1 code implementation • 29 Nov 2023 • Ziqiao Peng, Wentao Hu, Yue Shi, Xiangyu Zhu, Xiaomei Zhang, Hao Zhao, Jun He, Hongyan Liu, Zhaoxin Fan
A lifelike talking head requires synchronized coordination of subject identity, lip movements, facial expressions, and head poses.
no code implementations • 17 Nov 2023 • Jun He, Siang Yew Chong, Xin Yao
In this method, an EA is modeled as a Markov chain on a digraph.
no code implementations • 16 Oct 2023 • Kaixing Yang, Xukun Zhou, Xulong Tang, Ran Diao, Hongyan Liu, Jun He, Zhaoxin Fan
Dance and music are closely related forms of expression, with mutual retrieval between dance videos and music being a fundamental task in various fields like education, art, and sports.
no code implementations • 15 Sep 2023 • Xukun Zhou, Zhenbo Song, Jun He, Hongyan Liu, Zhaoxin Fan
Scene Graph Generation is a critical enabler of environmental comprehension for autonomous robotic systems.
no code implementations • 2 Sep 2023 • Jun He, Yuren Zhou
An open question regarding the fitness level method is what are the tightest lower and upper time bounds that can be constructed based on transition probabilities between fitness levels.
1 code implementation • 19 Jun 2023 • Ziqiao Peng, Yihao Luo, Yue Shi, Hao Xu, Xiangyu Zhu, Jun He, Hongyan Liu, Zhaoxin Fan
To enhance the visual accuracy of generated lip movement while reducing the dependence on labeled data, we propose a novel framework SelfTalk, by involving self-supervision in a cross-modals network system to learn 3D talking faces.
no code implementations • 25 Mar 2023 • Xukun Zhou, Jiwei Li, Tianwei Zhang, Lingjuan Lyu, Muqiao Yang, Jun He
Backdoor attack aims at inducing neural models to make incorrect predictions for poison data while keeping predictions on the clean dataset unchanged, which creates a considerable threat to current natural language processing (NLP) systems.
2 code implementations • ICCV 2023 • Ziqiao Peng, HaoYu Wu, Zhenbo Song, Hao Xu, Xiangyu Zhu, Jun He, Hongyan Liu, Zhaoxin Fan
Specifically, we introduce the emotion disentangling encoder (EDE) to disentangle the emotion and content in the speech by cross-reconstructed speech signals with different emotion labels.
1 code implementation • 22 Dec 2022 • Zhaoxin Fan, Kaixing Yang, Min Zhang, Zhenbo Song, Hongyan Liu, Jun He
In stage 1, a novel devices detection and tracking scheme is introduced, which accurately locate the height limit devices in the left or right image.
1 code implementation • 30 Nov 2022 • Zhaoxin Fan, Yuqing Pan, Hao Xu, Zhenbo Song, Zhicheng Wang, Kejian Wu, Hongyan Liu, Jun He
These novel elements of FuRPE not only serve to further refine the model but also to reduce potential biases that may arise from inaccuracies in pseudo labels, thereby optimizing the network's training process and enhancing the robustness of the model.
no code implementations • 23 Sep 2022 • Zhaoxin Fan, Zhenbo Song, Hongyan Liu, Jun He
Large-scale place recognition is a fundamental but challenging task, which plays an increasingly important role in autonomous driving and robotics.
no code implementations • 17 Sep 2022 • Zhaoxin Fan, Fengxin Li, Hongyan Liu, Jun He, Xiaoyong Du
In this paper, we research the new topic of object effects recommendation in micro-video platforms, which is a challenging but important task for many practical applications such as advertisement insertion.
1 code implementation • 1 Sep 2022 • ZiCheng Zhang, Wei Sun, Xiongkuo Min, Quan Zhou, Jun He, Qiyuan Wang, Guangtao Zhai
In specific, we split the point clouds into sub-models to represent local geometry distortions such as point shift and down-sampling.
Ranked #1 on Point Cloud Quality Assessment on SJTU-PCQA
no code implementations • 24 Jul 2022 • Zhong-Xue Gao, Tian-Tian Li, Han-Yu Jiang, Jun He
The synchronization of RyRs is found important to generate a global calcium oscillation.
no code implementations • 12 Jul 2022 • Ziyang Zong, Jun He, Lei Zhang, Hai Huan
However, for source free UDA, the source domain data can not be accessed during adaptation, which poses great challenge of measuring the domain gap.
no code implementations • 9 Jun 2022 • Wei Lu, Wei Sun, Xiongkuo Min, Wenhan Zhu, Quan Zhou, Jun He, Qiyuan Wang, ZiCheng Zhang, Tao Wang, Guangtao Zhai
In this paper, we propose a deep learning-based BIQA model for 4K content, which on one hand can recognize true and pseudo 4K content and on the other hand can evaluate their perceptual visual quality.
no code implementations • 20 Apr 2022 • Zhaoxin Fan, Yulin He, Zhicheng Wang, Kejian Wu, Hongyan Liu, Jun He
Real-world sensors often produce incomplete, irregular, and noisy point clouds, making point cloud completion increasingly important.
no code implementations • 4 Apr 2022 • Zhaoxin Fan, Zhenbo Song, Jian Xu, Zhicheng Wang, Kejian Wu, Hongyan Liu, Jun He
Recently, RGBD-based category-level 6D object pose estimation has achieved promising improvement in performance, however, the requirement of depth information prohibits broader applications.
no code implementations • 16 Dec 2021 • Tianfeng Liu, Yangrui Chen, Dan Li, Chuan Wu, Yibo Zhu, Jun He, Yanghua Peng, Hongzheng Chen, Hongzhi Chen, Chuanxiong Guo
Extensive experiments on various GNN models and large graph datasets show that BGL significantly outperforms existing GNN training systems by 20. 68x on average.
no code implementations • 20 Nov 2021 • Zhaoxin Fan, Zhengbo Song, Jian Xu, Zhicheng Wang, Kejian Wu, Hongyan Liu, Jun He
ACR-Pose consists of a Reconstructor and a Discriminator.
no code implementations • 29 Sep 2021 • Cong Wang, Jun He, Yu Chen, Xiufen Zou
Although differential evolution (DE) algorithms perform well on a large variety of complicated optimization problems, only a few theoretical studies are focused on the working principle of DE algorithms.
1 code implementation • COLING 2022 • Nan Wang, Jiwei Li, Yuxian Meng, Xiaofei Sun, Han Qiu, Ziyao Wang, Guoyin Wang, Jun He
We formalize predicate disambiguation as multiple-choice machine reading comprehension, where the descriptions of candidate senses of a given predicate are used as options to select the correct sense.
Ranked #1 on Semantic Role Labeling on CoNLL 2005
no code implementations • 29 Aug 2021 • Zhaoxin Fan, Zhenbo Song, Wenping Zhang, Hongyan Liu, Jun He, Xiaoyong Du
Third, we apply these kernels to previous point cloud features to generate new features, which is the well-known SO(3) mapping process.
1 code implementation • ACL 2020 • Feng Hou, Ruili Wang, Jun He, Yi Zhou
We propose a simple yet effective method, FGS2EE, to inject fine-grained semantic information into entity embeddings to reduce the distinctiveness and facilitate the learning of contextual commonality.
no code implementations • 14 Jun 2021 • Han-Yu Jiang, Jun He
At short time scale, the second open state is essential to reproduce the quasi-bistable regime, which emerges at a critical strength of connection for all three states involved in the fast processes and disappears at another critical point.
no code implementations • 29 May 2021 • Zhaoxin Fan, Yazhi Zhu, Yulin He, Qi Sun, Hongyan Liu, Jun He
Therefore, this study presents a comprehensive review of recent progress in object pose detection and tracking that belongs to the deep learning technical route.
no code implementations • 1 May 2021 • Zhaoxin Fan, Zhenbo Song, Hongyan Liu, Zhiwu Lu, Jun He, Xiaoyong Du
Point cloud-based large scale place recognition is fundamental for many applications like Simultaneous Localization and Mapping (SLAM).
Ranked #2 on 3D Place Recognition on Oxford RobotCar Dataset
no code implementations • 7 Apr 2021 • Han-Yu Jiang, Jun He
Conclusions: The prediction model based on convolutional neural network was successfully applied to select good candidates of the proteins with functions relevant to the ISR mechanism from the protein sequences which cannot be annotated by database alignment.
1 code implementation • 30 Mar 2021 • Jun He, Richang Hong, Xueliang Liu, Mingliang Xu, Qianru Sun
Few-shot classification studies the problem of quickly adapting a deep learner to understanding novel classes based on few support images.
no code implementations • 17 Feb 2021 • Tao Liu, Xin-Yang Liu, Yuan Gao, Hai Jin, Jun He, Xian-Lei Sheng, Wentao Jin, Ziyu Chen, Wei Li
Strong fluctuations in the low-$T$ quantum critical regime can give rise to a large thermal entropy change and thus significant cooling effect when approaching the QCP.
Strongly Correlated Electrons
no code implementations • 29 Jan 2021 • Jun-Tao Zhu, Lin-Qing Song, Jun He
Two states with spin parities $1/2^-$ and $3/2^-$ are predicted near the $\Xi'_c\bar{D}$, $\Xi_c\bar{D}$, and $\Xi_c^*\bar{D}$ thresholds, respectively.
High Energy Physics - Phenomenology
no code implementations • 24 Dec 2020 • Shu-Yu Liu, Shuang-Xing Zhu, Qi-Yi Wu, Chen Zhang, Peng-Bo Song, You-Guo Shi, Hao liu, Zi-Teng Liu, Jiao-Jiao Song, Fan-Ying Wu, Yin-Zou Zhao, Xiao-Fang Tang, Ya-Hua Yuan, Han Huang, Jun He, H. Y. Liu, Yu-Xia Duan, Jian-Qiao Meng
Two distinct carrier and coherent phonons relaxation processes were identified in the 5 K - 300 K range.
Materials Science Superconductivity
no code implementations • 17 Oct 2020 • Yunchao Wei, Shuai Zheng, Ming-Ming Cheng, Hang Zhao, LiWei Wang, Errui Ding, Yi Yang, Antonio Torralba, Ting Liu, Guolei Sun, Wenguan Wang, Luc van Gool, Wonho Bae, Junhyug Noh, Jinhwan Seo, Gunhee Kim, Hao Zhao, Ming Lu, Anbang Yao, Yiwen Guo, Yurong Chen, Li Zhang, Chuangchuang Tan, Tao Ruan, Guanghua Gu, Shikui Wei, Yao Zhao, Mariia Dobko, Ostap Viniavskyi, Oles Dobosevych, Zhendong Wang, Zhenyuan Chen, Chen Gong, Huanqing Yan, Jun He
The purpose of the Learning from Imperfect Data (LID) workshop is to inspire and facilitate the research in developing novel approaches that would harness the imperfect data and improve the data-efficiency during training.
no code implementations • 16 Sep 2020 • Zongyi Li, Xiaoqing Zheng, Jun He
We present RepRank, an unsupervised graph-based ranking model for extractive multi-document summarization in which the similarity between words, sentences, and word-to-sentence can be estimated by the distances between their vector representations in a unified vector space.
no code implementations • 10 Sep 2020 • Lu Liu, Zhenqiao Song, Xiaoqing Zheng, Jun He
One of the major challenges in coreference resolution is how to make use of entity-level features defined over clusters of mentions rather than mention pairs.
no code implementations • 31 Jul 2020 • Zhi-Tao Lu, Han-Yu Jiang, Jun He
It has a relatively small binding energy compared with the $d^*(2380)$ and a width close to the width of the $\Delta$ baryon, which suggests that it may be a dibaryon in a molecular state picture.
Nuclear Theory High Energy Physics - Phenomenology
no code implementations • 25 Jun 2020 • Wenbin Gao, Lei Zhang, Qi Teng, Jun He, Hao Wu
Recently, two attention methods are proposed via combining with Gated Recurrent Units (GRU) and Long Short-Term Memory (LSTM) network, which can capture the dependencies of sensing signals in both spatial and temporal domains simultaneously.
no code implementations • 5 Jun 2020 • Xin Cheng, Lei Zhang, Yin Tang, Yue Liu, Hao Wu, Jun He
For deep learning, improvements in performance have to heavily rely on increasing model size or capacity to scale to larger and larger datasets, which inevitably leads to the increase of operations.
no code implementations • 9 May 2020 • Jun He, Richang Hong, Xueliang Liu, Mingliang Xu, Zheng-Jun Zha, Meng Wang
Metric-based few-shot learning methods concentrate on learning transferable feature embedding that generalizes well from seen categories to unseen categories under the supervision of limited number of labelled instances.
no code implementations • 8 May 2020 • Yin Tang, Qi Teng, Lei Zhang, Fuhong Min, Jun He
A set of lower-dimensional filters is used as Lego bricks to be stacked for conventional filters, which does not rely on any special network structure.
no code implementations • 17 Apr 2020 • Senlin Shu, Fengmao Lv, Yan Yan, Li Li, Shuo He, Jun He
In this article, we propose to leverage the data augmentation technique to improve the performance of multi-label learning.
2 code implementations • 13 Apr 2020 • Kun Wang, Jun He, Lei Zhang
Recently, several attention mechanisms are proposed to handle the weakly labeled human activity data, which do not require accurate data annotation.
no code implementations • 29 Jan 2020 • Yu Chen, Jun He
Known as two cornerstones of problem solving by search, exploitation and exploration are extensively discussed for implementation and application of evolutionary algorithms (EAs).
1 code implementation • 11 Nov 2019 • Jun He, Quan-Jie Cao, Lei Zhang
Sequential visual task usually requires to pay attention to its current interested object conditional on its previous observations.
no code implementations • 7 Sep 2019 • Jun He, Thomas Jansen, Christine Zarges
Run time and solution quality are two popular measures of the performance of these algorithms.
no code implementations • 3 Sep 2019 • Cong Wang, Yu Chen, Jun He, Chengwang Xie
When globally optimal solutions of complicated optimization problems cannot be located by evolutionary algorithms (EAs) in polynomial expected running time, the hitting time/running time analysis is not flexible enough to accommodate the requirement of theoretical study, because sometimes we have no idea on what approximation ratio is available in polynomial expected running time.
no code implementations • 24 Mar 2019 • Kun Wang, Jun He, Lei Zhang
Unlike images or videos data which can be easily labeled by human being, sensor data annotation is a time-consuming process.
no code implementations • 27 Oct 2018 • Yu Chen, Jun He
But for hard functions such as the deceptive function, the ACR of both the (1+1) adaptive random univariate search and evolutionary programming is exponential.
no code implementations • 26 Oct 2018 • Jun He, Yu Chen, Yuren Zhou
In the empirical study of evolutionary algorithms, the solution quality is evaluated by either the fitness value or approximation error.
no code implementations • 11 Oct 2018 • Fei Tan, Zhi Wei, Jun He, Xiang Wu, Bo Peng, Haoran Liu, Zhenyu Yan
In this work, we focus on pre- dicting attrition, which is one of typical user intended actions.
no code implementations • 1 May 2018 • Wei Huang, Tao Xu, Kangshun Li, Jun He
PMODE and HECO-PDE are compared with the algorithms from the IEEE CEC 2018 competition and another recent MOEA for constrained optimisation.
no code implementations • 30 Apr 2018 • Jun He, Tao Xu
What is a valley on a fitness landscape?
no code implementations • 11 Nov 2015 • Jun He
In this paper, an analytic expression for calculating the relative approximation error is presented for a class of evolutionary algorithms, that is, (1+1) strictly elitist evolution algorithms.
no code implementations • 30 Sep 2015 • Tao Xu, Jun He
This paper proposes a new multi-objective method for solving constrained optimization problems.
no code implementations • 30 Apr 2015 • Jun He, Guangming Lin
The calculation of the average convergence rate is very simple and it is applicable for most evolutionary algorithms on both continuous and discrete optimization.
no code implementations • 12 Feb 2015 • Jun He, Yong Wang, Yuren Zhou
Multi-objective optimisation is regarded as one of the most promising ways for dealing with constrained optimisation problems in evolutionary optimisation.
no code implementations • 12 Dec 2014 • Jun He, Yue Zhang
In this paper, we present GASG21 (Grassmannian Adaptive Stochastic Gradient for $L_{2, 1}$ norm minimization), an adaptive stochastic gradient algorithm to robustly recover the low-rank subspace from a large matrix.
no code implementations • 3 Sep 2014 • Xinsheng Lai, Yuren Zhou, Jun He, Jun Zhang
We also show that GSEMO achieves a $(2ln(n))$-approximation ratio for the MLST problem in expected polynomial time of $n$ and $k$.
no code implementations • 14 Apr 2014 • Jun He, Boris Mitavskiy, Yuren Zhou
Nonetheless, few rigorous investigations address the quality of solutions that evolutionary algorithms may produce for the knapsack problem.
no code implementations • 3 Apr 2014 • Jun He, Feidun He, Hongbin Dong
On the other hand, genetic algorithms are well suited for solving the knapsack problem and they find reasonably good solutions quickly.
no code implementations • 9 Dec 2013 • Jun He, Feidun He, Xin Yao
The convergence, convergence rate and expected hitting time play fundamental roles in the analysis of randomised search heuristics.
no code implementations • 14 Aug 2013 • Jun He, Xin Yao
Population scalability is the ratio of the expected hitting time between a benchmark algorithm and an algorithm using a larger population size.
no code implementations • 3 Jun 2013 • Jun He, Dejiao Zhang, Laura Balzano, Tao Tao
t-GRASTA iteratively performs incremental gradient descent constrained to the Grassmann manifold of subspaces in order to simultaneously estimate a decomposition of a collection of images into a low-rank subspace, a sparse part of occlusions and foreground objects, and a transformation such as rotation or translation of the image.
no code implementations • 11 May 2013 • Boris Mitavskiy, Elio Tuci, Chris Cannings, Jonathan Rowe, Jun He
The classical Geiringer theorem addresses the limiting frequency of occurrence of various alleles after repeated application of crossover.
no code implementations • 11 May 2013 • Boris Mitavskiy, Jun He
Recently a finite population version of Geiringer theorem with nonhomologous recombination has been adopted to the setting of Monte-Carlo tree search to cope with randomness and incomplete information by exploiting the entrinsic similarities within the state space of the problem.
no code implementations • 11 May 2013 • Boris Mitavskiy, Jun He
Hybrid and mixed strategy EAs have become rather popular for tackling various complex and NP-hard optimization problems.
no code implementations • 13 Mar 2013 • Jun He, Wei Hou, Hongbin Dong, Feidun He
In mixed strategy meta-heuristics, each time one search strategy is chosen from a strategy pool with a probability and then is applied.
no code implementations • 28 Mar 2012 • Jun He, Tianshi Chen, Xin Yao
The aim of this paper is to answer the following research questions: Given a fitness function class, which functions are the easiest with respect to an evolutionary algorithm?
no code implementations • 8 Feb 2012 • Boris Mitavskiy, Jun He
Nowadays hybrid evolutionary algorithms, i. e, heuristic search algorithms combining several mutation operators some of which are meant to implement stochastically a well known technique designed for the specific problem in question while some others playing the role of random search, have become rather popular for tackling various NP-hard optimization problems.
no code implementations • 7 Dec 2011 • Jun He, Feidun He, Hongbin Dong
Mixed strategy EAs aim to integrate several mutation operators into a single algorithm.
1 code implementation • 18 Sep 2011 • Jun He, Laura Balzano, John C. S. Lui
This paper presents GRASTA (Grassmannian Robust Adaptive Subspace Tracking Algorithm), an efficient and robust online algorithm for tracking subspaces from highly incomplete information.
no code implementations • 23 Aug 2011 • Jun He, Tianshi Chen, Boris Mitavskiy
(1) We demonstrate rigorously that for elitist EAs with identical global mutation, using a lager population size always increases the average rate of convergence to the optimal set; and yet, sometimes, the expected number of generations needed to find an optimal solution (measured by either the maximal value or the average value) may increase, rather than decrease.