no code implementations • CVPR 2013 • Xiaobai Liu, Liang Lin, Alan L. Yuille
In this work, we present an efficient multi-scale low-rank representation for image segmentation.
no code implementations • CVPR 2013 • Keyang Shi, Keze Wang, Jiangbo Lu, Liang Lin
By fusing complementary contrast measures in such a pixelwise adaptive manner, the detection effectiveness is significantly boosted.
no code implementations • 11 Nov 2014 • Xiaodan Liang, Si Liu, Yunchao Wei, Luoqi Liu, Liang Lin, Shuicheng Yan
Then the concept detector can be fine-tuned based on these new instances.
no code implementations • 18 Jan 2015 • Canyi Lu, Jinhui Tang, Min Lin, Liang Lin, Shuicheng Yan, Zhouchen Lin
In this paper, we study the robust subspace clustering problem, which aims to cluster the given possibly noisy data points into their underlying subspaces.
no code implementations • 26 Jan 2015 • Keze Wang, Xiaolong Wang, Liang Lin, Meng Wang, WangMeng Zuo
Our model thus advances existing approaches in two aspects: (i) it acts directly on the raw inputs (grayscale-depth data) to conduct recognition instead of relying on hand-crafted features, and (ii) the model structure can be dynamically adjusted accounting for the temporal variations of human activities, i. e. the network configuration is allowed to be partially activated during inference.
no code implementations • 28 Jan 2015 • Liliang Zhang, Liang Lin, Xian Wu, Shengyong Ding, Lei Zhang
Sketch-based face recognition is an interesting task in vision and multimedia research, yet it is quite challenging due to the great difference between face photos and sketches.
no code implementations • 1 Feb 2015 • Xiaodan Liang, Liang Lin, Liangliang Cao
Action recognition is an important problem in multimedia understanding.
no code implementations • 1 Feb 2015 • Yuanlu Xu, Liang Lin, Wei-Shi Zheng, Xiaobai Liu
This paper aims at a newly raising task in visual surveillance: re-identifying people at a distance by matching body information, given several reference examples.
no code implementations • 2 Feb 2015 • Liang Lin, Ruimao Zhang, Xiaohua Duan
During the iterations of inference, the model of each category is analytically updated by a generative learning algorithm.
no code implementations • 2 Feb 2015 • Liang Lin, Xiaolong Wang, Wei Yang, Jian-Huang Lai
In this paper, we investigate a novel reconfigurable part-based model, namely And-Or graph model, to recognize object shapes in images.
no code implementations • 2 Feb 2015 • Liang Lin, Yongyi Lu, Yan Pan, Xiaowu Chen
With this graph representation, we pose trajectory analysis as a joint task of spatial graph partitioning and temporal graph matching.
no code implementations • 2 Feb 2015 • Zhujin Liang, Xiaolong Wang, Rui Huang, Liang Lin
This paper aims at one newly raising task in vision and multimedia research: recognizing human actions from still images.
no code implementations • 2 Feb 2015 • Bo Jiang, Yongyi Lu, Xiying Li, Liang Lin
Although the object detection and recognition has received growing attention for decades, a robust fire and flame detection method is rarely explored.
no code implementations • 2 Feb 2015 • Liang Lin, Yuanlu Xu, Xiaodan Liang, Jian-Huang Lai
Although it has been widely discussed in video surveillance, background subtraction is still an open problem in the context of complex scenarios, e. g., dynamic backgrounds, illumination variations, and indistinct foreground objects.
no code implementations • 2 Feb 2015 • Wangmeng Zuo, Faqiang Wang, David Zhang, Liang Lin, Yuchi Huang, Deyu Meng, Lei Zhang
Distance metric learning aims to learn from the given training data a valid distance metric, with which the similarity between data samples can be more effectively evaluated for classification.
no code implementations • NeurIPS 2012 • Xiaolong Wang, Liang Lin
A discriminative learning algorithm, extended from the CCCP [23], is proposed to train the model in a dynamical manner: the model structure (e. g., the configuration of the leaf-nodes associated with the or-nodes) is automatically determined with optimizing the multi-layer parameters during the iteration.
1 code implementation • 3 Feb 2015 • Xiaodan Liang, Qingxing Cao, Rui Huang, Liang Lin
The aim of this study is to provide an automatic computational framework to assist clinicians in diagnosing Focal Liver Lesions (FLLs) in Contrast-Enhancement Ultrasound (CEUS).
no code implementations • 3 Feb 2015 • Liang Lin, Xiaolong Wang, Wei Yang, Jian-Huang Lai
This paper proposes a simple yet effective method to learn the hierarchical object shape model consisting of local contour fragments, which represents a category of shapes in the form of an And-Or tree.
no code implementations • CVPR 2014 • Wei Yang, Ping Luo, Liang Lin
This paper aims at developing an integrated system of clothing co-parsing, in order to jointly parse a set of clothing images (unsegmented but annotated with tags) into semantic configurations.
no code implementations • NeurIPS 2014 • Xiaolong Wang, Liliang Zhang, Liang Lin, Zhujin Liang, WangMeng Zuo
We present a general joint task learning framework, in which each task (either object localization or object segmentation) is tackled via a multi-layer convolutional neural network, and the two networks work collaboratively to boost performance.
no code implementations • CVPR 2013 • Xiaolong Wang, Liang Lin, Lichao Huang, Shuicheng Yan
This paper proposes a reconfigurable model to recognize and detect multiclass (or multiview) objects with large variation in appearance.
no code implementations • 3 Feb 2015 • Xionghao Liu, Wei Yang, Liang Lin, Qing Wang, Zhaoquan Cai, Jian-Huang Lai
In the first step, the references are selected by jointly matching their appearances with the target as well as the semantics (i. e. the assigned labels of the target and the references).
no code implementations • 3 Feb 2015 • Zhanglin Peng, Liang Lin, Ruimao Zhang, Jing Xu
Constructing effective representations is a critical but challenging problem in multimedia understanding.
1 code implementation • 9 Mar 2015 • Xiaodan Liang, Si Liu, Xiaohui Shen, Jianchao Yang, Luoqi Liu, Jian Dong, Liang Lin, Shuicheng Yan
The first CNN network is with max-pooling, and designed to predict the template coefficients for each label mask, while the second CNN network is without max-pooling to preserve sensitivity to label mask position and accurately predict the active shape parameters.
no code implementations • CVPR 2015 • Si Liu, Xiaodan Liang, Luoqi Liu, Xiaohui Shen, Jianchao Yang, Changsheng Xu, Liang Lin, Xiaochun Cao, Shuicheng Yan
Under the classic K Nearest Neighbor (KNN)-based nonparametric framework, the parametric Matching Convolutional Neural Network (M-CNN) is proposed to predict the matching confidence and displacements of the best matched region in the testing image for a particular semantic region in one KNN image.
no code implementations • 20 Apr 2015 • Xiaohe Wu, WangMeng Zuo, Yuanyuan Zhu, Liang Lin
The generalization error bound of support vector machine (SVM) depends on the ratio of radius and margin, while standard SVM only considers the maximization of the margin but ignores the minimization of the radius.
no code implementations • CVPR 2013 • Keze Wang, Liang Lin, Jiangbo Lu, Chenglong Li, Keyang Shi
In this paper, we propose a unified framework called PISA, which stands for Pixelwise Image Saliency Aggregating various bottom-up cues and priors.
no code implementations • CVPR 2015 • Chenglong Li, Liang Lin, WangMeng Zuo, Shuicheng Yan, Jin Tang
In particular, the affinity matrix with the rank fixed can be decomposed into two sub-matrices of low rank, and then we iteratively optimize them with closed-form solutions.
no code implementations • CVPR 2015 • Wangmeng Zuo, Dongwei Ren, Shuhang Gu, Liang Lin, Lei Zhang
The maximum a posterior (MAP)-based blind deconvolution framework generally involves two stages: blur kernel estimation and non-blind restoration.
no code implementations • 13 Jul 2015 • Zhujin Liang, Shengyong Ding, Liang Lin
This paper investigates how to rapidly and accurately localize facial landmarks in unconstrained, cluttered environments rather than in the well segmented face images.
no code implementations • 8 Aug 2015 • Zhanglin Peng, Ya Li, Zhaoquan Cai, Liang Lin
In each layer, we construct a dictionary of filters by combining the filters from the lower layer, and iteratively optimize the image representation with a joint discriminative-generative formulation, i. e. minimization of empirical classification error plus regularization of analysis image generation over training images.
no code implementations • 19 Aug 2015 • Ruimao Zhang, Liang Lin, Rui Zhang, WangMeng Zuo, Lei Zhang
Furthermore, each bit of our hashing codes is unequally weighted so that we can manipulate the code lengths by truncating the insignificant bits.
no code implementations • 9 Sep 2015 • Xiaodan Liang, Yunchao Wei, Xiaohui Shen, Jianchao Yang, Liang Lin, Shuicheng Yan
Instance-level object segmentation is an important yet under-explored task.
no code implementations • 13 Nov 2015 • Tianshui Chen, Liang Lin, Lingbo Liu, Xiaonan Luo, Xuelong. Li
Our DISC framework is capable of uniformly highlighting the objects-of-interest from complex background while preserving well object details.
no code implementations • CVPR 2016 • Xiaodan Liang, Yunchao Wei, Xiaohui Shen, Zequn Jie, Jiashi Feng, Liang Lin, Shuicheng Yan
By being reversible, the proposal refinement sub-network adaptively determines an optimal number of refinement iterations required for each proposal during both training and testing.
no code implementations • CVPR 2016 • Xiaodan Liang, Xiaohui Shen, Donglai Xiang, Jiashi Feng, Liang Lin, Shuicheng Yan
The long chains of sequential computation by stacked LG-LSTM layers also enable each pixel to sense a much larger region for inference benefiting from the memorization of previous dependencies in all positions along all dimensions.
no code implementations • ICCV 2015 • Xiaodan Liang, Si Liu, Yunchao Wei, Luoqi Liu, Liang Lin, Shuicheng Yan
Then the concept detector can be fine-tuned based on these new instances.
no code implementations • ICCV 2015 • Xiaodan Liang, Chunyan Xu, Xiaohui Shen, Jianchao Yang, Si Liu, Jinhui Tang, Liang Lin, Shuicheng Yan
In this work, we address the human parsing task with a novel Contextualized Convolutional Neural Network (Co-CNN) architecture, which well integrates the cross-layer context, global image-level context, within-super-pixel context and cross-super-pixel neighborhood context into a unified network.
no code implementations • 5 Dec 2015 • Liang Lin, Keze Wang, WangMeng Zuo, Meng Wang, Jiebo Luo, Lei Zhang
Understanding human activity is very challenging even with the recently developed 3D/depth sensors.
no code implementations • 11 Dec 2015 • Shengyong Ding, Liang Lin, Guangrun Wang, Hongyang Chao
Identifying the same individual across different scenes is an important yet difficult task in intelligent video surveillance.
Ranked #9 on Person Re-Identification on SYSU-30k (using extra training data)
no code implementations • 22 Jan 2016 • Wangmeng Zuo, Xiaohe Wu, Liang Lin, Lei Zhang, Ming-Hsuan Yang
Sampling and budgeting training examples are two essential factors in tracking algorithms based on support vector machines (SVMs) as a trade-off between accuracy and efficiency.
no code implementations • 13 Feb 2016 • Shuye Zhang, Mude Lin, Tianshui Chen, Lianwen Jin, Liang Lin
Maximally stable extremal regions (MSER), which is a popular method to generate character proposals/candidates, has shown superior performance in scene text detection.
no code implementations • 23 Mar 2016 • Xiaodan Liang, Xiaohui Shen, Jiashi Feng, Liang Lin, Shuicheng Yan
By taking the semantic object parsing task as an exemplar application scenario, we propose the Graph Long Short-Term Memory (Graph LSTM) network, which is the generalization of LSTM from sequential data or multi-dimensional data to general graph-structured data.
no code implementations • 7 Apr 2016 • Zhanglin Peng, Ruimao Zhang, Xiaodan Liang, Xiaobai Liu, Liang Lin
This paper addresses the problem of geometric scene parsing, i. e. simultaneously labeling geometric surfaces (e. g. sky, ground and vertical plane) and determining the interaction relations (e. g. layering, supporting, siding and affinity) between main regions.
2 code implementations • CVPR 2017 • Tong Xiao, Shuang Li, Bochao Wang, Liang Lin, Xiaogang Wang
Existing person re-identification benchmarks and methods mainly focus on matching cropped pedestrian images between queries and candidates.
Ranked #9 on Person Re-Identification on CUHK03
no code implementations • CVPR 2016 • Liang Lin, Guangrun Wang, Rui Zhang, Ruimao Zhang, Xiaodan Liang, WangMeng Zuo
This paper addresses a fundamental problem of scene understanding: How to parse the scene image into a structured configuration (i. e., a semantic object hierarchy with object interaction relations) that finely accords with human perception.
no code implementations • 15 Apr 2016 • Guangrun Wang, Liang Lin, Shengyong Ding, Ya Li, Qing Wang
The past decade has witnessed the rapid development of feature representation learning and distance metric learning, whereas the two steps are often discussed separately.
Ranked #7 on Person Re-Identification on SYSU-30k (using extra training data)
1 code implementation • 18 Apr 2016 • Zhen Li, Yukang Gan, Xiaodan Liang, Yizhou Yu, Hui Cheng, Liang Lin
Another long short-term memorized fusion layer is set up to integrate the contexts along the vertical direction from different channels, and perform bi-directional propagation of the fused vertical contexts along the horizontal direction to obtain true 2D global contexts.
no code implementations • 13 May 2016 • Liang Lin, Guangrun Wang, WangMeng Zuo, Xiangchu Feng, Lei Zhang
Cross-domain visual data matching is one of the fundamental problems in many real-world vision tasks, e. g., matching persons across ID photos and surveillance videos.
no code implementations • CVPR 2016 • Faqiang Wang, WangMeng Zuo, Liang Lin, David Zhang, Lei Zhang
Person re-identification has been usually solved as either the matching of single-image representation (SIR) or the classification of cross-image representation (CIR).
no code implementations • CVPR 2016 • Keze Wang, Liang Lin, WangMeng Zuo, Shuhang Gu, Lei Zhang
Feature representation and object category classification are two key components of most object detection methods.
no code implementations • 24 Jul 2016 • Liliang Zhang, Liang Lin, Xiaodan Liang, Kaiming He
Detecting pedestrian has been arguably addressed as a special topic beyond general object detection.
Ranked #19 on Pedestrian Detection on Caltech
no code implementations • 25 Jul 2016 • Yukai Shi, Keze Wang, Li Xu, Liang Lin
Recently, machine learning based single image super resolution (SR) approaches focus on jointly learning representations for high-resolution (HR) and low-resolution (LR) image patch pairs to improve the quality of the super-resolved images.
no code implementations • 13 Aug 2016 • Keze Wang, Shengfu Zhai, Hui Cheng, Xiaodan Liang, Liang Lin
In this paper, we propose a novel inference-embedded multi-task learning framework for predicting human pose from still depth images, which is implemented with a deep architecture of neural networks.
no code implementations • 4 Dec 2016 • Tianshui Chen, Liang Lin, Xian Wu, Nong Xiao, Xiaonan Luo
To avoid the exhaustive search over locations and scales, current state-of-the-art object detection systems usually involve a crucial component generating a batch of candidate object proposals from images.
3 code implementations • 13 Jan 2017 • Keze Wang, Dongyu Zhang, Ya Li, Ruimao Zhang, Liang Lin
In this paper, we propose a novel active learning framework, which is capable of building a competitive classifier with optimal feature representation via a limited amount of labeled training instances in an incremental learning manner.
no code implementations • 13 Jan 2017 • Liang Lin, Keze Wang, Deyu Meng, WangMeng Zuo, Lei Zhang
By naturally combining two recently rising techniques: active learning (AL) and self-paced learning (SPL), our framework is capable of automatically annotating new instances and incorporating them into training under weak expert re-certification.
no code implementations • 20 Feb 2017 • Ruimao Zhang, Wei Yang, Zhanglin Peng, Xiaogang Wang, Liang Lin
This paper introduces Progressively Diffused Networks (PDNs) for unifying multi-scale context modeling with deep feature learning, by taking semantic image segmentation as an exemplar application.
no code implementations • CVPR 2017 • Xiaodan Liang, Liang Lin, Xiaohui Shen, Jiashi Feng, Shuicheng Yan, Eric P. Xing
Instead of learning LSTM models over the pre-fixed structures, we propose to further learn the intermediate interpretable multi-level graph structures in a progressive and stochastic way from data during the LSTM network optimization.
1 code implementation • CVPR 2017 • Ke Gong, Xiaodan Liang, Dongyu Zhang, Xiaohui Shen, Liang Lin
Human parsing has recently attracted a lot of research interests due to its huge application potentials.
Ranked #13 on Semantic Segmentation on LIP val
no code implementations • CVPR 2017 • Guanbin Li, Yuan Xie, Liang Lin, Yizhou Yu
Image saliency detection has recently witnessed rapid progress due to deep convolutional neural networks.
Ranked #15 on RGB Salient Object Detection on DUTS-TE (max F-measure metric)
no code implementations • CVPR 2017 • Guangrun Wang, Ping Luo, Liang Lin, Xiaogang Wang
This work significantly increases segmentation accuracy of CNNs by learning from an Image Descriptions in the Wild (IDW) dataset.
no code implementations • 15 Jul 2017 • Liang Lin, Lili Huang, Tianshui Chen, Yukang Gan, Hui Cheng
This paper aims at task-oriented action prediction, i. e., predicting a sequence of actions towards accomplishing a specific task under a certain scene, which is a new problem in computer vision research.
no code implementations • 26 Jul 2017 • Yukai Shi, Keze Wang, Chongyu Chen, Li Xu, Liang Lin
Single image super resolution (SR), which refers to reconstruct a higher-resolution (HR) image from the observed low-resolution (LR) image, has received substantial attention due to its tremendous application potentials.
no code implementations • 28 Jul 2017 • Ziliang Chen, Keze Wang, Xiao Wang, Pai Peng, Ebroul Izquierdo, Liang Lin
Aiming at improving performance of visual classification in a cost-effective manner, this paper proposes an incremental semi-supervised learning paradigm called Deep Co-Space (DCS).
no code implementations • CVPR 2017 • Mude Lin, Liang Lin, Xiaodan Liang, Keze Wang, Hui Cheng
3D human articulated pose recovery from monocular image sequences is very challenging due to the diverse appearances, viewpoints, occlusions, and also the human 3D pose is inherently ambiguous from the monocular imagery.
Ranked #20 on 3D Human Pose Estimation on HumanEva-I
no code implementations • CVPR 2017 • Qingxing Cao, Liang Lin, Yukai Shi, Xiaodan Liang, Guanbin Li
Face hallucination is a domain-specific super-resolution problem with the goal to generate high-resolution (HR) faces from low-resolution (LR) input images.
no code implementations • 27 Sep 2017 • Ruimao Zhang, Liang Lin, Guangrun Wang, Meng Wang, WangMeng Zuo
Rather than relying on elaborative annotations (e. g., manually labeled semantic maps and relations), we train our deep model in a weakly-supervised learning manner by leveraging the descriptive sentences of the training images.
no code implementations • ICCV 2017 • Ping Luo, Guangrun Wang, Liang Lin, Xiaogang Wang
The estimated labelmaps that capture accurate object classes and boundaries are used as ground truths in training to boost performance.
no code implementations • 4 Oct 2017 • Chenglong Li, Liang Lin, WangMeng Zuo, Jin Tang, Ming-Hsuan Yang
First, the graph is initialized by assigning binary weights of some image patches to indicate the object and background patches according to the predicted bounding box.
no code implementations • 4 Oct 2017 • Xiaodan Liang, Yunchao Wei, Liang Lin, Yunpeng Chen, Xiaohui Shen, Jianchao Yang, Shuicheng Yan
An intuition on human segmentation is that when a human is moving in a video, the video-context (e. g., appearance and motion clues) may potentially infer reasonable mask information for the whole human body.
no code implementations • 4 Oct 2017 • Dongyu Zhang, Liang Lin, Tianshui Chen, Xian Wu, Wenwei Tan, Ebroul Izquierdo
Sketch portrait generation benefits a wide range of applications such as digital entertainment and law enforcement.
no code implementations • ICCV 2017 • Zhouxia Wang, Tianshui Chen, Guanbin Li, Ruijia Xu, Liang Lin
This paper proposes a novel deep architecture to address multi-label image recognition, a fundamental and practical task towards general visual understanding.
1 code implementation • CVPR 2018 • Yue Luo, Jimmy Ren, Zhouxia Wang, Wenxiu Sun, Jinshan Pan, Jianbo Liu, Jiahao Pang, Liang Lin
Such suboptimal results are mainly attributed to the inability of imposing sequential geometric consistency, handling severe image quality degradation (e. g. motion blur and occlusion) as well as the inability of capturing the temporal correlation among video frames.
Ranked #3 on Pose Estimation on J-HMDB
2 code implementations • 20 Dec 2017 • Tianshui Chen, Liang Lin, WangMeng Zuo, Xiaonan Luo, Lei Zhang
In this work, aiming at a general and comprehensive way for neural network acceleration, we develop a Wavelet-like Auto-Encoder (WAE) that decomposes the original input image into two low-resolution channels (sub-images) and incorporate the WAE into the classification neural networks for joint training.
no code implementations • 20 Dec 2017 • Tianshui Chen, Zhouxia Wang, Guanbin Li, Liang Lin
Recognizing multiple labels of images is a fundamental but challenging task in computer vision, and remarkable progress has been attained by localizing semantic-aware image regions and predicting their labels with deep convolutional neural networks.
no code implementations • 21 Dec 2017 • Haofeng Li, Guanbin Li, Liang Lin, Yizhou Yu
Our proposed GAN-based framework consists of a fully convolutional design for the generator which helps to better preserve spatial structures and a joint loss function with a revised perceptual loss to capture high-level semantics in the context.
no code implementations • 20 Jan 2018 • Hanhui Li, Xiangjian He, Hefeng Wu, Saeed Amirgholipour Kasmani, Ruomei Wang, Xiaonan Luo, Liang Lin
In this paper, we aim at tackling the problem of crowd counting in extremely high-density scenes, which contain hundreds, or even thousands of people.
no code implementations • 9 Feb 2018 • Guangrun Wang, Jiefeng Peng, Ping Luo, Xinjiang Wang, Liang Lin
As an indispensable component, Batch Normalization (BN) has successfully improved the training of deep neural networks (DNNs) with mini-batches, by normalizing the distribution of the internal representation for each hidden layer.
1 code implementation • CVPR 2018 • Ruijia Xu, Ziliang Chen, WangMeng Zuo, Junjie Yan, Liang Lin
Motivated by the theoretical results in \cite{mansour2009domain}, the target distribution can be represented as the weighted combination of source distributions, and, the multi-source unsupervised domain adaptation via DCTN is then performed as two alternating steps: i) It deploys multi-way adversarial learning to minimize the discrepancy between the target and each of the multiple source domains, which also obtains the source-specific perplexity scores to denote the possibilities that a target sample belongs to different source domains.
Multi-Source Unsupervised Domain Adaptation Unsupervised Domain Adaptation
1 code implementation • CVPR 2018 • Yue Luo, Jimmy Ren, Mude Lin, Jiahao Pang, Wenxiu Sun, Hongsheng Li, Liang Lin
The resulting model outperforms all the previous monocular depth estimation methods as well as the stereo block matching method in the challenging KITTI dataset by only using a small number of real training data.
Ranked #43 on Monocular Depth Estimation on KITTI Eigen split
no code implementations • 17 Mar 2018 • Guanbin Li, Yuan Xie, Liang Lin
Our algorithm is based on alternately exploiting a graphical model and training a fully convolutional network for model updating.
1 code implementation • CVPR 2018 • Jiahao Pang, Wenxiu Sun, Chengxi Yang, Jimmy Ren, Ruichao Xiao, Jin Zeng, Liang Lin
By feeding real stereo pairs of different domains to stereo models pre-trained with synthetic data, we see that: i) a pre-trained model does not generalize well to the new domain, producing artifacts at boundaries and ill-posed regions; however, ii) feeding an up-sampled stereo pair leads to a disparity map with extra details.
no code implementations • CVPR 2018 • Keze Wang, Xiaopeng Yan, Dongyu Zhang, Lei Zhang, Liang Lin
Though quite challenging, leveraging large-scale unlabeled or partially labeled images in a cost-effective way has increasingly attracted interests for its great importance to computer vision.
no code implementations • CVPR 2018 • Qingxing Cao, Xiaodan Liang, Bailing Li, Guanbin Li, Liang Lin
This network comprises of two collaborative modules: i) an adversarial attention module to exploit the local visual evidence for each word parsed from the question; ii) a residual composition module to compose the previously mined evidence.
3 code implementations • 5 Apr 2018 • Xiaodan Liang, Ke Gong, Xiaohui Shen, Liang Lin
To further explore and take advantage of the semantic correlation of these two tasks, we propose a novel joint human parsing and pose estimation network to explore efficient context modeling, which can simultaneously predict parsing and pose with extremely high quality.
Ranked #10 on Semantic Segmentation on LIP val
2 code implementations • CVPR 2018 • Ke Yu, Chao Dong, Liang Lin, Chen Change Loy
We investigate a novel approach for image restoration by reinforcement learning.
1 code implementation • ECCV 2018 • Xiaoming Li, Ming Liu, Yuting Ye, WangMeng Zuo, Liang Lin, Ruigang Yang
For better recovery of fine facial details, we modify the problem setting by taking both the degraded observation and a high-quality guided image of the same identity as input to our guided face restoration network (GFRNet).
Ranked #1 on Image Super-Resolution on WebFace - 8x upscaling
5 code implementations • 18 May 2018 • Pengju Liu, Hongzhi Zhang, Kai Zhang, Liang Lin, WangMeng Zuo
With the modified U-Net architecture, wavelet transform is introduced to reduce the size of feature maps in the contracting subnetwork.
Ranked #2 on Grayscale Image Denoising on Set12 sigma25
no code implementations • 23 May 2018 • Min Wang, Xipeng Chen, Wentao Liu, Chen Qian, Liang Lin, Lizhuang Ma
In this paper, we propose a two-stage depth ranking based method (DRPose3D) to tackle the problem of 3D human pose estimation.
no code implementations • CVPR 2018 • Xian Wu, Guanbin Li, Qingxing Cao, Qingge Ji, Liang Lin
Automatically describing open-domain videos with natural language are attracting increasing interest in the field of artificial intelligence.
no code implementations • CVPR 2018 • Guanbin Li, Yuan Xie, Tianhao Wei, Keze Wang, Liang Lin
Image saliency detection has recently witnessed significant progress due to deep convolutional neural networks.
Ranked #2 on Video Salient Object Detection on DAVSOD-Difficult20 (using extra training data)
1 code implementation • 30 Jun 2018 • Keze Wang, Liang Lin, Xiaopeng Yan, Ziliang Chen, Dongyu Zhang, Lei Zhang
The proposed process can be compatible with mini-batch based training (i. e., using a batch of unlabeled or partially labeled data as a one-time input) for object detection.
no code implementations • 2 Jul 2018 • Tianshui Chen, Liang Lin, Riquan Chen, Yang Wu, Xiaonan Luo
Humans can naturally understand an image in depth with the aid of rich knowledge accumulated from daily lives or professions.
Fine-Grained Image Classification Fine-Grained Image Recognition +1
1 code implementation • 2 Jul 2018 • Zhouxia Wang, Tianshui Chen, Jimmy Ren, Weihao Yu, Hui Cheng, Liang Lin
And this structured knowledge can be efficiently integrated into the deep neural network architecture to promote social relationship understanding by an end-to-end trainable Graph Reasoning Model (GRM), in which a propagation mechanism is learned to propagate node message through the graph to explore the interaction between persons of interest and the contextual objects.
Ranked #2 on Visual Social Relationship Recognition on PIPA
no code implementations • 2 Jul 2018 • Lingbo Liu, Hongjun Wang, Guanbin Li, Wanli Ouyang, Liang Lin
Crowd counting from unconstrained scene images is a crucial task in many real-world applications like urban surveillance and management, but it is greatly challenged by the camera's perspective that causes huge appearance variations in people's scales and rotations.
no code implementations • 16 Jul 2018 • Ruimao Zhang, Hongbin Sun, Jingyu Li, Yuying Ge, Liang Lin, Ping Luo, Xiaogang Wang
To address the above issues, we present a novel and practical deep architecture for video person re-identification termed Self-and-Collaborative Attention Network (SCAN).
5 code implementations • ECCV 2018 • Bochao Wang, Huabin Zheng, Xiaodan Liang, Yimin Chen, Liang Lin, Meng Yang
Second, to alleviate boundary artifacts of warped clothes and make the results more realistic, we employ a Try-On Module that learns a composition mask to integrate the warped clothes and the rendered image to ensure smoothness.
1 code implementation • ECCV 2018 • Ke Gong, Xiaodan Liang, Yicheng Li, Yimin Chen, Ming Yang, Liang Lin
Instance-level human parsing towards real-world human analysis scenarios is still under-explored due to the absence of sufficient data resources and technical difficulty in parsing multiple instances in a single pass.
Ranked #6 on Human Part Segmentation on CIHP
1 code implementation • 2 Aug 2018 • Qixian Zhou, Xiaodan Liang, Ke Gong, Liang Lin
Beyond the existing single-person and multiple-person human parsing tasks in static images, this paper makes the first attempt to investigate a more realistic video instance-level human parsing that simultaneously segments out each person instance and parses each instance into more fine-grained parts (e. g., head, leg, dress).
no code implementations • 4 Aug 2018 • Guanbin Li, Xiang He, Wei zhang, Huiyou Chang, Le Dong, Liang Lin
Single image rain streaks removal has recently witnessed substantial progress due to the development of deep convolutional neural networks.
1 code implementation • 14 Aug 2018 • Tianshui Chen, Wenxi Wu, Yuefang Gao, Le Dong, Xiaonan Luo, Liang Lin
In this work, we investigate simultaneously predicting categories of different levels in the hierarchy and integrating this structured correlation information into the deep neural network by developing a novel Hierarchical Semantic Embedding (HSE) framework.
Ranked #52 on Fine-Grained Image Classification on CUB-200-2011
Fine-Grained Image Classification Fine-Grained Image Recognition +1
no code implementations • 25 Aug 2018 • Tianshui Chen, Riquan Chen, Lin Nie, Xiaonan Luo, Xiaobai Liu, Liang Lin
This paper focuses on semantic task planning, i. e., predicting a sequence of actions toward accomplishing a specific task under a certain scene, which is a new problem in computer vision research.
no code implementations • 1 Sep 2018 • Lingbo Liu, Ruimao Zhang, Jiefeng Peng, Guanbin Li, Bowen Du, Liang Lin
Traffic flow prediction is crucial for urban traffic management and public safety.
no code implementations • ECCV 2018 • Yukang Gan, Xiangyu Xu, Wenxiu Sun, Liang Lin
While significant progress has been made in monocular depth estimation with Convolutional Neural Networks (CNNs) extracting absolute features, such as edges and textures, the depth constraint of neighboring pixels, namely relative features, has been mostly ignored by recent methods.
no code implementations • ECCV 2018 • Xiaodan Liang, Hao Zhang, Liang Lin, Eric Xing
Despite the promising results on paired/unpaired image-to-image translation achieved by Generative Adversarial Networks (GANs), prior works often only transfer the low-level information (e. g. color or texture changes), but fail to manipulate high-level semantic meanings (e. g., geometric structure or content) of different object regions.
1 code implementation • 3 Sep 2018 • Yuan Yuan, Siyuan Liu, Jiawei Zhang, Yongbing Zhang, Chao Dong, Liang Lin
We consider the single image super-resolution problem in a more general case that the low-/high-resolution pairs and the down-sampling process are unavailable.
no code implementations • 6 Sep 2018 • Qingxing Cao, Bailin Li, Xiaodan Liang, Liang Lin
Collaborative reasoning for understanding image-question pairs is a very critical but underexplored topic in interpretable visual question answering systems.
no code implementations • 27 Sep 2018 • Ziliang Chen, Keze Wang, Liang Lin
We evaluate T2T across different learners, teachers, and tasks, which significantly demonstrates that structured knowledge can be inherited by the teachers to further benefit learners' training.
no code implementations • 3 Oct 2018 • Andrey Ignatov, Radu Timofte, Thang Van Vu, Tung Minh Luu, Trung X. Pham, Cao Van Nguyen, Yongwoo Kim, Jae-Seok Choi, Munchurl Kim, Jie Huang, Jiewen Ran, Chen Xing, Xingguang Zhou, Pengfei Zhu, Mingrui Geng, Yawei Li, Eirikur Agustsson, Shuhang Gu, Luc van Gool, Etienne de Stoutz, Nikolay Kobyshev, Kehui Nie, Yan Zhao, Gen Li, Tong Tong, Qinquan Gao, Liu Hanwen, Pablo Navarrete Michelini, Zhu Dan, Hu Fengshuo, Zheng Hui, Xiumei Wang, Lirui Deng, Rang Meng, Jinghui Qin, Yukai Shi, Wushao Wen, Liang Lin, Ruicheng Feng, Shixiang Wu, Chao Dong, Yu Qiao, Subeesh Vasu, Nimisha Thekke Madam, Praveen Kandula, A. N. Rajagopalan, Jie Liu, Cheolkon Jung
This paper reviews the first challenge on efficient perceptual image enhancement with the focus on deploying deep learning models on smartphones.
no code implementations • 10 Oct 2018 • Lili Huang, Jiefeng Peng, Ruimao Zhang, Guanbin Li, Liang Lin
Semantic image parsing, which refers to the process of decomposing images into semantic regions and constructing the structure representation of the input, has recently aroused widespread interest in the field of computer vision.
1 code implementation • NeurIPS 2018 • Chenhan Jiang, Hang Xu, Xiangdan Liang, Liang Lin
The dominant object detection approaches treat the recognition of each region separately and overlook crucial semantic correlations between objects in one scene.
no code implementations • 30 Oct 2018 • Guanbin Li, Yukang Gan, Hejun Wu, Nong Xiao, Liang Lin
In this paper, we address this problem by developing a Cross-Modal Attentional Context (CMAC) learning framework, which enables the full exploitation of the context information from both RGB and depth data.
3 code implementations • ICCV 2019 • Ruijia Xu, Guanbin Li, Jihan Yang, Liang Lin
Domain adaptation enables the learner to safely generalize into novel environments by mitigating domain shifts across distributions.
Ranked #7 on Domain Adaptation on ImageCLEF-DA
no code implementations • NeurIPS 2018 • Guangrun Wang, Jiefeng Peng, Ping Luo, Xinjiang Wang, Liang Lin
In this paper, we present a novel normalization method, called Kalman Normalization (KN), for improving and accelerating the training of DNNs, particularly under the context of micro-batches.
1 code implementation • NeurIPS 2018 • Xiaodan Liang, Zhiting Hu, Hao Zhang, Liang Lin, Eric P. Xing
To cooperate with local convolutions, each SGR is constituted by three modules: a) a primal local-to-semantic voting module where the features of all symbolic nodes are generated by voting from local representations; b) a graph reasoning module propagates information over knowledge graph to achieve global semantic coherency; c) a dual semantic-to-local mapping module learns new associations of the evolved symbolic nodes with local representations, and accordingly enhances local features.
Ranked #81 on Semantic Segmentation on ADE20K val
no code implementations • 4 Dec 2018 • Xu Cai, Yang Wu, Guanbin Li, Ziliang Chen, Liang Lin
FRAME (Filters, Random fields, And Maximum Entropy) is an energy-based descriptive model that synthesizes visual realism by capturing mutual patterns from structural input signals.
no code implementations • 10 Dec 2018 • Lingbo Liu, Guanbin Li, Yuan Xie, Yizhou Yu, Qing Wang, Liang Lin
In this paper, we propose a novel cascaded backbone-branches fully convolutional neural network~(BB-FCN) for rapidly and accurately localizing facial landmarks in unconstrained and cluttered settings.
no code implementations • ICLR 2019 • Sirui Xie, Junning Huang, Lanxin Lei, Chunxiao Liu, Zheng Ma, Wei zhang, Liang Lin
Reinforcement learning agents need exploratory behaviors to escape from local optima.
2 code implementations • ICLR 2019 • Sirui Xie, Hehui Zheng, Chunxiao Liu, Liang Lin
In experiments on CIFAR-10, SNAS takes less epochs to find a cell architecture with state-of-the-art accuracy than non-differentiable evolution-based and reinforcement-learning-based NAS, which is also transferable to ImageNet.
Ranked #25 on Neural Architecture Search on NAS-Bench-201, CIFAR-10
2 code implementations • arXiv.org 2019 • Keze Wang, Liang Lin, Chenhan Jiang, Chen Qian, Pengxu Wei
Driven by recent computer vision and robotic applications, recovering 3D human poses has become increasingly important and attracted growing interests.
Ranked #263 on 3D Human Pose Estimation on Human3.6M
1 code implementation • 30 Jan 2019 • Lin Xu, Qixian Zhou, Ke Gong, Xiaodan Liang, Jianheng Tang, Liang Lin
Besides the challenges for conversational dialogue systems (e. g. topic transition coherency and question understanding), automatic medical diagnosis further poses more critical requirements for the dialogue rationality in the context of medical knowledge and symptom-disease relations.
3 code implementations • CVPR 2019 • Tianshui Chen, Weihao Yu, Riquan Chen, Liang Lin
More specifically, we show that the statistical correlations between objects appearing in images and their relationships, can be explicitly represented by a structured knowledge graph, and a routing mechanism is learned to propagate messages through the graph to explore their interactions.
Ranked #9 on Scene Graph Generation on Visual Genome
no code implementations • CVPR 2019 • Xipeng Chen, Kwan-Yee Lin, Wentao Liu, Chen Qian, Xiaogang Wang, Liang Lin
Recent studies have shown remarkable advances in 3D human pose estimation from monocular images, with the help of large-scale in-door 3D datasets and sophisticated network architectures.
1 code implementation • CVPR 2019 • Guangrun Wang, Keze Wang, Liang Lin
This paper presents a novel adaptively connected neural network (ACNet) to improve the traditional convolutional neural networks (CNNs) {in} two aspects.
Ranked #1 on Document Classification on Cora
1 code implementation • 8 Apr 2019 • Guangrun Wang, Guangcong Wang, Xujie Zhang, Jian-Huang Lai, Zhengtao Yu, Liang Lin
Learning a Re-ID model with bag-level annotation is called the weakly supervised Re-ID problem.
Ranked #2 on Person Re-Identification on SYSU-30k
1 code implementation • CVPR 2019 • Ke Gong, Yiming Gao, Xiaodan Liang, Xiaohui Shen, Meng Wang, Liang Lin
By distilling universal semantic graph representation to each specific task, Graphonomy is able to predict all levels of parsing labels in one system without piling up the complexity.
no code implementations • 22 Apr 2019 • Guanbin Li, Xin Zhu, Yirui Zeng, Qing Wang, Liang Lin
Specifically, by analyzing the symbiosis and mutual exclusion of AUs in various facial expressions, we organize the facial AUs in the form of structured knowledge-graph and integrate a Gated Graph Neural Network (GGNN) in a multi-scale CNN framework to propagate node information through the graph for generating enhanced AU representation.
no code implementations • 4 May 2019 • Yukai Shi, Guanbin Li, Qingxing Cao, Keze Wang, Liang Lin
Face hallucination is a domain-specific super-resolution problem that aims to generate a high-resolution (HR) face image from a low-resolution~(LR) input.
no code implementations • 15 May 2019 • Lingbo Liu, Zhilin Qiu, Guanbin Li, Qing Wang, Wanli Ouyang, Liang Lin
Finally, a GCC module is applied to model the correlation between all regions by computing a global correlation feature as a weighted sum of all regional features, with the weights being calculated as the similarity between the corresponding region pairs.
1 code implementation • CVPR 2019 • Ziliang Chen, Jingyu Zhuang, Xiaodan Liang, Liang Lin
(Unsupervised) Domain Adaptation (DA) seeks for classifying target instances when solely provided with source labeled and target unlabeled examples for training.
Ranked #3 on Multi-target Domain Adaptation on Office-Home
1 code implementation • 8 Jul 2019 • Ziliang Chen, Zhanfu Yang, Xiaoxi Wang, Xiaodan Liang, Xiaopeng Yan, Guanbin Li, Liang Lin
A broad range of cross-$m$-domain generation researches boil down to matching a joint distribution by deep generative models (DGMs).
no code implementations • 5 Aug 2019 • Chenglong Li, Yan Huang, Liang Wang, Jin Tang, Liang Lin
Many state-of-the-art trackers usually resort to the pretrained convolutional neural network (CNN) model for correlation filtering, in which deep features could usually be redundant, noisy and less discriminative for some certain instances, and the tracking performance might thus be affected.
1 code implementation • ICCV 2019 • Pengxiang Yan, Guanbin Li, Yuan Xie, Zhen Li, Chuan Wang, Tianshui Chen, Liang Lin
Specifically, we present an effective video saliency detector that consists of a spatial refinement network and a spatiotemporal module.
Ranked #1 on Video Salient Object Detection on VOS-T (using extra training data)
2 code implementations • ICCV 2019 • Tianshui Chen, Muxin Xu, Xiaolu Hui, Hefeng Wu, Liang Lin
Recognizing multiple labels of images is a practical and challenging task, and significant progress has been made by searching semantic-aware regions and modeling label dependency.
Ranked #8 on Multi-Label Classification on PASCAL VOC 2007
no code implementations • ICCV 2019 • Lingbo Liu, Zhilin Qiu, Guanbin Li, Shufan Liu, Wanli Ouyang, Liang Lin
Automatic estimation of the number of people in unconstrained crowded scenes is a challenging task and one major difficulty stems from the huge scale variation of people.
no code implementations • ICCV 2019 • Zhanghui Kuang, Yiming Gao, Guanbin Li, Ping Luo, Yimin Chen, Liang Lin, Wayne Zhang
To address this issue, we propose a novel Graph Reasoning Network (GRNet) on a Similarity Pyramid, which learns similarities between a query and a gallery cloth by using both global and local representations in multiple scales.
Ranked #4 on Image Retrieval on DeepFashion - Consumer-to-shop (Rank-1 metric)
2 code implementations • 2 Sep 2019 • Lingbo Liu, Jiajie Zhen, Guanbin Li, Geng Zhan, Zhaocheng He, Bowen Du, Liang Lin
Specifically, the first ConvLSTM unit takes normal traffic flow features as input and generates a hidden state at each time-step, which is further fed into the connected convolutional layer for spatial attention map inference.
no code implementations • 23 Sep 2019 • Qingxing Cao, Bailin Li, Xiaodan Liang, Liang Lin
Explanation and high-order reasoning capabilities are crucial for real-world visual question answering with diverse levels of inference complexity (e. g., what is the dog that is near the girl playing with?)
no code implementations • 28 Sep 2019 • Xiaopeng Yan, Ziliang Chen, Anni Xu, Xiaoxi Wang, Xiaodan Liang, Liang Lin
Resembling the rapid learning capability of human, few-shot learning empowers vision systems to understand new concepts by training with few samples.
Ranked #19 on Few-Shot Object Detection on MS-COCO (30-shot)
no code implementations • CVPR 2019 • Weijiang Yu, Xiaodan Liang, Ke Gong, Chenhan Jiang, Nong Xiao, Liang Lin
Each Layout-Graph Reasoning(LGR) layer aims to map feature representations into structural graph nodes via a Map-to-Node module, performs reasoning over structural graph nodes to achieve global layout coherency via a layout-graph reasoning module, and then maps graph nodes back to enhance feature representations via a Node-to-Map module.
no code implementations • 31 Oct 2019 • Yang Wu, Pengxu Wei, Liang Lin
To solve this problem, we derive a second-order Wasserstein gradient flow of the global relative entropy from Fokker-Planck equation.
1 code implementation • 21 Nov 2019 • Riquan Chen, Tianshui Chen, Xiaolu Hui, Hefeng Wu, Guanbin Li, Liang Lin
In this work, we represent the semantic correlations in the form of structured knowledge graph and integrate this graph into deep neural networks to promote few-shot learning by a novel Knowledge Graph Transfer Network (KGTN).
1 code implementation • 29 Nov 2019 • Changlin Li, Jiefeng Peng, Liuchun Yuan, Guangrun Wang, Xiaodan Liang, Liang Lin, Xiaojun Chang
Moreover, we find that the knowledge of a network model lies not only in the network parameters but also in the network architecture.
Ranked #1 on Neural Architecture Search on CIFAR-100
no code implementations • 18 Dec 2019 • Jihan Yang, Ruijia Xu, Ruiyu Li, Xiaojuan Qi, Xiaoyong Shen, Guanbin Li, Liang Lin
In contrast to adversarial alignment, we propose to explicitly train a domain-invariant classifier by generating and defensing against pointwise feature space adversarial perturbations.
2 code implementations • 14 Jan 2020 • Lingbo Liu, Jingwen Chen, Hefeng Wu, Jiajie Zhen, Guanbin Li, Liang Lin
To address this problem, we model a metro system as graphs with various topologies and propose a unified Physical-Virtual Collaboration Graph Network (PVCGN), which can effectively learn the complex ridership patterns from the tailor-designed graphs.
1 code implementation • 18 Jan 2020 • Jie Wu, Guanbin Li, Si Liu, Liang Lin
Temporally language grounding in untrimmed videos is a newly-raised task in video understanding.
no code implementations • 22 Jan 2020 • Haofeng Li, Guanbin Li, BinBin Yang, Guanqi Chen, Liang Lin, Yizhou Yu
The proposed algorithm for the first time achieves competitive accuracy and high inference efficiency simultaneously with a single CPU thread.
1 code implementation • 25 Feb 2020 • Yukai Shi, Haoyu Zhong, Zhijing Yang, Xiaojun Yang, Liang Lin
Previous image SR methods fail to exhibit similar performance on Real-SR as the image data is not aligned inherently.
1 code implementation • 14 Mar 2020 • Junfan Lin, Keze Wang, Ziliang Chen, Xiaodan Liang, Liang Lin
To eliminate this bias and inspired by the propensity score matching technique with causal diagram, we propose a propensity-based patient simulator to effectively answer unrecorded inquiry by drawing knowledge from the other records; Bias (ii) inherently comes along with the passively collected data, and is one of the key obstacles for training the agent towards "learning how" rather than "remembering what".
no code implementations • 23 Mar 2020 • Qingxing Cao, Xiaodan Liang, Keze Wang, Liang Lin
Inspired by the property of a capsule network that can carve a tree structure inside a regular convolutional neural network (CNN), we propose a hierarchical compositional reasoning model called the "Linguistically driven Graph Capsule Network", where the compositional process is guided by the linguistic parse tree.
2 code implementations • 23 Mar 2020 • Lingbo Liu, Jiaqi Chen, Hefeng Wu, Tianshui Chen, Guanbin Li, Liang Lin
Crowd counting is an application-oriented task and its inference efficiency is crucial for real-world applications.
1 code implementation • CVPR 2020 • Hongjun Wang, Guangrun Wang, Ya Li, Dongyu Zhang, Liang Lin
To examine the robustness of ReID systems is rather important because the insecurity of ReID systems may cause severe losses, e. g., the criminals may use the adversarial perturbations to cheat the CCTV systems.
no code implementations • CVPR 2020 • Yangxin Wu, Gengwei Zhang, Yiming Gao, Xiajun Deng, Ke Gong, Xiaodan Liang, Liang Lin
We introduce a Bidirectional Graph Reasoning Network (BGRNet), which incorporates graph structure into the conventional panoptic segmentation network to mine the intra-modular and intermodular relations within and between foreground things and background stuff classes.
no code implementations • 24 Apr 2020 • Zhongzhan Huang, Wenqi Shao, Xinjiang Wang, Liang Lin, Ping Luo
Channel pruning is a popular technique for compressing convolutional neural networks (CNNs), where various pruning criteria have been proposed to remove the redundant filters.
no code implementations • 3 May 2020 • Kai Zhang, Shuhang Gu, Radu Timofte, Taizhang Shang, Qiuju Dai, Shengchen Zhu, Tong Yang, Yandong Guo, Younghyun Jo, Sejong Yang, Seon Joo Kim, Lin Zha, Jiande Jiang, Xinbo Gao, Wen Lu, Jing Liu, Kwangjin Yoon, Taegyun Jeon, Kazutoshi Akita, Takeru Ooba, Norimichi Ukita, Zhipeng Luo, Yuehan Yao, Zhenyu Xu, Dongliang He, Wenhao Wu, Yukang Ding, Chao Li, Fu Li, Shilei Wen, Jianwei Li, Fuzhi Yang, Huan Yang, Jianlong Fu, Byung-Hoon Kim, JaeHyun Baek, Jong Chul Ye, Yuchen Fan, Thomas S. Huang, Junyeop Lee, Bokyeung Lee, Jungki Min, Gwantae Kim, Kanghyu Lee, Jaihyun Park, Mykola Mykhailych, Haoyu Zhong, Yukai Shi, Xiaojun Yang, Zhijing Yang, Liang Lin, Tongtong Zhao, Jinjia Peng, Huibing Wang, Zhi Jin, Jiahao Wu, Yifu Chen, Chenming Shang, Huanrong Zhang, Jeongki Min, Hrishikesh P. S, Densen Puthussery, Jiji C. V
This paper reviews the NTIRE 2020 challenge on perceptual extreme super-resolution with focus on proposed solutions and results.
1 code implementation • ECCV 2020 • Bailin Li, Bowen Wu, Jiang Su, Guangrun Wang, Liang Lin
Many algorithms try to predict model performance of the pruned sub-nets by introducing various evaluation methods.
Ranked #6 on Network Pruning on ImageNet
1 code implementation • 21 Jul 2020 • Jie Wu, Tianshui Chen, Hefeng Wu, Zhi Yang, Guangchun Luo, Liang Lin
This is primarily due to (i) the conservative characteristic of traditional training objectives that drives the model to generate correct but hardly discriminative captions for similar images and (ii) the uneven word distribution of the ground-truth captions, which encourages generating highly frequent words/phrases while suppressing the less frequent but more concrete ones.
1 code implementation • 3 Aug 2020 • Yuan Xie, Tianshui Chen, Tao Pu, Hefeng Wu, Liang Lin
However, most of these works focus on holistic feature adaptation, and they ignore local features that are more transferable across different datasets.
Cross-Domain Facial Expression Recognition Facial Expression Recognition (FER)
1 code implementation • 3 Aug 2020 • Tianshui Chen, Tao Pu, Hefeng Wu, Yuan Xie, Lingbo Liu, Liang Lin
Although each declares to achieve superior performance, fair comparisons are lacking due to the inconsistent choices of the source/target datasets and feature extractors.
Ranked #1 on Cross-Domain Facial Expression Recognition on Source: AFE, Target: CK+, JAFFE, SFEW2.0, FER2013, ExpW
Cross-Domain Facial Expression Recognition Domain Adaptation +3
1 code implementation • ECCV 2020 • Pengxu Wei, Ziwei Xie, Hannan Lu, Zongyuan Zhan, Qixiang Ye, WangMeng Zuo, Liang Lin
Learning an SR model with conventional pixel-wise loss usually is easily dominated by flat regions and edges, and fails to infer realistic details of complex textures.
no code implementations • 23 Aug 2020 • Junpeng Tan, Yukai Shi, Zhijing Yang, Caizhen Wen, Liang Lin
To ensure that we achieve effective sparse representation and clustering performance on the original data matrix, adaptive graph regularization and unsupervised clustering constraints are also incorporated in the proposed model to preserve the internal structural features of the data.
1 code implementation • 1 Sep 2020 • Yang Liu, Keze Wang, Guanbin Li, Liang Lin
In this paper, we propose a novel framework, named Semantics-aware Adaptive Knowledge Distillation Networks (SAKDN), to enhance action recognition in vision-sensor modality (videos) by adaptively transferring and distilling the knowledge from multiple wearable sensors.
no code implementations • 17 Sep 2020 • Haofeng Li, Yirui Zeng, Guanbin Li, Liang Lin, Yizhou Yu
The field of computer vision has witnessed phenomenal progress in recent years partially due to the development of deep convolutional neural networks.
1 code implementation • ECCV 2020 • Ganlong Zhao, Guanbin Li, Ruijia Xu, Liang Lin
Domain adaptation for object detection tries to adapt the detector from labeled datasets to unlabeled ones for better performance.
no code implementations • 18 Sep 2020 • Jie Wu, Guanbin Li, Xiaoguang Han, Liang Lin
Temporal grounding of natural language in untrimmed videos is a fundamental yet challenging multimedia task facilitating cross-media visual content retrieval.
no code implementations • 20 Sep 2020 • Tianshui Chen, Liang Lin, Riquan Chen, Xiaolu Hui, Hefeng Wu
The framework exploits prior knowledge to guide adaptive information propagation among different categories to facilitate multi-label analysis and reduce the dependency of training samples.
Few-Shot Learning Multi-label Image Recognition with Partial Labels
no code implementations • 25 Sep 2020 • Pengxu Wei, Hannan Lu, Radu Timofte, Liang Lin, WangMeng Zuo, Zhihong Pan, Baopu Li, Teng Xi, Yanwen Fan, Gang Zhang, Jingtuo Liu, Junyu Han, Errui Ding, Tangxin Xie, Liang Cao, Yan Zou, Yi Shen, Jialiang Zhang, Yu Jia, Kaihua Cheng, Chenhuan Wu, Yue Lin, Cen Liu, Yunbo Peng, Xueyi Zou, Zhipeng Luo, Yuehan Yao, Zhenyu Xu, Syed Waqas Zamir, Aditya Arora, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Tongtong Zhao, Shanshan Zhao, Yoseob Han, Byung-Hoon Kim, JaeHyun Baek, HaoNing Wu, Dejia Xu, Bo Zhou, Wei Guan, Xiaobo Li, Chen Ye, Hao Li, Yukai Shi, Zhijing Yang, Xiaojun Yang, Haoyu Zhong, Xin Li, Xin Jin, Yaojun Wu, Yingxue Pang, Sen Liu, Zhi-Song Liu, Li-Wen Wang, Chu-Tak Li, Marie-Paule Cani, Wan-Chi Siu, Yuanbo Zhou, Rao Muhammad Umer, Christian Micheloni, Xiaofeng Cong, Rajat Gupta, Keon-Hee Ahn, Jun-Hyuk Kim, Jun-Ho Choi, Jong-Seok Lee, Feras Almasri, Thomas Vandamme, Olivier Debeir
This paper introduces the real image Super-Resolution (SR) challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2020.
1 code implementation • EMNLP 2020 • Lishan Huang, Zheng Ye, Jinghui Qin, Liang Lin, Xiaodan Liang
Capitalized on the topic-level dialogue graph, we propose a new evaluation metric GRADE, which stands for Graph-enhanced Representations for Automatic Dialogue Evaluation.
1 code implementation • EMNLP 2020 • Jinghui Qin, Lihui Lin, Xiaodan Liang, Rumin Zhang, Liang Lin
A practical automatic textual math word problems (MWPs) solver should be able to solve various textual MWPs while most existing works only focused on one-unknown linear MWPs.
Ranked #10 on Math Word Problem Solving on ALG514
no code implementations • 15 Oct 2020 • Hongjun Wang, Guanbin Li, Xiaobai Liu, Liang Lin
Although deep convolutional neural networks (CNNs) have demonstrated remarkable performance on multiple computer vision tasks, researches on adversarial learning have shown that deep models are vulnerable to adversarial examples, which are crafted by adding visually imperceptible perturbations to the input images.
2 code implementations • NeurIPS 2020 • Yangxin Wu, Gengwei Zhang, Hang Xu, Xiaodan Liang, Liang Lin
In this work, we propose an efficient, cooperative and highly automated framework to simultaneously search for all main components including backbone, segmentation branches, and feature fusion module in a unified panoptic segmentation pipeline based on the prevailing one-shot Network Architecture Search (NAS) paradigm.
1 code implementation • 30 Nov 2020 • Junfan Lin, Zhongzhan Huang, Keze Wang, Xiaodan Liang, Weiwei Chen, Liang Lin
Although deep reinforcement learning (RL) has been successfully applied to a variety of robotic control tasks, it's still challenging to apply it to real-world tasks, due to the poor sample efficiency.
1 code implementation • CVPR 2021 • Lingbo Liu, Jiaqi Chen, Hefeng Wu, Guanbin Li, Chenglong Li, Liang Lin
Extensive experiments conducted on the RGBT-CC benchmark demonstrate the effectiveness of our framework for RGBT crowd counting.
1 code implementation • 14 Dec 2020 • Qingxing Cao, Bailin Li, Xiaodan Liang, Keze Wang, Liang Lin
Specifically, we generate the question-answer pair based on both the Visual Genome scene graph and an external knowledge base with controlled programs to disentangle the knowledge from other biases.
1 code implementation • 22 Dec 2020 • Shuai Lin, Pan Zhou, Xiaodan Liang, Jianheng Tang, Ruihui Zhao, Ziliang Chen, Liang Lin
Besides, we develop a Graph-Evolving Meta-Learning (GEML) framework that learns to evolve the commonsense graph for reasoning disease-symptom correlations in a new disease, which effectively alleviates the needs of a large number of dialogues.
no code implementations • 22 Dec 2020 • Yubei Xiao, Ke Gong, Pan Zhou, Guolin Zheng, Xiaodan Liang, Liang Lin
When sampling tasks in MML-ASR, AMS adaptively determines the task sampling probability for each source language.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
no code implementations • 24 Dec 2020 • Yinya Huang, Meng Fang, Xunlin Zhan, Qingxing Cao, Xiaodan Liang, Liang Lin
It is crucial since the quality of the evidence is the key to answering commonsense questions, and even determines the upper bound on the QA systems performance.
1 code implementation • 29 Dec 2020 • Tao Pu, Tianshui Chen, Yuan Xie, Hefeng Wu, Liang Lin
In this work, we explore the correlations among the action units and facial expressions, and devise an AU-Expression Knowledge Constrained Representation Learning (AUE-CRL) framework to learn the AU representations without AU annotations and adaptively use representations to facilitate facial expression recognition.
Facial Expression Recognition Facial Expression Recognition (FER) +1
no code implementations • 1 Jan 2021 • Junfan Lin, Changxin Huang, Xiaodan Liang, Liang Lin
The curiosity is added to the target entropy to increase the entropy temperature for unfamiliar states and decrease the target entropy for familiar states.
no code implementations • ICCV 2021 • Qingxing Cao, Wentao Wan, Keze Wang, Xiaodan Liang, Liang Lin
The experimental results show that our proposed method can improve current VQA models on OOD split without losing performance on the in-domain test data.
no code implementations • 1 Jan 2021 • Fuyu Wang, Pan Zhou, Xiaodan Liang, Liang Lin
To solve this issue, we propose a novel DynamIc Self-sUperviSed Erasure (DISUSE) which adaptively erases redundant and artifactual clues in the context and questions to learn and establish the correct corresponding pair relations between the questions and their clues.
no code implementations • 1 Jan 2021 • Junfan Lin, Lin Xu, Ziliang Chen, Liang Lin
To this end, we propose a novel DSMAD agent, INS-DS (Introspective Diagnosis System) comprising of two separate yet cooperative modules, i. e., an inquiry module for proposing symptom-inquiries and an introspective module for deciding when to inform a disease.
no code implementations • 1 Jan 2021 • Hongjun Wang, Guanbin Li, Liang Lin
To protect the security of machine learning models against adversarial examples, adversarial training becomes the most popular and powerful strategy against various adversarial attacks by injecting adversarial examples into training data.
no code implementations • 4 Jan 2021 • Yang Liu, Keze Wang, Haoyuan Lan, Liang Lin
To model multi-scale temporal dependencies, our TCGL integrates the prior knowledge about the frame and snippet orders into graph structures, i. e., the intra-/inter- snippet temporal contrastive graphs.
no code implementations • 9 Jan 2021 • Fuyu Wang, Xiaodan Liang, Lin Xu, Liang Lin
Beyond generating long and topic-coherent paragraphs in traditional captioning tasks, the medical image report composition task poses more task-oriented challenges by requiring both the highly-accurate medical term diagnosis and multiple heterogeneous forms of information including impression and findings.
2 code implementations • 26 Jan 2021 • Liang Lin, Yiming Gao, Ke Gong, Meng Wang, Xiaodan Liang
Prior highly-tuned image parsing models are usually studied in a certain domain with a specific set of semantic labels and can hardly be adapted into other scenarios (e. g., sharing discrepant label granularity) without extensive re-training.
no code implementations • 1 Feb 2021 • Yukai Shi, Sen Zhang, Chenxing Zhou, Xiaodan Liang, Xiaojun Yang, Liang Lin
Non-parallel text style transfer has attracted increasing research interests in recent years.
no code implementations • 31 Mar 2021 • Guangrun Wang, Liang Lin, Rongcong Chen, Guangcong Wang, Jiqi Zhang
In this work, we prove that dynamically adapting network architectures tailored for each domain task along with weight finetuning benefits in both efficiency and effectiveness, compared to the existing image recognition pipeline that only tunes the weights regardless of the architecture.
1 code implementation • ICCV 2021 • Guangrun Wang, Keze Wang, Guangcong Wang, Philip H. S. Torr, Liang Lin
In this paper, we reveal two contradictory phenomena in contrastive learning that we call under-clustering and over-clustering problems, which are major obstacles to learning efficiency.
Ranked #1 on Self-Supervised Person Re-Identification on SYSU-30k
1 code implementation • Findings (ACL) 2021 • Jiaqi Chen, Jianheng Tang, Jinghui Qin, Xiaodan Liang, Lingbo Liu, Eric P. Xing, Liang Lin
Therefore, we propose a Geometric Question Answering dataset GeoQA, containing 4, 998 geometric problems with corresponding annotated programs, which illustrate the solving process of the given problems.
Ranked #4 on Mathematical Reasoning on PGPS9K
1 code implementation • ACL 2021 • Zheng Ye, Liucun Lu, Lishan Huang, Liang Lin, Xiaodan Liang
To address these limitations, we propose Quantifiable Dialogue Coherence Evaluation (QuantiDCE), a novel framework aiming to train a quantifiable dialogue coherence metric that can reflect the actual human rating standards.
1 code implementation • 17 Jun 2021 • Shuai Lin, Pan Zhou, Zi-Yuan Hu, Shuojia Wang, Ruihui Zhao, Yefeng Zheng, Liang Lin, Eric Xing, Xiaodan Liang
However, since for a query, its negatives are uniformly sampled from all graphs, existing methods suffer from the critical sampling bias issue, i. e., the negatives likely having the same semantic structure with the query, leading to performance degradation.
1 code implementation • 2 Jul 2021 • Lingbo Liu, Yuying Zhu, Guanbin Li, Ziyi Wu, Lei Bai, Liang Lin
In this work, we proposed a novel neural network module termed Heterogeneous Information Aggregation Machine (HIAM), which fully exploits heterogeneous information of historical data (e. g., incomplete OD matrices, unfinished order vectors, and DO matrices) to jointly learn the evolutionary patterns of OD and DO ridership.
1 code implementation • ACL 2021 • Jinghui Qin, Xiaodan Liang, Yining Hong, Jianheng Tang, Liang Lin
Previous math word problem solvers following the encoder-decoder paradigm fail to explicitly incorporate essential math symbolic constraints, leading to unexplainable and unreasonable predictions.
1 code implementation • 23 Jul 2021 • Bingqian Lin, Yi Zhu, Yanxin Long, Xiaodan Liang, Qixiang Ye, Liang Lin
Specifically, we propose a Dynamic Reinforced Instruction Attacker (DR-Attacker), which learns to mislead the navigator to move to the wrong target by destroying the most instructive information in instructions at different timesteps.
no code implementations • 9 Aug 2021 • Jie Wu, Wei zhang, Guanbin Li, Wenhao Wu, Xiao Tan, YingYing Li, Errui Ding, Liang Lin
In this paper, we introduce a novel task, referred to as Weakly-Supervised Spatio-Temporal Anomaly Detection (WSSTAD) in surveillance video.
no code implementations • ICCV 2021 • Junkai Huang, Chaowei Fang, Weikai Chen, Zhenhua Chai, Xiaolin Wei, Pengxu Wei, Liang Lin, Guanbin Li
Open-set semi-supervised learning (open-set SSL) investigates a challenging but practical scenario where out-of-distribution (OOD) samples are contained in the unlabeled data.
1 code implementation • ICCV 2021 • Jiefeng Peng, Jiqi Zhang, Changlin Li, Guangrun Wang, Xiaodan Liang, Liang Lin
We attribute this ranking correlation problem to the supernet training consistency shift, including feature shift and parameter shift.
no code implementations • Findings (EMNLP) 2021 • Guolin Zheng, Yubei Xiao, Ke Gong, Pan Zhou, Xiaodan Liang, Liang Lin
Specifically, we unify a pre-trained acoustic model (wav2vec 2. 0) and a language model (BERT) into an end-to-end trainable framework.