Zobrazeno 1 - 10
of 276
pro vyhledávání: '"Tian, YingLi"'
Autor:
Vahdani, Elahe, Tian, Yingli
This paper tackles the challenge of point-supervised temporal action detection, wherein only a single frame is annotated for each action instance in the training set. Most of the current methods, hindered by the sparse nature of annotated points, str
Externí odkaz:
http://arxiv.org/abs/2310.13585
Autor:
Hassan, Saad, Seita, Matthew, Berke, Larwan, Tian, Yingli, Gale, Elaine, Lee, Sooyeon, Huenerfauth, Matt
We are releasing a dataset containing videos of both fluent and non-fluent signers using American Sign Language (ASL), which were collected using a Kinect v2 sensor. This dataset was collected as a part of a project to develop and evaluate computer v
Externí odkaz:
http://arxiv.org/abs/2207.04021
Autor:
Wang, Haiyan, Tian, Yingli
Point cloud has drawn more and more research attention as well as real-world applications. However, many of these applications (e.g. autonomous driving and robotic manipulation) are actually based on sequential point clouds (i.e. four dimensions) bec
Externí odkaz:
http://arxiv.org/abs/2204.09337
Autor:
Wang, Haiyan, Hutchcroft, Will, Li, Yuguang, Wan, Zhiqiang, Boyadzhiev, Ivaylo, Tian, Yingli, Kang, Sing Bing
In this paper, we propose a new deep learning-based method for estimating room layout given a pair of 360 panoramas. Our system, called Position-aware Stereo Merging Network or PSMNet, is an end-to-end joint layout-pose estimator. PSMNet consists of
Externí odkaz:
http://arxiv.org/abs/2203.15965
Conventional self-supervised monocular depth prediction methods are based on a static environment assumption, which leads to accuracy degradation in dynamic scenes due to the mismatch and occlusion problems introduced by object motions. Existing dyna
Externí odkaz:
http://arxiv.org/abs/2203.15174
Autor:
Vahdani, Elahe, Tian, Yingli
Publikováno v:
In Computer Vision and Image Understanding September 2024 246
Autor:
Nguyen, Kien, Fookes, Clinton, Sridharan, Sridha, Tian, Yingli, Liu, Feng, Liu, Xiaoming, Ross, Arun
The rapid emergence of airborne platforms and imaging sensors are enabling new forms of aerial surveillance due to their unprecedented advantages in scale, mobility, deployment and covert observation capabilities. This paper provides a comprehensive
Externí odkaz:
http://arxiv.org/abs/2201.03080
In recent years, semi-supervised learning has been widely explored and shows excellent data efficiency for 2D data. There is an emerging need to improve data efficiency for 3D tasks due to the scarcity of labeled 3D data. This paper explores how the
Externí odkaz:
http://arxiv.org/abs/2110.11601
Autor:
Vahdani, Elahe, Tian, Yingli
Understanding human behavior and activity facilitates advancement of numerous real-world applications, and is critical for video analysis. Despite the progress of action recognition algorithms in trimmed videos, the majority of real-world videos are
Externí odkaz:
http://arxiv.org/abs/2110.00111
Self-supervised monocular depth prediction provides a cost-effective solution to obtain the 3D location of each pixel. However, the existing approaches usually lead to unsatisfactory accuracy, which is critical for autonomous robots. In this paper, w
Externí odkaz:
http://arxiv.org/abs/2109.09628