Myungchul Kim

Youngjoon Jang, Youngtaek Oh, Jae Won Cho et al.

The goal of this work is to develop self-sufficient framework for Continuous Sign Language Recognition (CSLR) that addresses key issues of sign language recognition. These include the need for complex multi-scale features such as hands, face, and mouth for understanding, and absence of frame-level annotations. To this end, we propose (1) Divide and Focus Convolution (DFConv) which extracts both manual and non-manual features without the need for additional networks or annotations, and (2) Dense Pseudo-Label Refinement (DPLR) which propagates non-spiky frame-level pseudo-labels by combining the ground truth gloss sequence labels with the predicted sequence. We demonstrate that our model achieves state-of-the-art performance among RGB-based methods on large-scale CSLR benchmarks, PHOENIX-2014 and PHOENIX-2014-T, while showing comparable results with better efficiency when compared to other approaches that use multi-modality or extra annotations.

Kyoungjun Park, Myungchul Kim, Laihyuk Park

Video streaming services strive to support high-quality videos at higher resolutions and frame rates to improve the quality of experience (QoE). However, high-quality videos consume considerable amounts of energy on mobile devices. This paper proposes NeuSaver, which reduces the power consumption of mobile devices when streaming videos by applying an adaptive frame rate to each video chunk without compromising user experience. NeuSaver generates an optimal policy that determines the appropriate frame rate for each video chunk using reinforcement learning (RL). The RL model automatically learns the policy that maximizes the QoE goals based on previous observations. NeuSaver also uses an asynchronous advantage actor-critic algorithm to reinforce the RL model quickly and robustly. Streaming servers that support NeuSaver preprocesses videos into segments with various frame rates, which is similar to the process of creating videos with multiple bit rates in dynamic adaptive streaming over HTTP. NeuSaver utilizes the commonly used H.264 video codec. We evaluated NeuSaver in various experiments and a user study through four video categories along with the state-of-the-art model. Our experiments showed that NeuSaver effectively reduces the power consumption of mobile devices when streaming video by an average of 16.14% and up to 23.12% while achieving high QoE.

Myungchul Kim, Sanghyun Woo, Dahun Kim et al.

Pursuing a more coherent scene understanding towards real-time vision applications, single-stage instance segmentation has recently gained popularity, achieving a simpler and more efficient design than its two-stage counterparts. Besides, its global mask representation often leads to superior accuracy to the two-stage Mask R-CNN which has been dominant thus far. Despite the promising advances in single-stage methods, finer delineation of instance boundaries still remains unexcavated. Indeed, boundary information provides a strong shape representation that can operate in synergy with the fully-convolutional mask features of the single-stage segmenter. In this work, we propose Boundary Basis based Instance Segmentation(B2Inst) to learn a global boundary representation that can complement existing global-mask-based methods that are often lacking high-frequency details. Besides, we devise a unified quality measure of both mask and boundary and introduce a network block that learns to score the per-instance predictions of itself. When applied to the strongest baselines in single-stage instance segmentation, our B2Inst leads to consistent improvements and accurately parse out the instance boundaries in a scene. Regardless of being single-stage or two-stage frameworks, we outperform the existing state-of-the-art methods on the COCO dataset with the same ResNet-50 and ResNet-101 backbones.

Kyoungjun Park, Myungchul Kim

Streaming services gradually support high-quality videos for better user experience. However, streaming high-quality video on mobile devices consumes a considerable amount of energy. This paper presents the design and prototype of EVSO, which achieves power saving by applying adaptive frame rates to parts of videos with a little degradation of the user experience. EVSO utilizes a novel perceptual similarity measurement method based on human visual perception specialized for a video encoder. We also extend the media presentation description, in which the video content is selected based only on the network bandwidth, to allow for additional consideration of the user's battery status. EVSO's streaming server preprocesses the video into several processed videos according to the similarity intensity of each part of the video and then provides the client with the processed video suitable for the network bandwidth and the battery status of the client's mobile device. The EVSO system was implemented on the commonly used H.264/AVC encoder. We conduct various experiments and a user study with nine videos. Our experimental results show that EVSO effectively reduces energy consumption when mobile devices use streaming services by 22% on average and up to 27% while maintaining the quality of the user experience.