sayednadim / gated_convolution_tensorflow Goto Github PK

I am a computer vision researcher with experience in developing cutting-edge AI-based solutions for autonomous vehicles, leading several teams and concurrently working as an AI researcher. I have experience in designing traditional/deep learning methods for 2D & 3D image processing techniques, utilizing supervised/semi-supervised/unsupervised learning, working with different sensors (RGB pinhole/wideangle/Fisheye cameras, Monochrome cameras, NIR/LWIR cameras, Neuromorphic sensors, LiDAR, IMU, etc.), and deep generative models.

I am currently working as a Group Lead and AI researcher in DeltaX.ai. Prior to that, I was working as a vision researcher in CVIP Lab, Gachon University, Republic of Korea.

• Group Lead | Nov 2023 - Present | Automotive Perception Group, AI Lab, DeltaX.ai, Rep. of Korea.

  • Leading several teams working on building ADAS solutions and SCMS-DMS-OMS solutions.

• Team Lead and AI Researcher | Oct 2022 - Nov 2023 | X-Camera ADAS Team, AI Lab, DeltaX.ai, Rep. of Korea.

  • Led a team of developers working on large-scale, complex, and cutting-edge systems.
  • Prepared industrial proposals for projects and PoCs.
  • Managed the delivery of multiple, complex, simultaneous development projects from design through to release.
  • Led cutting-edge R&D projects which eventually progressed to industrial projects/PoCs.
  • Monitored the performance of the team and reported on performance metrics.
  • Conducted job-related administrative works.

• Vision Researcher | Mar 2019 - Sep 2022 | Computer Vision and Image Processing (CVIP) Lab, Gachon University, Rep. of Korea.

  • Worked with deep learning-based generative image synthesis tasks such as image inpainting, image colorization etc., and stereo depth estimation using bio-inspired vision systems.
  • Participated in various industrial projects regarding depth estimation, face detection etc.
  • Provided lectures on the concepts of computer vision/ deep learning and hands-on training on Python and PyTorch.
  • Conducted job-related administrative works.

• Analyst, Business Development | Jul 2018 - Jan 2019 | Apex DMIT Ltd. (former 'Kazi IT Center'), Dhaka, Bangladesh.

  • Participated in analysing and managing overseas assets.
  • Managed several assets and freelance contractors through direct/indirect supervisions.
  • Performed several administrative duties such as participating/supervising asset bidding, compiling reports, attending/organizing seminars etc.

• Teaching Assistant | Feb 2018 - Jun 2018 | Dept. of EEE, University of Liberal Arts, Bangladesh.

  • Provided lectures on course-specific concepts and hands-on training on circuits and embedded systems.
  • Allocated tasks, projects and performed grading.
  • Conducted job-related administrative works.

Here are some queries about me....

• 🔭 I’m currently working on color filter arrays and event cameras.
• 💬 I usually work with PyTorch. I have experiences with TensorFlow (1.x), Keras and MATLAB.
• 📫 How to reach me: smnadimuddin at gmail dot com

• Nov 20, 2023 - [Job] I have been assigned as a Group Lead at DeltaX.ai. I will be overseeing the Automotive Perception Group and mainly be working with several teams to build ADAS, DMS, OMS and SCMS solutions.
• Apr 14, 2023 - [Conference] Our team has successfully participated in CVPR’23 2nd Monocular Depth Estimation Challenge.
• Oct 25, 2022 - [Job] I have joined DeltaX.ai as a Team Lead and AI Researcher.
• Sep 4, 2022 - [Journal] Our paper “Multi-Scale Attention-Guided Non-Local Network for HDR Image Reconstruction” has been published in the Sensors (Q1, Impact Factor - 3.847) Journal.
• Aug 1, 2022 - [Conference] Our team has successfully participated in ECCV’22 AIM Challenge on Reversed ISP (Track 1).
• Jun 26, 2022 - [Journal] Our paper “Unsupervised Deep Event Stereo for Depth Estimation” has been accepted in the IEEE Transactions on Circuits and Systems for Video Technology- (Q1, Impact Factor - 5.859).
• May 10, 2022 - [Journal] Our paper “SIFNet: Free-form image inpainting using color split-inpaint-fuse approach” has been published in the Computer Vision and Image Understanding Journal (Volume 221, August 2022, 103446) - (Q1, Impact Factor - 4.886).
• Feb 3, 2021 - [Conference] Our paper “Deep Event Stereo Leveraged by Event to Image Translation” is published in AAAI Conference on Artificial Intelligence (AAAI-21).
• Jul 21, 2020 - [Conference] Our team has successfully participated in ECCV AIM Challenge on Image Extreme Inpainting.
• Jun 4, 2020 - [Journal] Our paper “Global and local attention-based free-form image inpainting” has been published in the Sensors (Q1, Impact Factor - 3.847) Journal.