-
- 부교수
-
허재필
-
- 031-290-7965
- jaepilheo@skku.edu
-
컴퓨터 비전
관심분야
Large-Scale Image Search Similarity Search for High-Dimensional Data Object Detection and Recognition Automatic Image Tagging Collision Detection
학력
- (Ph.D.) 2015. 02. KAIST 전산학과
- (M.S.) 2010. 08. KAIST 전산학과
- (B.S.) 2008. 02. KAIST 전산학과
약력/경력
- 2017. 03. - 현재 성균관대학교 소프트웨어학과 부교수, 수원, 대한민국
- 2015. 12. - 2017. 02. 연구원, ETRI (한국전자통신연구원), 대전, 대한민국
- 2015. 02. - 2015. 11. Postdoctoral Researcher, KAIST, 대전, 대한민국
- 2014. 07. - 2014. 10. Research Intern, Adobe, San Jose, CA, US
- 2013. 12. - 2014. 03. Research Intern, Adobe, San Jose, CA, US
학술지 논문
- (2021) Pixel-level kernel estimation for blind super-resolution. IEEE ACCESS. 9
- (2020) Pseudo Conditional Regularization for Inverse Mapping of GANs. IEEE ACCESS. 8, 1
- (2020) Mutually Orthogonal Softmax Axes for Cross-Domain Retrieval. IEEE ACCESS. 8, 1
- (2019) Learning Coarse and Fine Features for Precise Temporal Action Localization. IEEE ACCESS. 7, 1
- (2019) Distance Encoded Product Quantization for Approximate K-Nearest Neighbor Search in High-Dimensional Space. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE. 41, 9
- (2019) Content-Aware Focal Plane Selection and Proposals for Object Tracking on Plenoptic Image Sequences. SENSORS. 19, 1
- (2017) Rank-based voting with inclusion relationship for accurate image search. VISUAL COMPUTER. 33, 6-8
- (2016) Shortlist Selection with Residual-Aware Distance Estimator for K-Nearest Neighbor Search. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. 1, 1
- (2015) Spherical Hashing: Binary Code Embedding with Hyperspheres. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE. 37, 11
- (2014) Distance Encoded Product Quantization. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014. 1, 1
- (2014) Quadra-embedding: Binary code embedding with low quantization error. COMPUTER VISION AND IMAGE UNDERSTANDING. 125, 1
- (2012) Spherical Hashing. IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2012. 1, 1
학술회의논문
- (2022) Difficulty-Aware Simulator for Open Set Recognition. European Conference on Computer Vision. 이스라엘
- (2022) Tailoring Self-Supervision for Supervised Learning. European Conference on Computer Vision. 이스라엘
- (2022) Local Attention Pyramid for Scene Image Generation. Conference on Computer Vision and Pattern Recognition. 미국
- (2022) Task Discrepancy Maximization for Fine-grained Few-Shot Classification. Conference on Computer Vision and Pattern Recognition. 미국
- (2021) Collaborative Learning with Disentangled Features for Zero-shot Domain Adaptation. International Conference on Computer Vision. 캐나다
- (2021) Product Quantizer Aware Inverted Index for Scalable Nearest Neighbor Search. International Conference on Computer Vision. 캐나다
- (2021) Self-Supervised Video GANs: Learning for Appearance Consistency and Motion Coherency. Conference on Computer Vision and Pattern Recognition. 미국
- (2020) MCM: 레이블 노이즈에 강건한 Mix Contrastive-Match. 2020년 한국소프트웨어종합학술대회. 대한민국
- (2020) ROI pooling을 통한 One-stage object detection의 수용장 크기 개선. 2020년 한국소프트웨어종합학술대회. 대한민국
- (2020) 심층신경망의 불확실성 기반 열린 집합 도메인 적응. 2020년 한국소프트웨어종합학술대회. 대한민국
- (2020) 저해상도 이미지 기반 손실 함수를 활용한 해상도 개선. 2020년 한국소프트웨어종합학술대회. 대한민국
- (2020) VarSR: Variational Super-Resolution Network for Very Low Resolution Images. European Conference on Computer Vision. 영국
- (2019) Accurate and consistent depth estimation for light field camera arrays. PROCEEDINGS OF SPIE. 미국
- (2018) Plenoptic Imaging Techniques for Improving Accuracy and Robustness of Object Tracking. Proc. SPIE, Three-Dimensional Imaging, Visualization, and Display 2018. 미국