1 code implementation • 27 Apr 2024 • Zhixiong Huang, Xinying Wang, Jinjiang Li, Shenglan Liu, Lin Feng
In this work, we investigate injecting the depth prior into the deep UIE model for more precise scene enhancement capability.
1 code implementation • 27 Sep 2023 • Wujun Wen, Jinrong Zhang, Shenglan Liu, Yunheng Li, QiFeng Li, Lin Feng
The end-to-end SVTAS which regard TAS as an action segment clustering task can expand the application scenarios of TAS; and RL is used to alleviate the problem of inconsistent optimization objective and direction.
no code implementations • CVPR 2023 • Kaiyuan Liu, Yunheng Li, Shenglan Liu, Chenwei Tan, Zihang Shao
Timestamp supervised temporal action segmentation (TSTAS) is more cost-effective than fully supervised counterparts.
1 code implementation • 18 Aug 2022 • Lianyu Hu, Shenglan Liu, Wei Feng
In such conditions, short-term dependencies are few formally considered, which are critical for classifying similar actions.
Ranked #1 on Skeleton Based Action Recognition on Kinetics-400
1 code implementation • Neurocomputing 2021 • Yunheng Li, Zhuben Dong, Kaiyuan Liu, Lin Feng, Lianyu Hu, Jie Zhu, Li Xu, YuHan Wang, Shenglan Liu
Due to boundary ambiguity and over-segmentation issues, identifying all the frames in long untrimmed videos is still challenging.
Ranked #12 on Action Segmentation on GTEA
no code implementations • 5 Feb 2021 • Shuliang Xu, Shenglan Liu, Lin Feng
However, most self-supervised graph neural networks only use adjacency matrix as the input topology information of graph and cannot obtain too high-order information since the number of layers of graph neural network is fairly limited.
no code implementations • 22 Nov 2020 • Shenglan Liu, Yang Yu
As a widely used method in machine learning, principal component analysis (PCA) shows excellent properties for dimensionality reduction.
no code implementations • 29 Jun 2020 • Shenglan Liu, Yang Yu
Manifold Learning occupies a vital role in the field of nonlinear dimensionality reduction and its ideas also serve for other relevant methods.
no code implementations • 16 Sep 2019 • Shenglan Liu, Yang Yu, Yang Liu, Hong Qiao, Lin Feng, Jiashi Feng
Manifold learning now plays a very important role in machine learning and many relevant applications.
no code implementations • 10 May 2019 • Lin Feng, Caifeng Liu, Shenglan Liu, Huibing Wang
Traditional face alignment based on machine learning usually tracks the localizations of facial landmarks employing a static model trained offline where all of the training data is available in advance.
1 code implementation • 24 Jan 2019 • Caifeng Liu, Lin Feng, Guochao Liu, Huibing Wang, Shenglan Liu
Music genre recognition based on visual representation has been successfully explored over the last years.
1 code implementation • 11 Jan 2019 • Shenglan Liu, Dong Jiang, Lin Feng, Feilong Wang, Zhanbo Feng, Xiang Liu, Shuai Guo, Bingjun Li, Yuchen Cong
We finally design a Rubik's cube robot and construct a dataset to illustrate the efficiency and effectiveness of our online methods and to indicate the ineffectiveness of offline method by color drifting in our dataset.
no code implementations • 8 Nov 2018 • Shenglan Liu, Shuai Guo, Hong Qiao, Yang Wang, Bin Wang, Wenbo Luo, Mingming Zhang, Keye Zhang, Bixuan Du
As RGB view and depth view lie in different spaces, a new distance metric bag of neighbors (BON) used in MvLE can get the similar distributions of the two views.
no code implementations • 25 Oct 2018 • Shenglan Liu, Xiang Liu, Yang Liu, Lin Feng, Hong Qiao, Jian Zhou, Yang Wang
Supervised learning methods are widely used in machine learning.
no code implementations • 12 Nov 2017 • Youchen Du, Shenglan Liu, Lin Feng, Menghui Chen, Jie Wu
The recent introduction of depth cameras like Leap Motion Controller allows researchers to exploit the depth information to recognize hand gesture more robustly.
no code implementations • 30 Oct 2017 • Lin Feng, Shuliang Xu, Feilong Wang, Shenglan Liu
Extreme learning machine (ELM) is a new single hidden layer feedback neural network.
no code implementations • 24 Mar 2017 • Shenglan Liu, Muxin Sun, Wei Wang, Feilong Wang
In this paper, we use Kinect and propose a feature graph fusion (FGF) for robot recognition.
no code implementations • 11 Mar 2017 • Shenglan Liu, Jun Wu, Lin Feng, Feilong Wang
This paper proposed a new explicit nonlinear dimensionality reduction using neural networks for image retrieval tasks.
no code implementations • 24 Sep 2016 • Shenglan Liu, Muxin Sun, Lin Feng, Yang Liu, Jun Wu
Multi-feature fusion ranking can be utilized to improve the ranking list of query.
no code implementations • 24 Sep 2016 • Shenglan Liu, Jun Wu, Lin Feng, Yang Liu, Hong Qiao, Wenbo Luo Muxin Sun, Wei Wang
Incompatibility of image descriptor and ranking is always neglected in image retrieval.