internship offer from Facebook for Fall 2020

01/02/20: I accepted research internship offer from Google for Summer 2020

12/4/19: Our work on modality bridging named as Top 10 Breakthroughs of 2019

10/29/19: Our team won the 1st place in AIDA Knowledge Graph Construction Challenge

10/02/19: Featured in Columbia Engineering for our achievement on Decoding the Brain

09/26/19: We won the NYC Media Lab’s Grand Prize for our work on Decoding the Brain to Intelligible Speech

03/07/19: Dr. Francis Collins, director of NIH, covered our paper on reconstructing speech from the human brain using AI at NIH Director’s blog.

03/02/19: Our paper on image-phrase grounding got accepted in CVPR 2019

03/01/19: My work on modality bridging featured exclusively in FRANKFURTER ALLGMEINE ZEITUNG (FAZ), the second highest circulated newspaper in Germany

01/30/19: Our work on speech reconstruction from the brain featured in more than 100 news and science outlets

01/29/19: I accepted research internship offer from Microsoft for Summer 2019

01/28/19: Our paper on speech reconstruction from the brain featured in “The Top-5 AI Stories” of NVIDIA

My Personal Hobbies

I love many forms of art, including performing art (dancing, singing, music), photography, calligraphy, and poetry.

I have three pages:

Photography: Xperture

Poetry: ChaameGoo

Digital Art: Behance

Eat Healthy, Live Healthy

“You are what you seek”, Rumi

“You are what you eat”, Science

I’m a big advocate of active lifestyle accompanied by a healthy diet!

I regularly do sports, including bouldering and volleyball, while following a healthy diet

Contact Me