Embedded Files
Kenan AK
Kenan AK
PhD, Applied Scientist, Amazon (USA)
Research Interests: Machine Learning, Computer Vision, Multimodal Learning, Large Language Models
Kenan is an Applied Scientist at Amazon. He was Research Scientist at The Visual Intelligence lab of the Institute for Infocomm Research, A*STAR, Singapore (2020-2022). He received his PhD in Electrical and Computer Engineering from the National University of Singapore in 2020. During his PhD, he was fully funded by A*STAR Graduate Academy under Singapore International Graduate Award. He was also at the Adobe Deep Learning team in San Jose, California, in 2019. His deep-learning-based text-to-image generation algorithm, ranked second overall in the FashionGen Challenge was held as part of the Computer Vision for Fashion, Art and Design Workshop at the European Conference on Computer Vision (ECCV 2018) in Munich, Germany (8-14 September 2018).
Education
Education
Ph.D. in Electrical and Computer Engineering, National University of Singapore 2016 – 2020
Research Focus: Deep Learning, Image Retrieval, text-to-image synthesis
M.Sc. in Electrical and Electronics Engineering, Bogazici University, Turkey 2015 – 2016
During my MS study at Bogazici University, I received Singapore International Graduate Award, and moved to NUS Singapore.
B.Sc. in Electrical and Electronics Engineering, Isik University, Turkey 2010 – 2015
Research Focus: Computer Vision, Semantic Segmentation
Selected Publications
Selected Publications
A. Köksal, K. E. Ak, Y. Sun, D. Rajan and J. H. Lim, "Controllable Video Generation with Text-based Instructions," in IEEE Transactions on Multimedia, 2023 doi: 10.1109/TMM.2023.3262972.
Ak, Kenan Emir, et al. "Leveraging Efficient Training and Feature Fusion in Transformers for Multimodal Classification." 2023 IEEE International Conference on Image Processing (ICIP). IEEE, 2023.
Kim, T., Ahn, P., Kim, S., Lee, S., Marsden, M., Sala, A., ... & Sun, M. (2023). NICE 2023 Zero-shot Image Captioning Challenge. arXiv preprint arXiv:2309.01961. [Ranked 3rd at Industry Track of NICE (New frontiers for zero-shot Image Captioning Evaluation) Challenge at CVPR 2023]
Ak, K. E., Sun, Y., & Lim, J. H. (2022). Learning by imagination: A joint framework for text-based image manipulation and change captioning. IEEE Transactions on Multimedia. 2022
Kenan E. Ak, Ying Sun, and Joo Hwee Lim, “Robust Multi-Frame Future Prediction by Leveraging View Synthesis”, International Conference on Image Processing (ICIP) 2021.
Huijing Zhan, Lin Jie, Kenan E. Ak, Boxin Shi, Ling-Yu Duan, Alex C. Kot. “A3-FKG: Attentive Attribute-Aware Fashion Knowledge Graph for Outfit Preference Prediction”, IEEE Transactions on Multimedia (TMM) 2021.
Ying Sun, Yi Cheng, Mei Chee Leong, Hui Li Tan, Kenan E. Ak, “Team VI-I2R Technical Report on EPIC-Kitchens Action Anticipation Challenge 2020”, Proceedings of the IEEE Computer Vision and Pattern Recognition Workshop (CVPRW) 2020. [Ranked 2nd at EPIC-Kitchens Action Anticipation Challenge at CVPR 2020]
Kenan E. Ak, Ning Xu, Zhe Lin, and Yilin Wang, Incorporating Reinforced Adversarial Learning in Autoregressive Image Generation, European Conference on Computer Vision (ECCV) 2020, Scotland
Kenan E. Ak, Ying Sun, and Joo Hwee Lim, Learning Cross-modal Representations for Language-based Image Manipulation, IEEE International Conference on Image Processing (ICIP) 2020, United Arab Emirates.
Heqing Zou, Kenan E. Ak, and Ashraf A. Kassim, Edge-gan: edge conditioned multi-view face image generation, IEEE International Conference on Image Processing (ICIP) 2020, United Arab Emirates.
Kenan E. Ak, Joo Hwee Lim, Jo Yew Tham, Ashraf A. Kassim, Semantically consistent text to fashion image synthesis with an enhanced attentional generative adversarial network, Pattern Recognition Letters 2020. [Ranked 2nd at the FashionGen Challenge that was held at ECCV 2018]
Kenan E. Ak, Joo Hwee Lim, Jo Yew Tham, Ashraf A. Kassim, Attribute Manipulation Generative Adversarial Networks for Fashion Images, In Proceedings of the IEEE International Conference on Computer Vision (ICCV) 2019, Korea.
Kenan E. Ak, Joo Hwee Lim, Jo Yew Tham, Ashraf A. Kassim, Semantically Consistent Hierarchical Text to Fashion Image Synthesis with an enhanced-Attentional Generative Adversarial Network, In Proceedings of the IEEE International Conference on Computer Vision (ICCV) Workshop 2019, Korea.
Kenan E. Ak, Ashraf A. Kassim, Joo Hwee Lim, and Jo Yew Tham, FashionSearchNet: Fashion Search with Attribute Manipulation, ECCV 2018 Workshop.
Kenan E. Ak, Ashraf A. Kassim, Joo Hwee Lim, and Jo Yew Tham, Learning Attribute Representations with Localization for Flexible Fashion Search, In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018. [Paper]
Kenan E. Ak, Joo Hwee Lim, Jo Yew Tham, and Ashraf A. Kassim, Efficient Multi-Attribute Similarity Learning Towards Attribute-based Fashion Search, IEEE Winter Conference on Applications of Computer Vision (WACV), 2018. [Paper] [Presentation]
Kenan E. Ak, Joo Hwee Lim, Jo Yew Tham, and Ashraf A. Kassim, Which shirt for my first date? Towards a Flexible Attribute-based Fashion Query System, Pattern Recognition Letters 2018.
Hasan Fehmi Ateş, Sercan Sunnetçi., Kenan E. Ak, "Kernel Likelihood Estimation for Superpixel Image Parsing", in ICIAR 2016.
Kenan E. Ak and Hasan Fehmi Ateş, "Scene segmentation and labeling using multi-hypothesis superpixels," in IEEE SIU 2015.
Awards, Recognition, Professional Service
Awards, Recognition, Professional Service
Rank 3rd - Industry Track of NICE (New frontiers for zero-shot Image Captioning Evaluation) Challenge at CVPR 2023 in Vancouver, Canada.
With our Amazon team, we develop robust image captioning models that advance the state-of-the-art both in terms of accuracy and fairness. Our model achieved 3rd place in Industry track. For more information: https://nice.lgresearch.ai/
Student & Education Activities Chair, IEEE International Conference on Acoustics, Speech, & Signal Processing (ICASSP) 2022, Singapore.
Rank 2nd - EPIC-Kitchens Action Anticipation Challenge at CVPR 2020 in Seattle, United States
Our team, under the team name VI-I2R, achieved 2nd place for both seen and unseen kitchens in EPIC-Kitchens Action Anticipation Challenge at CVPR 2020. For more information: https://oar.a-star.edu.sg/jspui/handle/123456789/4474
Ranked 2nd at the FashionGen Challenge that was held at ECCV 2018 in Munich, Germany
My deep-learning-based text-to-image generation algorithm ranked second overall in the FashionGen Challenge that was held as part of the Computer Vision for Fashion, Art, and Design Workshop at the European Conference on Computer Vision (ECCV 2018) in Munich, Germany (8-14 September 2018). This project was a part of my Ph.D. research at the National University of Singapore. This research is published at Pattern Recognition Letters in 2020. For more information: (https://www.sciencedirect.com/science/article/abs/pii/S0167865520300751).
A*STAR Singapore International Graduate Award (SINGA) 2016-2020
Fully-funded PhD position at the ECE Department of National University of Singapore.
Google Sites
Report abuse