Search Results - "Mesmakhosroshahi, Maral"

Stereo-based region of interest generation for real-time pedestrian detection by Kim, Joohee, Mesmakhosroshahi, Maral

“…Pedestrian detection is one of the major goals in advanced driver assistance systems (ADAS) which has become an active research area in recent years. In this…”
Get full text

Pedestrian Detection and Tracking for Advanced Driver Assistance Systems by Mesmakhosroshahi, Maral

“…In this thesis, we present a stereo-based pedestrian detection framework for advanced driver assistance systems by exploiting both color and depth information…”
Get full text

Feature-based ROI generation for stereo-based pedestrian detection by Mesmakhosroshahi, Maral, Loghman, Maziar, Joohee Kim

“…Region of interest (ROI) generation is an important step in stereo-based pedestrian detection systems. In this paper, we propose an ROI generation method by…”
Get full text

Stereo based region of interest generation for pedestrian detection in driver assistance systems by Mesmakhosroshahi, Maral, Joohee Kim, Yunsik Lee, Jong-bok Kim

“…Pedestrian detection is one of the major goals in advanced driver assistance systems (ADAS) which has become an active research area in recent years. In this…”
Get full text

Training Large Neural Networks with Constant Memory using a New Execution Algorithm by Pudipeddi, Bharadwaj, Mesmakhosroshahi, Maral, Xi, Jinwen, Bharadwaj, Sujeeth

“…Widely popular transformer-based NLP models such as BERT and Turing-NLG have enormous capacity trending to billions of parameters. Current execution methods…”
Get full text

Microscaling Data Formats for Deep Learning by Rouhani, Bita Darvish, Zhao, Ritchie, More, Ankit, Hall, Mathew, Khodamoradi, Alireza, Deng, Summer, Choudhary, Dhruv, Cornea, Marius, Dellinger, Eric, Denolf, Kristof, Dusan, Stosic, Elango, Venmugil, Golub, Maximilian, Heinecke, Alexander, James-Roxby, Phil, Jani, Dharmesh, Kolhe, Gaurav, Langhammer, Martin, Li, Ada, Melnick, Levi, Mesmakhosroshahi, Maral, Rodriguez, Andres, Schulte, Michael, Shafipour, Rasoul, Shao, Lei, Siu, Michael, Dubey, Pradeep, Micikevicius, Paulius, Naumov, Maxim, Verrilli, Colin, Wittig, Ralph, Burger, Doug, Chung, Eric

“…Narrow bit-width data formats are key to reducing the computational and storage costs of modern deep learning applications. This paper evaluates Microscaling…”
Get full text

With Shared Microexponents, A Little Shifting Goes a Long Way by Rouhani, Bita, Zhao, Ritchie, Elango, Venmugil, Shafipour, Rasoul, Hall, Mathew, Mesmakhosroshahi, Maral, More, Ankit, Melnick, Levi, Golub, Maximilian, Varatkar, Girish, Shao, Lei, Kolhe, Gaurav, Melts, Dimitry, Klar, Jasmine, L'Heureux, Renee, Perry, Matt, Burger, Doug, Chung, Eric, Deng, Zhaoxia, Naghshineh, Sam, Park, Jongsoo, Naumov, Maxim

“…This paper introduces Block Data Representations (BDR), a framework for exploring and evaluating a wide spectrum of narrow-precision formats for deep learning…”
Get full text

Reducing search space for fast pedestrian detection by Mesmakhosroshahi, Maral, Joohee Kim

“…Region of interest (ROI) generation used to extract candidate windows which are likely to have pedestrians is an important step in pedestrian detection…”
Get full text

Fast depth estimation using spatio-temporal prediction for stereo-based pedestrian detection by Zarshenas, Amin, Mesmakhosroshahi, Maral, Joohee Kim

“…Generating a high-quality disparity map is a fundamental step in many applications such as stereo vision-based pedestrian detection for advanced driver…”
Get full text

Depth gradient based region of interest generation for pedestrian detection by Mesmakhosroshahi, Maral, Kwang-Hoon Chung, Yunsik Lee, Joohee Kim

“…In this paper, we present a novel region of interest (ROI) generation method for stereo-based pedestrian detection systems. In the proposed algorithm, the…”
Get full text

Improving spatio-temporal feature extraction techniques and their applications in action classification by Mesmakhosroshahi, M., Joohee Kim

“…Space-time feature extraction is a recent and popular method used for action recognition. This paper presents a new algorithm to improve the robustness of…”
Get full text