© 2015 by TAE-HYUN OH. Proudly created with Wix.com

  • facebook-square

Information about computer vision and machine learning academic field

 

- Top-tier conferences

: CVPR, ICCV, ECCV, NIPS, ICML, and ICLR are considered high prestigious top-tier conferences, which have greater impact than most SCI journals. According to Google scholar metrics, all these conferences are listed in the top 100 publications across all academic fields. Out of them, CVPR is the 10th rank among all academic fields, e.g., Cell journal is just the 9th rank. In terms of acceptance rate, oral presentations are about 4% and poster presentations about 20%, i.e., highly competitive. 

- Top-tier journals

IEEE TPAMI and IJCV have among the highest impact factors across all computer science categories. As of 2019, the impact factor of TPAMI is 17.730.

  • Selected publications (International Journal)

Learning to Localize Sound Sources in Visual Scenes: Analysis and Applications

Arda Senocak, Tae-Hyun Oh, Junsik Kim, Ming-Hsuan Yang, In So Kweon

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), to appear.

[Dataset] [Featured by Seamless]

Qualcomm Innovation Paper Award 2018 by Qualcomm Korea R&D center

Kyungdon Joo, Tae-Hyun Oh, In So Kweon, Jean-Charles Bazin

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), to appear.

Kyungdon Joo, Tae-Hyun Oh, Junsik Kim, In So Kweon 

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2019

Hyowon Ha, Tae-Hyun Oh, In So Kweon

IEEE Signal Processing Letters, 2018.

Tae-Hyun Oh, Yasuyuki Matsushita, Yu-Wing Tai, In So Kweon

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2018.

This conference version received Gold Prize (Acceptance rate 0.8%), 21th HumanTech Paper Award by Samsung. 

[Project page] [arXiv]

Tae-Hyun Oh, Yu-Wing Tai, Jean-Chales Bazin, Hyeongwoo Kim, In So Kweon

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2016.

Tae-Hyun Oh, Joon-Young Lee, Yu-Wing Tai, In So Kweon

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2015.

Inwook Shim, Jongwon Choi, Seunghak Shin, Tae-Hyun Oh, Unghui Lee, Byungtae Ahn, Dong-Geol Choi, David Hyunchul Shim, In So Kweon

IEEE Transactions on Intelligence Transportation Systems (TITS), 2015.

Qualcomm Innovation Award 2013.

With this system, we won Youl-Jeong award (5th rank) from the autonomous vehicle challenge 2012 by Hyundai Motors, Korea.

[Video]

Tae-Hyun Oh, David Wipf, Yasuyuki Matsushita, In So Kweon

Preprint (arxiv)

A Novel Low-Rank Constraint Method with the Sparsity Model for Moving Object Analysis

Tae-Hyun Oh

Master Thesis, KAIST

Please reload

  • Selected publications (International Conference)

​Dong-Jin Kim, Jinsoo Choi, Tae-Hyun Oh, In So Kweon

Conference on Empirical Methods in Natural Language Processing (EMNLP), 2019 (Long paper)

[PDF]

Also, presented at

"Language and Vision Workshop"

"Visual Question Answering and Dialog Workshop" in conjunction with CVPR, 2019, and

"CLVL: 3rd Workshop on Closing the Loop Between Vision and Language" in conjunction with ICCV, 2019.

Seokju Lee, Junsik Kim, Tae-Hyun Oh, Yongseop Jeong, Donggeun Yoo, Stephen Lin, In So Kweon

British Machine Vision Conference (BMVC), 2019

International Conference on Machine Learning (ICML), Jun., 2019

This has been covered by more than 20 media including BBC News, Fortune, Engadget, ZDNet, TechCrunch, Geek, and MIT News. Also, this work was posted on the front page of the MIT CSAIL web page as a representative illustration of AI group.

[PDF] [Project page]

Speech2Face: Learning the Face Behind a Voice

Tae-Hyun Oh*, Tali Dekel*, Changil Kim*, Inbar Mosseri, William T. Freeman, Michael Rubinstein, Wojciech Matusik

(* Equally contributed)

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun., 2019.

This has been covered by lots of media. You can google it.

[PDF] [Project page]

Speech2Face synthesizes someone’s face image from hearing their speech. We train it with 2 millions of video clips with near 100,000 different people's faces.

The work is an effort to better understand the capabilities of machine perception, i.e., the speech-face association.
When we hear a voice on the radio or the phone call, we, human, often build a mental model to imagine how the person looks. Our work can be considered as a replication of a human mental model by machine. For the Speech2Face task, we rarely understood how strongly we human can parse and whether it is indeed correct or just noisy bias. The reconstructed face by Speech2Face could be used as a proxy to study these.

We can imagine a range of applications, including for privacy-minded people who want to share real photos of themselves off the internet or video calls.

Variational Prototyping-Encoder: One-Shot Learning with Prototypical Images

Junsik Kim, Tae-Hyun Oh, Seokju Lee, Fei Pan, In So Kweon

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun., 2019.

[PDF]

Dong-Jin Kim, Jinsoo Choi, Tae-Hyun Oh, In So Kweon

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun., 2019.

[PDF] [Project page] [Dataset] [Evaluation code (coming soon)]

Also presented at 

Language and Vision Workshop in conjunction with CVPR, 2019, and

Visual Question Answering and Dialog Workshop in conjunction with CVPR, 2019

Suwon Shon, Tae-Hyun Oh, James Glass

International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May, 2019

[PDF]

In this work, an attention mechanism based fusion method is applied for the multi-modal person verification task. The fusion method adaptively combines person speech and visual face information on a feature-level. We demonstrate that the attention implicitly weighs either modality according to their quality and distinctiveness; thus, it is tolerant against missing modality and outlier. Interestingly, even when a single modal input is given, our multi-modal network performs favorably against the networks trained only with either of modalities. This behavior evidently is similar to the multisensory representation used in human's person recognition capability [Bülthoff and Newell, Distinctive voices enhance the visual recognition of unfamiliar faces, Cognition'15].​

Asian Conference on Computer Vision (ACCV), Dec., 2018.

[PDF] [Project page]

 

If you see a picture of someone, can you anticipate their voice? If you hear someone's voice, can you guess what they look like?

This work conducted both human and machine experiments to see their capability of association between voice and face. Our experiments show that the human indeed has such capability and machines can have a similar capability like the human, opening many questions about how physical appearance and voice are correlated.

European Conference on Computer Vision (ECCV), Sep., 2018.

Accepted as a full oral paper (2.3% acceptance rate)

[Project page] [Video results] [PDF] [Oral presentation]

 

Video motion magnification is a technique that magnifies subtle motion almost invisible by human eyes in video so that we can clearly observe it. This work presents the first learning-based method for video motion magnification. We show that physically plausible motion representation can be learned by deep neural networks only with synthetic data.

Yağız Aksoy, Tae-Hyun Oh, Sylvain Paris, Marc Pollefeys, Wojciech Matusik

ACM Transactions on Graphics (ACM SIGGRAPH), 2018

Selected as Video Trailer

This has been covered by more than 17 media including BBC news, MIT CSAIL news, Nvidia news, and Digital Trend. Refer to the project page for the detail media coverage.

[PDF] [Project page] [Video]

 

 

This work proposed a new concept, an automatic semantic soft segmentation, which provides semantically meaningful and accurate soft transitions between different object regions. It can enhance image editing and computational imaging applications.

Part-based Player Identification using Deep Convolutional Representation and Multi-scale Pooling

Arda Senocak, Tae-Hyun Oh, Junsik Kim, In So Kweon

In CVSports workshop in conjunction with CVPR, Jun., 2018

Selected as Oral paper.

Kyungdon Joo, Tae-Hyun Oh, In So Kweon, Jean-Charles Bazin

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun., 2018.

Arda Senocak, Tae-Hyun Oh, Junsik Kim, Ming-Hsuan Yang, In So Kweon

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun., 2018.

[Dataset] [Featured by Seamless]

Qualcomm Innovation Paper Award 2018 by Qualcomm Korea R&D center

Will be presented in Sight & Sound Workshop (Oral) and VisionMeetsCognition Workshop (Oral, invited) in conjunction with CVPR 2018.

Jinsoo  Choi, Tae-Hyun Oh, In So  Kweon

IEEE Winter Conference on Applications of Computer Vision (WAVC), 2018.

The conference name of 'IEEE Workshop on Applications of Computer Vision (WACV)' is changed to 'Winter'.

Dong-Jin  Kim, Jinsoo  Choi, Tae-Hyun Oh, Youngjin  Yoon, In So  Kweon

IEEE Winter Conference on Applications of Computer Vision (WAVC), 2018.

The conference name of 'IEEE Workshop on Applications of Computer Vision (WACV)' is changed to 'Winter'.

AAAI Conference on Artificial Intelligence (AAAI), 2018.

Best Poster Award from Image Processing and Image Understanding Workshop (IPIU), Korea.

{Tae-Hyun  Oh, Kyungdon  Joo}*, Neel  Joshi, Baoyuan  Wang, In So  Kweon, Sing Bing  Kang

(*Equally contributed)

IEEE International Conference on Computer Vision, (ICCV), 2017.

Best Poster Presentation Award in IWRCV 2018.

[PDF] [Project Page]

Donghyeon  Cho, Jinsun  Park, Tae-Hyun  Oh, Yu-Wing  Tai, In So  Kweon

IEEE International Conference on Computer Vision, (ICCV), 2017.

Selected as Spotlight (Acceptance rate 2.61%)

[PDF]

Jinsoo Choi, Tae-Hyun Oh, In So Kweon

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun., 2016.

Selected as Spotlight (Accept rate 9.7%)

[PDF] [Presentation in Las Vegas] [Dataset]

{Tae-Hyun Oh, Kyungdon Joo}*, Junsik Kim, In So Kweon   (*Equally contributed)

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun., 2016.

Hyowon Ha, Tae-Hyun Oh, In So Kweon

International Conference on 3D Vision (3DV), Oct., 2015.

Kyungdon Joo, Namil Kim, Tae-Hyun Oh, In So Kweon

IEEE International Conference on Image Processing (ICIP), Sep., 2015.

Selected as the Top 10% paper in ICIP 2015.

Tae-Hyun Oh, Yasuyuki Matsushita, Yu-Wing Tai, In So Kweon

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun., 2015

Received Gold Prize (Acceptance rate 0.8%), 21th HumanTech Paper Award by Samsung. 

[Project page]

SoonMin Hwang, Tae-Hyun Oh, In So Kweon

Workshop in conjunction with the 12th Asian Conference on Computer Vision (ACCVW), 2014

Min Jung Kim, Tae-Hyun Oh, In So Kweon

IEEE International Conference on Image Processing (ICIP), Oct., 2014

Jongwon Choi, Hyeongwoo Kim, Tae-Hyun Oh, In So Kweon

IEEE International Conference on Image Processing (ICIP), Oct., 2014

Tae-Hyun Oh, Hyeongwoo Kim, Yu-Wing Tai, Jean-Chales Bazin, In So Kweon

IEEE International Conference on Computer Vision, (ICCV), Dec., 2013.

Tae-Hyun Oh, Joon-Young Lee, In So Kweon

IEEE International Conference on Image Processing (ICIP), Sep., 2013