no code implementations • 25 Jan 2024 • Chuankun Li, Shuai Li, Yanbo Gao, Ping Chen, Jian Li, Wanqing Li
To address this problem, the overfitting mechanism behind the unsupervised learning for skeleton based action recognition is first investigated.
no code implementations • 16 Sep 2023 • Yueyang Li, Yonghong Hou, Wanqing Li
Point-level weakly-supervised temporal action localization (PWTAL) aims to localize actions with only a single timestamp annotation for each action instance.
Pseudo Label Weakly-supervised Temporal Action Localization +1
no code implementations • 6 Oct 2022 • Zhimin Gao, Peitao Wang, Pei Lv, Xiaoheng Jiang, Qidong Liu, Pichao Wang, Mingliang Xu, Wanqing Li
Besides, these methods directly calculate the pair-wise global self-attention equally for all the joints in both the spatial and temporal dimensions, undervaluing the effect of discriminative local joints and the short-range temporal dynamics.
1 code implementation • 21 Sep 2022 • Zihui Guo, Yonghong Hou, Pichao Wang, Zhimin Gao, Mingliang Xu, Wanqing Li
It has been studied either using first person vision (FPV) or third person vision (TPV).
no code implementations • 6 Aug 2022 • Haoyuan Zhang, Yonghong Hou, Wenjing Zhang, Wanqing Li
The CPM identifies non-self positives in a contextual queue to boost learning.
no code implementations • 17 Jun 2022 • Zhiyi Gao, Yonghong Hou, Wanqing Li, Zihui Guo, Bin Yu
This approach has been challenged by the semantic gap between the visual space and semantic space.
no code implementations • CVPR 2022 • Jianjun Lei, Xiangrui Liu, Bo Peng, Dengchao Jin, Wanqing Li, Jingxiao Gu
Existing learning-based stereo compression methods usually adopt a unidirectional approach to encoding one image independently and the other image conditioned upon the first.
no code implementations • 1 Dec 2021 • Jie Zhu, Bo Peng, Wanqing Li, Haifeng Shen, Zhe Zhang, Jianjun Lei
It is built upon Transformer and is capable of extracting dense features with global context and 3D consistency, which are crucial to achieving reliable matching for MVS.
1 code implementation • 13 Nov 2021 • Shuangyan Miao, Yonghong Hou, Zhimin Gao, Mingliang Xu, Wanqing Li
This paper proposes a new graph convolutional operator called central difference graph convolution (CDGC) for skeleton based action recognition.
no code implementations • 29 Oct 2021 • Bingzheng Liu, Jianjun Lei, Bo Peng, Chuanbo Yu, Wanqing Li, Nam Ling
In particular, the network consists of a token transformation module (TTM) that facilities the transformation of the features extracted from a source viewpoint image into an intrinsic representation with respect to a pre-defined reference pose and a view generation module (VGM) that synthesizes an arbitrary view from the representation.
no code implementations • 27 Sep 2021 • Xun Yao, Junlong Ma, Xinrong Hu, Junping Liu, Jie Yang, Wanqing Li
The task of multiple choice question answering (MCQA) refers to identifying a suitable answer from multiple candidates, by estimating the matching score among the triple of the passage, question and answer.
no code implementations • 25 Apr 2021 • Umair Iqbal, Johan Barthelemy, Wanqing Li, Pascal Perez
Positive value of $R^{2}$ score indicated the presence of correlation between visual features and hydraulic blockage and suggested that both can be interrelated with each other.
no code implementations • 21 Apr 2021 • Umair Iqbal, Johan Barthelemy, Wanqing Li, Pascal Perez
Blockage of culverts by transported debris materials is reported as main contributor in originating urban flash floods.
no code implementations • 6 Mar 2021 • Umair Iqbal, Johan Barthelemy, Pascal Perez, Wanqing Li
Hydraulic blockage of cross-drainage structures such as culverts is considered one of main contributor in triggering urban flash floods.
no code implementations • 22 Jan 2021 • Chuankun Li, Shuai Li, Yanbo Gao, Xiang Zhang, Wanqing Li
The self-attention based graph convolutional network has a dynamic self-attention mechanism to adaptively exploit the relationships of all hand joints in addition to the fixed topology and local feature extraction in the GCN.
no code implementations • 5 Jan 2021 • Xiangyu Li, Yonghong Hou, Pichao Wang, Zhimin Gao, Mingliang Xu, Wanqing Li
In this paper, we propose a \textbf{Tr}ansformer-based RGB-D \textbf{e}gocentric \textbf{a}ction \textbf{r}ecognition framework, called Trear.
no code implementations • 8 Dec 2020 • Xiangyu Li, Yonghong Hou, Pichao Wang, Zhimin Gao, Mingliang Xu, Wanqing Li
In this paper, we propose a method consisting of two camera pose estimators that deal with the information from pairwise images and a short sequence of images respectively.
no code implementations • 1 Nov 2020 • Beidi Zhao, Shuai Li, Yanbo Gao, Chuankun Li, Wanqing Li
Smartphone sensors based human activity recognition is attracting increasing interests nowadays with the popularization of smartphones.
no code implementations • 29 Oct 2020 • Haoyuan Zhang, Yonghong Hou, Pichao Wang, Zihui Guo, Wanqing Li
The recently developed DARTS (Differentiable Architecture Search) is adopted to search for an effective network architecture that is built upon the two types of cells.
no code implementations • 26 May 2020 • Jing Zhang, Wanqing Li, Lu Sheng, Chang Tang, Philip Ogunbona
Given an existing system learned from previous source domains, it is desirable to adapt the system to new domains without accessing and forgetting all the previous domains in some applications.
1 code implementation • 11 Oct 2019 • Shuai Li, Wanqing Li, Chris Cook, Yanbo Gao
Recurrent neural networks (RNNs) are known to be difficult to train due to the gradient vanishing and exploding problems and thus difficult to learn long-term patterns and construct deep networks.
no code implementations • 16 Apr 2018 • Shuai Li, Dinei Florencio, Wanqing Li, Yaqin Zhao, Chris Cook
Conventional methods cannot distinguish the foreground from background due to the small differences between them and thus suffer from under-detection of the camouflaged foreground objects.
no code implementations • 25 Mar 2018 • Jing Zhang, Wanqing Li, Philip Ogunbona
This paper presents a novel multi-task learning-based method for unsupervised domain adaptation.
1 code implementation • CVPR 2018 • Jing Zhang, Zewei Ding, Wanqing Li, Philip Ogunbona
This paper proposes an importance weighted adversarial nets-based method for unsupervised domain adaptation, specific for partial domain adaptation where the target domain has less number of classes compared to the source domain.
no code implementations • 17 Mar 2018 • Pichao Wang, Wanqing Li, Zhimin Gao, Chang Tang, Philip Ogunbona
This paper proposes three simple, compact yet effective representations of depth sequences, referred to respectively as Dynamic Depth Images (DDI), Dynamic Depth Normal Images (DDNI) and Dynamic Depth Motion Normal Images (DDMNI), for both isolated and continuous action recognition.
11 code implementations • CVPR 2018 • Shuai Li, Wanqing Li, Chris Cook, Ce Zhu, Yanbo Gao
Experimental results have shown that the proposed IndRNN is able to process very long sequences (over 5000 time steps), can be used to construct very deep networks (21 layers used in the experiment) and still be trained robustly.
Ranked #10 on Language Modelling on Penn Treebank (Character Level)
no code implementations • 5 Dec 2017 • Pichao Wang, Wanqing Li, Jun Wan, Philip Ogunbona, Xinwang Liu
Differently from the conventional ConvNet that learns the deep separable features for homogeneous modality-based classification with only one softmax loss function, the c-ConvNet enhances the discriminative power of the deeply learned features and weakens the undesired modality discrepancy by jointly optimizing a ranking loss and a softmax loss for both homogeneous and heterogeneous modalities.
no code implementations • 31 Oct 2017 • Pichao Wang, Wanqing Li, Philip Ogunbona, Jun Wan, Sergio Escalera
Specifically, deep learning methods based on the CNN and RNN architectures have been adopted for motion recognition using RGB-D data.
no code implementations • 11 Jul 2017 • Shuai Li, Dinei Florencio, Yaqin Zhao, Chris Cook, Wanqing Li
This paper proposes a texture guided weighted voting (TGWV) method which can efficiently detect foreground objects in camouflaged scenes.
no code implementations • 6 Jul 2017 • Chuankun Li, Pichao Wang, Shuang Wang, Yonghong Hou, Wanqing Li
Recent methods based on 3D skeleton data have achieved outstanding performance due to its conciseness, robustness, and view-independent representation.
no code implementations • 16 Jun 2017 • Shuai Li, Wanqing Li, Chris Cook, Ce Zhu, Yanbo Gao
Such a network with learnable pooling function is referred to as a fully trainable network (FTN).
no code implementations • CVPR 2017 • Jing Zhang, Wanqing Li, Philip Ogunbona
This paper presents a novel unsupervised domain adaptation method for cross-domain visual recognition.
Ranked #5 on Domain Adaptation on Office-Caltech
no code implementations • 11 May 2017 • Jing Zhang, Wanqing Li, Philip Ogunbona, Dong Xu
This paper takes a problem-oriented perspective and presents a comprehensive review of transfer learning methods, both shallow and deep, for cross-dataset visual recognition.
1 code implementation • 2 May 2017 • Zewei Ding, Pichao Wang, Philip O. Ogunbona, Wanqing Li
The proposed method achieved state-of-the-art performance on NTU RGB+D dataset for 3D human action analysis.
Ranked #105 on Skeleton Based Action Recognition on NTU RGB+D (Accuracy (CV) metric)
no code implementations • CVPR 2017 • Pichao Wang, Wanqing Li, Zhimin Gao, Yuyao Zhang, Chang Tang, Philip Ogunbona
Based on the scene flow vectors, we propose a new representation, namely, Scene Flow to Action Map (SFAM), that describes several long term spatio-temporal dynamics for action recognition.
Ranked #3 on Hand Gesture Recognition on ChaLearn val
no code implementations • 7 Jan 2017 • Pichao Wang, Wanqing Li, Song Liu, Zhimin Gao, Chang Tang, Philip Ogunbona
This paper proposes three simple, compact yet effective representations of depth sequences, referred to respectively as Dynamic Depth Images (DDI), Dynamic Depth Normal Images (DDNI) and Dynamic Depth Motion Normal Images (DDMNI).
Ranked #2 on Hand Gesture Recognition on ChaLearn val
no code implementations • 30 Dec 2016 • Pichao Wang, Wanqing Li, Chuankun Li, Yonghong Hou
Convolutional Neural Networks (ConvNets) have recently shown promising performance in many computer vision tasks, especially image-based recognition.
Ranked #1 on Skeleton Based Action Recognition on Gaming 3D (G3D)
no code implementations • 8 Nov 2016 • Pichao Wang, Zhaoyang Li, Yonghong Hou, Wanqing Li
Recently, Convolutional Neural Networks (ConvNets) have shown promising performances in many computer vision tasks, especially image-based recognition.
no code implementations • 27 Oct 2016 • Jianjia Zhang, Lei Wang, Luping Zhou, Wanqing Li
A variety of methods have been proposed to boost its efficacy, with some recent ones resorting to nonlinear kernel technique.
no code implementations • 22 Aug 2016 • Pichao Wang, Wanqing Li, Song Liu, Yuyao Zhang, Zhimin Gao, Philip Ogunbona
This paper addresses the problem of continuous gesture recognition from sequences of depth maps using convolutional neutral networks (ConvNets).
no code implementations • 1 Apr 2016 • Lijuan Zhou, Wanqing Li, Philip Ogunbona
This paper presents a novel method for learning a pose lexicon comprising semantic poses defined by textual instructions and their associated visual poses defined by visual features.
no code implementations • 22 Feb 2016 • Song Liu, Wanqing Li, Philip Ogunbona, Yang-Wai Chow
This paper presents an extension to the KinectFusion algorithm which allows creating simplified 3D models with high quality RGB textures.
no code implementations • 22 Feb 2016 • Song Liu, Wanqing Li, Stephen Davis, Christian Ritz, Hongda Tian
Product layout is extracted from an input image by means of unsupervised recurring pattern detection and matched via graph matching with the expected product layout specified by a planogram to measure the level of compliance.
no code implementations • 1 Feb 2016 • Pichao Wang, Zhaoyang Li, Yonghong Hou, Wanqing Li
This paper proposes a new framework for RGB-D-based action recognition that takes advantages of hand-designed features from skeleton data and deeply learned features from depth maps, and exploits effectively both the local and global temporal information.
no code implementations • 21 Jan 2016 • Jing Zhang, Wanqing Li, Philip O. Ogunbona, Pichao Wang, Chang Tang
Human action recognition from RGB-D (Red, Green, Blue and Depth) data has attracted increasing attention since the first work reported in 2010.
no code implementations • ICCV 2015 • Lei Wang, Jianjia Zhang, Luping Zhou, Chang Tang, Wanqing Li
It proposes an open framework to use the kernel matrix over feature dimensions as a generic representation and discusses its properties and advantages.
no code implementations • 10 Nov 2015 • Chang Tang, Pichao Wang, Wanqing Li
This paper presents a fast yet effective method to recognize actions from stream of noisy skeleton data, and a novel weighted covariance descriptor is adopted to accumulate evidence.
no code implementations • IEEE Transactions on Human-Machine Systems 2016 2015 • Pichao Wang, Wanqing Li, Zhimin Gao, Jing Zhang, Chang Tang, Philip Ogunbona
In addition, the method was evaluated on the large dataset constructed from the above datasets.
Ranked #9 on Multimodal Activity Recognition on EV-Action
no code implementations • 20 Jan 2015 • Pichao Wang, Wanqing Li, Zhimin Gao, Jing Zhang, Chang Tang, Philip Ogunbona
The results show that our approach can achieve state-of-the-art results on the individual datasets and without dramatical performance degradation on the Combined Dataset.
no code implementations • 14 Sep 2014 • Pichao Wang, Wanqing Li, Philip Ogunbona, Zhimin Gao, Hanling Zhang
These parts are referred to as Frequent Local Parts or FLPs.
1 code implementation • 8 Jul 2014 • Jianjia Zhang, Lei Wang, Luping Zhou, Wanqing Li
A comprehensive experimental study is conducted on a variety of image classification tasks to compare our proposed discriminative Stein kernel with the original Stein kernel and other commonly used methods for evaluating the similarity between SPD matrices.
no code implementations • CVPR 2013 • Lei Wang, Jianjia Zhang, Luping Zhou, Wanqing Li
Distributional word clustering merges the words having similar probability distributions to attain reliable parameter estimation, compact classification models and even better classification performance.