Hyung-Il Kim

Electronics and Telecommunications Research Institute | ETRI · Visual Intelligence Research Section

Although gaze estimation methods have been developed with deep learning techniques, there has been no such approach as aim to attain accurate performance in low-resolution face images with a pixel width of 50 pixels or less. To solve a limitation under the challenging low-resolution conditions, we propose a high-frequency attentive super-resolved g...

Visual Speech Recognition (VSR) aims to infer speech into text depending on lip movements alone. As it focuses on visual information to model the speech, its performance is inherently sensitive to personal lip appearances and movements, and this makes the VSR models show degraded performance when they are applied to unseen speakers. In this paper,...

Since many safety-critical systems, such as surgical robots and autonomous driving cars operate in unstable environments with sensor noise and incomplete data, it is desirable for object detectors to take the localization uncertainty into account. However, there are several limitations of the existing uncertainty estimation methods for anchor-based...

For the past decades, face recognition (FR) has been actively studied in computer vision and pattern recognition society. Recently, due to the advances in deep learning, the FR technology shows high performance for most of the benchmark datasets. However, when the FR algorithm is applied to a real-world scenario, the performance has been known to b...

Although gaze estimation methods have been developed with deep learning techniques, there has been no such approach as aim to attain accurate performance in low-resolution face images with a pixel width of 50 pixels or less. To solve a limitation under the challenging low-resolution conditions, we propose a high-frequency attentive super-resolved g...

For the past decades, face recognition (FR) has been actively studied in computer vision and pattern recognition society. Recently, due to the advances in deep learning, the FR technology shows high performance for most of the benchmark datasets. However, when the FR algorithm is applied to a real-world scenario, the performance has been known to b...

Video classification researches have recently attracted attention in the fields of temporal modeling and efficient 3D convolutional architectures. However, the temporal modeling methods are not efficient, and there is little interest in how to deal with temporal modeling in the 3D efficient architectures. To build an efficient 3D architecture for t...

Our work addresses long-term motion context issues for predicting future frames. To predict the future precisely, it is required to capture which long-term motion context (e.g., walking or running) the input motion (e.g., leg movement) belongs to. The bottlenecks arising when dealing with the long-term motion context are: (i) how to predict the lon...

Images captured by cameras in closed-circuit televisions and black boxes in cities have low or poor quality owing to lens distortion and optical blur. Moreover, actual images acquired through imaging sensors of cameras such as charge-coupled devices and complementary metal-oxide-semiconductors generally include noise with spatial-variant characteri...

Face detection is the first step in a wide range of face applications. However, detecting faces in the wild is still a challenging task due to the wide range of variations in pose, scale, and occlusions. Recently, many deep learning methods have been proposed for face detection. However, further improvements are required in the wild. Another import...

Human action recognition (HAR) is a core technology for human–computer interaction and video understanding, attracting significant research and development attention in the field of computer vision. However, in uncontrolled environments, achieving effective HAR is still challenging, due to the widely varying nature of video content. In previous res...

Face recognition has received a great deal of attention for the wide range of applications in real-world scenario. In this scenario, mismatches (so called heterogeneity) in terms of resolution and illumination between gallery and test face images are inevitable due to the different capturing conditions. In order to deal with the mismatch problem, w...

In real-world face recognition (FR) scenario, illumination variation has been known to be a challenging problem because face appearance dramatically changes depending on the illumination conditions. In order to deal with this illumination variation effectively, an illumination-reduced feature learning method using deep convolutional neural network...

Automatic face recognition (FR) under uncontrolled environments has attracted considerable research attention. In the uncontrolled environments, pose variation is known as one of the crucial factors that influences FR performance. In this paper, we propose a discriminative and pose-robust feature representation using the multi-task learning in deep...

Recently, high-performance face recognition has attracted research attention in real-world scenarios. Thanks to the advances in sensor technology, face recognition system equipped with multiple sensors has been widely researched. Among them, face recognition system with near-infrared imagery has been one important research topic. In this paper, com...

In video surveillance system, the exposure of a person`s face is a serious threat to personal privacy. To protect the personal privacy in large amount of videos, an automatic face detection method is required to locate and mask the person`s face. However, in real-world surveillance videos, the effectiveness of existing face detection methods could...

Considerable research efforts have been made for face recognition in various real-world applications. However, degraded face images, acquired in the real-world, make face recognition difficult. In this paper, we propose a new face image quality assessment that aims to realize a robust and reliable face recognition system. The proposed method consid...

In recent years, high-speed signal reconstruction with sub-Nyquist sampling have attracted the attention of researchers in the signal processing field. Nonetheless, such methods have been limited either by the need to utilize multiple cameras, or relying on newly designed imaging hardware. In this paper, we propose a high-speed periodic motion reco...

Recently the development of intelligent surveillance system increasingly requires low power consumption. For power saving, this chapter presents an event detection function based on automatically detected human faces, which adaptively changes from low-power camera mode to high performance camera mode. We propose efficient face detection (FD) method...

Human action recognition (HAR) is at the core of human-computer interaction and video scene understanding. However, achieving effective HAR in an unconstrained environment is still a challenging task. To that end, trajectory-based video representations are currently widely used. Despite the promising levels of effectiveness achieved by these approa...

Automatic face recognition (FR) based applications in low computing power constrained systems, such as mobile and smart camera, have become particularly interesting topic in recent years. In this context, we present computationally efficient FR framework underpinning the so-called feature scalability algorithm. The proposed framework aims at implem...

Recently, the development of practical face recognition (FR) system has received much attention. Despite of its extensive study, the FR performance could be severely degraded in real-life scenario (e.g., CCTV surveillance), due to uncontrolled face image conditions of pose/alignment, blur, and brightness. This paper proposes new automated face qual...

In real world facial expression recognition, blurred face images could hamper achieving high performance due to the lack of distinct edges and textures. In this paper, we propose a new feature extraction method that is robust to blurred face images for facial expression recognition. In the proposed method, the facial feature is extracted adaptively...

Recently, the development of intelligent surveillance system increasingly requires low power consumption. For the power saving, this paper presents an event detection function based on automatically detected human faces, which adaptively convert from low power camera mode to high performance camera mode. We propose an efficient face detection (FD)...

This paper presents a new facial expression recognition (FER) which exploits the effectiveness of color information and sparse representation. For extracting face feature, we compute color vector differences between color pixels so that they can effectively capture change of face appearance (e.g., skin texture). Through comparative and extensive ex...

Although color texture features have proven to be highly effective for face analysis, the comparisons between the color texture features have not been presented in the literature. The aim of this paper is to find the best way for combining color and texture features for face analysis. For this purpose, four different approaches (proposed for face r...

Recently, the evaluating method of the bone mineral density (BMD) in X-ray absorptiometry image has been studied for the early diagnosis of osteoporosis which is known as a metabolic disease. The BMD, in general, is evaluated by calculating pixel intensity in the bone segmented regions. Accurate bone region extraction is extremely crucial for the B...