1 code implementation • In2Writing (ACL) 2022 • Nayu Liu, Wenjing Han, Guangcan Liu, Da Peng, Ran Zhang, Xiaorui Wang, Huabin Ruan
In this work, we take a further step towards satisfying practical demands in Chinese lyric generation from musical short-video creators, in respect of the challenges on songs’ format constraints, creating specific lyrics from open-ended inspiration inputs, and language rhyme grace.
no code implementations • 19 Mar 2024 • Kaile Du, Yifan Zhou, Fan Lyu, Yuyang Li, Chen Lu, Guangcan Liu
The partial label challenge in Multi-Label Class-Incremental Learning (MLCIL) arises when only the new classes are labeled during training, while past and future labels remain unavailable.
no code implementations • 13 Feb 2024 • Fan Lyu, Kaile Du, Yuyang Li, Hanyu Zhao, Zhang Zhang, Guangcan Liu, Liang Wang
At the source stage, we transform a pre-trained deterministic model into a Bayesian Neural Network (BNN) via a variational warm-up strategy, injecting uncertainties into the model.
1 code implementation • ICCV 2023 • Yisheng Zhu, Hu Han, Zhengtao Yu, Guangcan Liu
Specifically, we design a Relative Visual Tempo Learning (RVTL) task to explore the motion information in intra-video clips, and an Appearance-Consistency (AC) task to learn appearance information simultaneously, resulting in more representative spatiotemporal features.
no code implementations • 20 Nov 2022 • Wenyan Pan, Zhili Zhou, Guangcan Liu, Teng Huang, Hongyang Yan, Q. M. Jonathan Wu
However, we argue that those models achieve sub-optimal detection performance as it tends to: 1) distinguish the manipulation traces from a lot of noisy information within the entire image, and 2) ignore the trace relations among the pixels of each manipulated region and its surroundings.
no code implementations • 27 May 2021 • Xingyu Xie, Qiuhao Wang, Zenan Ling, Xia Li, Yisen Wang, Guangcan Liu, Zhouchen Lin
In this paper, we investigate an emerging question: can an implicit equilibrium model's equilibrium point be regarded as the solution of an optimization problem?
1 code implementation • 23 Apr 2021 • Guangcan Liu
Recently, Liu and Zhang studied the rather challenging problem of time series forecasting from the perspective of compressed sensing.
no code implementations • 1 Jan 2021 • Xingyu Xie, Hao Kong, Jianlong Wu, Guangcan Liu, Zhouchen Lin
First of all, to perform matrix inverse, we provide a differentiable yet efficient way, named LD-Minv, which is a learnable deep neural network (DNN) with each layer being an $L$-th order matrix polynomial.
1 code implementation • ICML 2020 • Xingyu Xie, Hao Kong, Jianlong Wu, Wayne Zhang, Guangcan Liu, Zhouchen Lin
While successful in many fields, deep neural networks (DNNs) still suffer from some open problems such as bad local minima and unsatisfactory generalization performance.
no code implementations • 26 Dec 2019 • Jiahuan Ren, Zhao Zhang, Sheng Li, Yang Wang, Guangcan Liu, Shuicheng Yan, Meng Wang
Specifically, J-RFDL performs the robust representation by DL in a factorized compressed space to eliminate the negative effects of noise and outliers on the results, which can also make the DL process efficient.
no code implementations • 13 Dec 2019 • Xianzhen Li, Zhao Zhang, Yang Wang, Guangcan Liu, Shuicheng Yan, Meng Wang
In this paper, we explore the deep multi-subspace recovery problem by designing a multilayer architecture for latent LRR.
1 code implementation • 6 Sep 2019 • Guangcan Liu, Wayne Zhang
This paper studies the problem of time series forecasting (TSF) from the perspective of compressed sensing.
no code implementations • 2 Sep 2019 • Zhao Zhang, Yan Zhang, Sheng Li, Guangcan Liu, Dan Zeng, Shuicheng Yan, Meng Wang
For auto-weighting, RFA-LCF jointly preserves the manifold structures in the basis concept space and new coordinate space in an adaptive manner by minimizing the reconstruction errors on clean data, anchor points and coordinates.
no code implementations • 21 Aug 2019 • Zhao Zhang, Yulin Sun, Zheng Zhang, Yang Wang, Guangcan Liu, Meng Wang
In this setting, our TP-DPL integrates the twin-incoherence based latent flexible DPL and the joint embedding of codes as well as salient features by twin-projection into a unified model in an adaptive neighborhood-preserving manner.
no code implementations • 29 May 2019 • Zhao Zhang, Lei Jia, Mingbo Zhao, Guangcan Liu, Meng Wang, Shuicheng Yan
A Kernel-Induced Label Propagation (Kernel-LP) framework by mapping is proposed for high-dimensional data classification using the most informative patterns of data in kernel space.
no code implementations • 25 May 2019 • Zhao Zhang, Weiming Jiang, Zheng Zhang, Sheng Li, Guangcan Liu, Jie Qin
More importantly, LC-PDL avoids using the complementary data matrix to learn the sub-dictionary over each class.
no code implementations • 25 May 2019 • Zhao Zhang, Yan Zhang, Sheng Li, Guangcan Liu, Meng Wang, Shuicheng Yan
RFA-LCF integrates the robust flexible CF, robust sparse local-coordinate coding and the adaptive reconstruction weighting learning into a unified model.
no code implementations • 25 May 2019 • Zhao Zhang, Yan Zhang, Guangcan Liu, Jinhui Tang, Shuicheng Yan, Meng Wang
To enrich prior knowledge to enhance the discrimination, RS2ACF clearly uses class information of labeled data and more importantly propagates it to unlabeled data by jointly learning an explicit label indicator for unlabeled data.
1 code implementation • 15 May 2019 • Xingyu Xie, Jianlong Wu, Zhisheng Zhong, Guangcan Liu, Zhouchen Lin
Recently, a number of learning-based optimization methods that combine data-driven architectures with the classical optimization algorithms have been proposed and explored, showing superior empirical performance in solving various ill-posed inverse problems, but there is still a scarcity of rigorous analysis about the convergence behaviors of learning-based optimization.
1 code implementation • 9 Nov 2018 • Xingyu Xie, Jianlong Wu, Guangcan Liu, Jun Wang
To tackle this issue, we propose a novel method for matrix recovery in this paper, which could well handle the case where the target matrix is low-rank in an implicit feature space but high-rank or even full-rank in its original form.
no code implementations • 30 Mar 2018 • Guangcan Liu, Zhao Zhang, Qingshan Liu, Kongkai Xiong
Dimension reduction is widely regarded as an effective way for decreasing the computation, storage and communication loads of data-driven intelligent systems, leading to a growing demand for statistical methods that allow analysis (e. g., clustering) of compressed data.
no code implementations • NeurIPS 2017 • Guangcan Liu, Qingshan Liu, Xiaotong Yuan
To break through the limits of random sampling, this paper introduces a new hypothesis called \emph{isomeric condition}, which is provably weaker than the assumption of uniform sampling and arguably holds even when the missing data is placed irregularly.
no code implementations • 3 Sep 2017 • Yang Li, Guangcan Liu, Sheng-Yong Chen
Due to its efficiency and stability, Robust Principal Component Analysis (RPCA) has been emerging as a promising tool for moving object detection.
no code implementations • NeurIPS 2016 • Xiaotong Yuan, Ping Li, Tong Zhang, Qingshan Liu, Guangcan Liu
We investigate a subclass of exponential family graphical models of which the sufficient statistics are defined by arbitrary additive forms.
no code implementations • ICCV 2015 • Changqing Zhang, Huazhu Fu, Si Liu, Guangcan Liu, Xiaochun Cao
We introduce a low-rank tensor constraint to explore the complementary information from multiple views and, accordingly, establish a novel method called Low-rank Tensor constrained Multiview Subspace Clustering (LT-MSC).
no code implementations • 16 Nov 2014 • Weipeng Zhang, Jie Shen, Guangcan Liu, Yong Yu
Unlike previous approaches, our approach models the clothing attributes as latent variables and thus requires no explicit labeling for the clothing attributes.
no code implementations • 19 Apr 2014 • Jie Shen, Guangcan Liu, Jia Chen, Yuqiang Fang, Jianbin Xie, Yong Yu, Shuicheng Yan
In this paper, we utilize structured learning to simultaneously address two intertwined problems: human pose estimation (HPE) and garment attribute classification (GAC), which are valuable for a variety of computer vision and multimedia applications.
no code implementations • 17 Apr 2014 • Guangcan Liu, Ping Li
To better handle non-uniform data, in this paper we propose a method termed Low-Rank Factor Decomposition (LRFD), which imposes an additional restriction that the data points must be represented as linear combinations of the bases in a dictionary constructed or learnt in advance.
no code implementations • NeurIPS 2014 • Guangcan Liu, Ping Li
More precisely, we mathematically prove that if the dictionary itself is low-rank then LRR is immune to the coherence parameter which increases with the underlying cluster number.
no code implementations • 10 Sep 2012 • Guangcan Liu, Shiyu Chang, Yi Ma
We show that the minimizer of this regularizer guarantees to give good approximation to the blur kernel if the original image is sharp enough.
no code implementations • 8 Sep 2011 • Guangcan Liu, Huan Xu, Shuicheng Yan
In this work, we address the following matrix recovery problem: suppose we are given a set of data points containing two parts, one part consists of samples drawn from a union of multiple subspaces and the other part consists of outliers.
1 code implementation • 14 Oct 2010 • Guangcan Liu, Zhouchen Lin, Shuicheng Yan, Ju Sun, Yong Yu, Yi Ma
In this work we address the subspace recovery problem.