Kaixing Zhao

Prof. Dr. Kaixing Zhao

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 August 2024 in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
Verified
Journal Article
Open access
Kaixing ZhaoKaixing Zhao
Kaixing Zhao
RLRui Lai
Rui Lai
BGBin Guo
Bin Guo
LLLe Liu
Le Liu
LHLiang He
Liang He
YZYuhang Zhao
Yuhang Zhao
Accessible image exploration systems are able to help people with visual impairments (PVI) to understand image content by providing different types of interactions. With the development of computer vision technologies, image exploration systems are supporting more fine-grained image content processing, including image segmentation, description and object recognition. However, in developing countries like China, it is still rare for PVI to widely rely on such accessible system. To better understand the usage situation of accessible image exploration system in China and improve the image understanding of PVI in China, we developed AI-Vision, an Android based hierarchical accessible image exploration system supporting the generations of image general description, local object description and metadata information. Our 7-day diary study with 10 PVI verified the usability of AI-Vision and also revealed a series of design implications for improving accessible image exploration systems similar to AI-Vision.

4 February 2024
Verified
Book Chapter
Closed access
PDF file
BZBo Zhang
Bo Zhang
ZMZuheng Ming
Zuheng Ming
YLYaqian Liu
Yaqian Liu
WFWei Feng
Wei Feng
LHLiang He
Liang He
Kaixing ZhaoKaixing Zhao
Kaixing Zhao

14 November 2022 in Proceedings of the ACM on Human-Computer Interaction
Verified
Journal Article
Open access
Kaixing ZhaoKaixing Zhao
Kaixing Zhao
JMJulie Mulet
Julie Mulet
CSClara Sorita
Clara Sorita
BOBernard Oriola
Bernard Oriola
Marcos SerranoMarcos Serrano
Marcos Serrano
CJChristophe Jouffrais
Christophe Jouffrais
The lockdown period related to the COVID-19 pandemic has had a strong impact on the educational system in general, but more particularly on the special education system. Indeed, in the case of people with visual impairments, the regular tools relying heavily on images and videos were no longer usable. This specific situation highlighted an urgent need to develop tools that are accessible and that can provide solutions for remote teaching with people with VI. However, there is little work on the difficulties that this population encounters when they learn remotely as well as on the current practices of special education teachers. Such a lack of understanding limits the development of remote teaching systems that are adapted. In this paper, we conducted an online survey regarding the practices of 59 professionals giving lessons to pupils with VI, followed by a series of focus groups with special education workers facing teaching issues during the lockdown period. We followed an iterative design process where we designed successive low-fidelity prototypes to drive successive focus groups. We contribute with an analysis of the issues faced by special education teachers in this situation, and a concept to drive the future development of a tool for remote graphic-based teaching with pupils with VI.

1 August 2024 in Personal and Ubiquitous Computing
Verified
Journal Article
Closed access
PDF file
YYYafang Yang
Yafang Yang
BGBin Guo
Bin Guo
YLYunji Liang
Yunji Liang
Kaixing ZhaoKaixing Zhao
Kaixing Zhao
ZYZhiwen Yu
Zhiwen Yu

3 June 2024
Verified
Conference Paper
Open access
RXRuonan Xu
Ruonan Xu
BGBin Guo
Bin Guo
Kaixing ZhaoKaixing Zhao
Kaixing Zhao
YJYao Jing
Yao Jing
YDYasan Ding
Yasan Ding
ZYZhiwen Yu
Zhiwen Yu
Achieving robust control of quadruped robots in dynamic and complex terrains is still a challenging task. Although reinforcement learning-based control strategies have made great progress in simulation and reality, motion control of quadruped robots based on depth cameras is still worth studying. In this paper, we proposed a reinforcement learning framework that uses visual perception and proprioception as inputs to train a quadruped robot for robust control, and designed a new depth completion network called DRI-Net for completing missing depth visual information. The proposed network is based on fusing the depth features from depth maps with the contour features from RGB images and enabled the quadruped robot to accurately perceive external environment. Our main aim is to improve the decision making procedure of reinforcement learning controller and final evaluations in dynamic multi-obstacle environments demonstrated that our method outperformed the baselines in terms of multiple metrics.

11 May 2024
Verified
Conference Paper
Open access
Kaixing ZhaoKaixing Zhao
Kaixing Zhao
CWChaoyi Wu
Chaoyi Wu
TXTao Xu
Tao Xu
LHLiang He
Liang He
Marcos SerranoMarcos Serrano
Marcos Serrano
ARAnne Roudaut
Anne Roudaut
We extend grasp models to encompass one-handed interaction with arbitrary shaped touchscreen devices. Current models focus on how objects are stably held by external forces. However, with touchscreen devices, we postulate that users do a trade-off between holding securely and exploring interactively. To verify this, we first conducted a qualitative study which asked participants to grasp 3D printed objects while considering its different interactivity. Results of the study confirm our hypothesis and reveal obvious change in postures. To further verify this trade-off and design interactions, we developed a simulation software capable of computing the stability of a grasp and its reachability. We conducted the second study based on the observed predominant grasps to validate our software with a glove. Results also confirm a consistent trade-off between stability and reachability. We conclude by discussing how this research can help designing computational tools focusing on hand-held interactions with arbitrary shaped touchscreen devices.