I am a Research Scientist in the TCL AI Lab at TCL Research, Hong Kong where I work on Computer Vision, Machine Learning, and Deep Learning. I received my Ph.D. degree in electrical engineering from the City University of Hong Kong, in 2019. During my Ph.D. study, I worked under the supervision of Dr.Lai-Man Po on Face Liveness detection using Deep Learning techniques. Prior to my Ph.D. degree, I worked in NuSyS Lab under the supervision of Dr. Muhammad Tariq on Wireless Multimedia Sensor Networks (WMSN). I also worked as an Algorithm Specialist with TCL Corporate Research (Hong Kong) co., Limited before assuming duties as a Research Scientist at the same center in 2021.

Research Interests

Deep Learning and Computer Vision, Federated Learning, Video Understanding, Computational Photography, Audio Understanding

Available Positions

Software Engineer (Intern)

We are looking for a Software Engineer (Intern) to work with us at TCL AI Lab (Hong Kong) on the project titled “How Smart Homes Perceive and Respond to Environmental Sound”. As a Software Engineer (Intern), you will play a key role in front-end and back-end software components integration, developing user-friendly interfaces, and assisting the senior engineers in software deployment and testing. This is an excellent opportunity to gain hands-on experience in a fast-paced environment and to work with cutting-edge technologies. The internship position is flexible and the duration can be extended based on satisfactory performance.

Requirements: The candidate should have hands-on experience with Python, JAVA, and C++. Knowledge of deep neural networks and their deployment on mobile and web platforms would be a plus.

Interested candidates are encouraged to submit their resumes at yasar@tcl.com.

News

1. [2024] Our paper titled Exploring Federated Self-Supervised Learning for General Purpose Audio Understanding has been accepted to the ICASSP-2024 workshop on Self-supervision in Audio, Speech and Beyond. [Preprint]
2. [2024] Our paper titled AudioRepInceptionNeXt: A lightweight single-stream architecture for efficient audio recognition has been accepted in NeuroComputing [Preprint] [Code] .
3. [2023] Our paper titled Large Separable Kernel Attention: Rethinking the Large Kernel Attention Design in CNN has been accepted in ESWA [Preprint] [Code] .
4. [2023] Our paper titled L-DAWA: Layer-wise Divergence Aware Weight Aggregation in Federated Self-Supervised Visual Representation Learning has been accepted in ICCV-2023 [Preprint] [Supplementary Materials].
5. [2023] Our solution got first place award in EPIC-SOUNDS Audio-Based Interaction Recognition
6. [2023] A short highlight on using federated learning with self-supervision for video understanding is now available on the Flower Blogs
7. [2022] Our paper titled Federated Self-Supervised Learning for Video Understanding has been accepted in ECCV-2022
8. [2022] Video of my short talk on Federated Learning with Self-Supervision at the Flower Summit 2022 is now available on the Flower YouTube Channel
9. [2022] A paper is accepted in L3D-IVU - CVPR2022
10. [2021] Our paper titled VCGAN: Video Colorization with Generative Adversarial Networks has been accepted for publication in IEEE Transactions on Multimedia
11. [2021] Our book chapter titled Visual Information Processing and Transmission in Wireless Multimedia Sensor Networks: A Deep Learning-Based Practical Approach has been accepted for publication in the upcoming book Internet of Multimedia Things (IoMT): Techniques and Applications

Reviewer

1. Journals: IEEE TCSVT, IEEE Access, ESWA, JVCI, SPIC, IEEE TNNLS
2. Conferences: IEEE CVPR-2024, IEEE ICET, IEEE INMIC, CVPR-FedVision (2023-2024)