no code implementations • NeurIPS 2008 • Chunhua Shen, Alan Welsh, Lei Wang
In this work, we consider the problem of learning a positive semidefinite matrix.
no code implementations • 23 Jan 2009 • Chunhua Shen, Hanxi Li
We study boosting algorithms from a new perspective.
no code implementations • NeurIPS 2009 • Chunhua Shen, Junae Kim, Lei Wang, Anton Hengel
In this work, we propose a boosting-based technique, termed BoostMetric, for learning a Mahalanobis distance metric.
no code implementations • 29 Sep 2010 • Sakrapee Paisitkriangkrai, Chunhua Shen, Jian Zhang
There is an abundant literature on face detection due to its important role in many vision applications.
no code implementations • 3 Oct 2011 • Hanxi Li, Chunhua Shen, Yongsheng Gao
It also overwhelms other modular heuristics on the faces with random occlusions, extreme expressions and disguises.
no code implementations • 14 Feb 2013 • Chunhua Shen, Guosheng Lin, Anton Van Den Hengel
Inspired by structured support vector machines (SSVM), here we propose a new boosting algorithm for structured output prediction, which we refer to as StructBoost.
no code implementations • 25 Mar 2013 • Sakrapee Paisitkriangkrai, Chunhua Shen, Anton Van Den Hengel
In this work, we present a new approach to train an effective node classifier in a cascade detector.
no code implementations • CVPR 2013 • Fumin Shen, Chunhua Shen, Qinfeng Shi, Anton Van Den Hengel, Zhenmin Tang
We particularly show that hashing on the basis of t-SNE .
1 code implementation • CVPR 2013 • Peng Wang, Chunhua Shen, Anton Van Den Hengel
Second, compared with conventional SDP methods, the new SDP formulation leads to a significantly more efficient and scalable dual optimization approach, which has the same degree of complexity as spectral methods.
no code implementations • 4 Apr 2013 • Fumin Shen, Chunhua Shen, Rhys Hill, Anton Van Den Hengel, Zhenmin Tang
Minimization of the $L_\infty$ norm, which can be viewed as approximately solving the non-convex least median estimation problem, is a powerful method for outlier removal and hence robust regression.
no code implementations • CVPR 2013 • Zhenhua Wang, Qinfeng Shi, Chunhua Shen, Anton Van Den Hengel
Markov Random Fields (MRFs) have been successfully applied to human activity modelling, largely due to their ability to model complex dependencies and deal with local uncertainty.
no code implementations • CVPR 2013 • Xi Li, Chunhua Shen, Anthony Dick, Anton Van Den Hengel
A key problem in visual tracking is to represent the appearance of an object in a way that is robust to visual changes.
no code implementations • CVPR 2013 • Rui Yao, Qinfeng Shi, Chunhua Shen, Yanning Zhang, Anton Van Den Hengel
Despite many advances made in the area, deformable targets and partial occlusions continue to represent key problems in visual tracking.
no code implementations • 21 Jul 2013 • Sakrapee Paisitkriangkrai, Chunhua Shen, Anton Van Den Hengel
In this work, we propose a scalable and simple stage-wise multi-class boosting method, which also directly maximizes the multi-class margin.
no code implementations • 7 Sep 2013 • Guosheng Lin, Chunhua Shen, David Suter, Anton Van Den Hengel
This framework allows a number of existing approaches to hashing to be placed in context, and simplifies the development of new problem-specific hashing methods.
no code implementations • 22 Sep 2013 • Fumin Shen, Chunhua Shen
The main finding of this work is that the standard image classification pipeline, which consists of dictionary learning, feature encoding, spatial pyramid pooling and linear classification, outperforms all state-of-the-art face recognition methods on the tested benchmark datasets (we have tested on AR, Extended Yale B, the challenging FERET, and LFW-a datasets).
no code implementations • 25 Sep 2013 • Yao Li, Wenjing Jia, Chunhua Shen, Anton Van Den Hengel
In order to measure the characterness we develop three novel cues that are tailored for character detection, and a Bayesian method for their integration.
no code implementations • 3 Oct 2013 • Fayao Liu, Luping Zhou, Chunhua Shen, Jianping Yin
In this work, we propose a novel multiple kernel learning framework to combine multi-modal features for AD classification, which is scalable and easy to implement.
no code implementations • 3 Oct 2013 • Sakrapee Paisitkriangkrai, Chunhua Shen, Anton Van Den Hengel
We propose a novel ensemble learning method which achieves a maximal detection rate at a user-defined range of false positive rates by directly optimizing the partial AUC using structured learning.
no code implementations • 7 Oct 2013 • Fayao Liu, Chunhua Shen, Ian Reid, Anton Van Den Hengel
Feature encoding with respect to an over-complete dictionary learned by unsupervised methods, followed by spatial pyramid pooling, and linear classification, has exhibited powerful strength in various vision applications.
no code implementations • 18 Oct 2013 • Mehrtash Harandi, Conrad Sanderson, Chunhua Shen, Brian C. Lovell
Recent advances in computer vision and machine learning suggest that a wide range of problems can be addressed more appropriately by considering non-Euclidean geometry.
no code implementations • 22 Oct 2013 • Xi Li, Yao Li, Chunhua Shen, Anthony Dick, Anton Van Den Hengel
In this work, we model an image as a hypergraph that utilizes a set of hyperedges to capture the contextual properties of image pixels or regions.
no code implementations • 23 Nov 2013 • Guosheng Lin, Chunhua Shen, Anton Van Den Hengel, David Suter
Different from most existing multi-class boosting methods, which use the same set of weak learners for all the classes, we train class specified weak learners (i. e., each class has a different set of weak learners).
no code implementations • 17 Dec 2013 • Zhen Zhang, Qinfeng Shi, Yanning Zhang, Chunhua Shen, Anton Van Den Hengel
We show that using Marginal Polytope Diagrams allows the number of constraints to be reduced without loosening the LP relaxations.
no code implementations • 4 Jan 2014 • Xi Li, Weiming Hu, Chunhua Shen, Anthony Dick, Zhongfei Zhang
Using both CAHSM and DHPC, a robust spectral clustering algorithm is developed.
no code implementations • 4 Jan 2014 • Chunhua Shen, Fayao Liu
This finding not only enables us to design new ensemble learning methods directly from kernel methods, but also makes it possible to take advantage of those highly-optimized fast linear SVM solvers for ensemble learning.
no code implementations • 30 Jan 2014 • Lingqiao Liu, Lei Wang, Chunhua Shen
In the third criterion, which shows the best merging performance, we propose a max-margin-based parameter estimation method and apply it with multinomial distribution.
no code implementations • 31 Jan 2014 • Mehrtash Harandi, Richard Hartley, Chunhua Shen, Brian Lovell, Conrad Sanderson
With the aim of building a bridge between the two realms, we address the problem of sparse coding and dictionary learning over the space of linear subspaces, which form Riemannian structures known as Grassmann manifolds.
no code implementations • 22 Feb 2014 • Yan Yan, Chunhua Shen, Hanzi Wang
constraint for spectral clustering.
no code implementations • 26 Feb 2014 • Sakrapee Paisitkriangkrai, Chunhua Shen, Anton Van Den Hengel
The use of high-dimensional features has become a normal practice in many computer vision applications.
1 code implementation • CVPR 2014 • Guosheng Lin, Chunhua Shen, Qinfeng Shi, Anton Van Den Hengel, David Suter
Here we propose to use boosted decision trees for achieving non-linearity in hashing, which are fast to train and evaluate, hence more suitable for hashing with high dimensional data.
no code implementations • 13 Apr 2014 • Fayao Liu, Chunhua Shen
In this work, we propose to learn deep convolutional image features using unsupervised and supervised learning.
no code implementations • 20 Apr 2014 • Peng Wang, Chunhua Shen, Anton Van Den Hengel, Philip Torr
We propose a Branch-and-Cut (B&C) method for solving general MAP-MRF inference problems.
no code implementations • 26 Jun 2014 • Fumin Shen, Chunhua Shen, Heng Tao Shen
Spatial pyramid pooling of features encoded by an over-complete dictionary has been the key component of many state-of-the-art image classification systems.
no code implementations • 26 Jun 2014 • Fumin Shen, Chunhua Shen, Heng Tao Shen
We propose a very simple, efficient yet surprisingly effective feature extraction method for face recognition (about 20 lines of Matlab code), which is mainly inspired by spatial pyramid pooling in generic image classification.
no code implementations • 3 Jul 2014 • Sakrapee Paisitkriangkrai, Chunhua Shen, Anton Van Den Hengel
The combination of these factors leads to a pedestrian detector which outperforms all competitors on all of the standard benchmark datasets.
no code implementations • 4 Jul 2014 • Guosheng Lin, Chunhua Shen, Jianxin Wu
Hashing has proven a valuable tool for large-scale information retrieval.
1 code implementation • 24 Aug 2014 • Guosheng Lin, Chunhua Shen, Anton Van Den Hengel
The proposed framework allows a number of existing approaches to hashing to be placed in context, and simplifies the development of new problem-specific hashing methods.
no code implementations • 7 Sep 2014 • Lei Luo, Chunhua Shen, Xinwang Liu, Chunyuan Zhang
We propose and implement a computational model for the short-cut rule and apply it to the problem of shape decomposition.
no code implementations • 18 Sep 2014 • Sakrapee Paisitkriangkrai, Chunhua Shen, Anton Van Den Hengel
Experimental results on both synthetic and real-world data sets demonstrate the effectiveness of our approach, and we show that it is possible to train state-of-the-art pedestrian detectors using the proposed structured ensemble learning method with spatially pooled features.
no code implementations • CVPR 2015 • Fayao Liu, Chunhua Shen, Guosheng Lin
Therefore, we in this paper present a deep convolutional neural field model for estimating depths from a single image, aiming to jointly explore the capacity of deep CNN and continuous CRF.
no code implementations • NeurIPS 2014 • Lingqiao Liu, Chunhua Shen, Lei Wang, Anton Van Den Hengel, Chao Wang
By calculating the gradient vector of the proposed model, we derive a new fisher vector encoding strategy, termed Sparse Coding based Fisher Vector Coding (SCFVC).
no code implementations • CVPR 2015 • Yao Li, Lingqiao Liu, Chunhua Shen, Anton Van Den Hengel
We apply our approach to scene and object classification tasks, and demonstrate that our approach outperforms all previous works on mid-level visual element discovery by a sizeable margin with far fewer elements being used.
no code implementations • 27 Nov 2014 • Peng Wang, Chunhua Shen, Anton Van Den Hengel, Philip H. S. Torr
Two standard relaxation methods are widely used for solving general BQPs--spectral methods and semidefinite programming (SDP), each with their own advantages and disadvantages.
no code implementations • 27 Nov 2014 • Hui Li, Chunhua Shen, Anton Van Den Hengel, Qinfeng Shi
Our method is also much faster and more scalable than standard interior-point SDP solvers based WLDA.
1 code implementation • CVPR 2015 • Lingqiao Liu, Chunhua Shen, Anton Van Den Hengel
This paper, however, advocates that if used appropriately convolutional layer activations can be turned into a powerful image representation which enjoys many advantages over fully-connected layer activations.
no code implementations • 2 Dec 2014 • Fumin Shen, Chunhua Shen, Qinfeng Shi, Anton Van Den Hengel, Zhenmin Tang, Heng Tao Shen
In addition, a supervised inductive manifold hashing framework is developed by incorporating the label information, which is shown to greatly advance the semantic retrieval performance.
1 code implementation • 4 Jan 2015 • Chao Zhang, Chunhua Shen, Tingzhi Shen
We experimentally demonstrate that the learned features, together with our matching model, outperforms state-of-the-art methods such as the SIFT flow, coherency sensitive hashing and the recent deformable spatial pyramid matching methods both in terms of accuracy and computation efficiency.
1 code implementation • 26 Feb 2015 • Fayao Liu, Chunhua Shen, Guosheng Lin, Ian Reid
Therefore, here we present a deep convolutional neural field model for estimating depths from single monocular images, aiming to jointly explore the capacity of deep CNN and continuous CRF.
no code implementations • 4 Mar 2015 • Peng Wang, Yuanzhouhan Cao, Chunhua Shen, Lingqiao Liu, Heng Tao Shen
One challenge is that video contains a varying number of frames which is incompatible to the standard input format of CNNs.
1 code implementation • CVPR 2015 • Fumin Shen, Chunhua Shen, Wei Liu, Heng Tao Shen
This paper has been withdrawn by the authour.
no code implementations • CVPR 2015 • Sakrapee Paisitkriangkrai, Chunhua Shen, Anton Van Den Hengel
We propose an effective structured learning based approach to the problem of person re-identification which outperforms the current state-of-the-art on most benchmark data sets evaluated.
no code implementations • 28 Mar 2015 • Fayao Liu, Guosheng Lin, Chunhua Shen
The deep CNN is trained on the ImageNet dataset and transferred to image segmentations here for constructing potentials of superpixels.
no code implementations • CVPR 2016 • Guosheng Lin, Chunhua Shen, Anton van dan Hengel, Ian Reid
Recent advances in semantic image segmentation have mostly been achieved by training deep convolutional neural networks (CNNs).
Ranked #54 on Semantic Segmentation on PASCAL Context
no code implementations • CVPR 2015 • Peng Wang, Chunhua Shen, Anton Van Den Hengel
Conditional Random Fields (CRF) have been widely used in a variety of computer vision tasks.
no code implementations • 20 Apr 2015 • Ruizhi Qiao, Lingqiao Liu, Chunhua Shen, Anton von den Hengel
The introduction of low-cost RGB-D sensors has promoted the research in skeleton-based human action recognition.
no code implementations • CVPR 2015 • Bo Li, Chunhua Shen, Yuchao Dai, Anton Van Den Hengel, Mingyi He
Predicting the depth (or surface normal) of a scene from single monocular color images is a challenging task.
no code implementations • CVPR 2015 • Mingkui Tan, Qinfeng Shi, Anton Van Den Hengel, Chunhua Shen, Junbin Gao, Fuyuan Hu, Zhen Zhang
Exploiting label dependency for multi-label image classification can significantly improve classification performance.
1 code implementation • CVPR 2016 • Qi Wu, Chunhua Shen, Lingqiao Liu, Anthony Dick, Anton Van Den Hengel
Much of the recent progress in Vision-to-Language (V2L) problems has been achieved through a combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs).
no code implementations • NeurIPS 2015 • Guosheng Lin, Chunhua Shen, Ian Reid, Anton Van Den Hengel
The network output dimension for message estimation is the same as the number of classes, in contrast to the network output for general CNN potential functions in CRFs, which is exponential in the order of the potentials.
1 code implementation • 21 Jun 2015 • Yao Li, Lingqiao Liu, Chunhua Shen, Anton Van Den Hengel
The purpose of mid-level visual element discovery is to find clusters of image patches that are both representative and discriminative.
no code implementations • 21 Jul 2015 • Xi Li, Chunhua Shen, Anthony Dick, Zhongfei Zhang, Yueting Zhuang
Object identification results for an entire video sequence are achieved by systematically combining the tracking information and visual recognition at each frame.
no code implementations • 4 Oct 2015 • Lingqiao Liu, Chunhua Shen, Anton Van Den Hengel
Most of these studies adopt activations from a single DCNN layer, usually the fully-connected layer, as the image representation.
no code implementations • 12 Oct 2015 • Qichang Hu, Sakrapee Paisitkriangkrai, Chunhua Shen, Anton Van Den Hengel, Fatih Porikli
The proposed framework consists of a dense feature extractor and detectors of three important classes.
no code implementations • 9 Nov 2015 • Peng Wang, Qi Wu, Chunhua Shen, Anton Van Den Hengel, Anthony Dick
We describe a method for visual question answering which is capable of reasoning about contents of an image on the basis of information extracted from a large-scale knowledge base.
no code implementations • CVPR 2016 • Qi Wu, Peng Wang, Chunhua Shen, Anthony Dick, Anton Van Den Hengel
Priming a recurrent neural network with this combined information, and the submitted question, leads to a very flexible visual question answering approach.
no code implementations • 27 Nov 2015 • Sakrapee Paisitkriangkrai, Lin Wu, Chunhua Shen, Anton Van Den Hengel
However, seeking an optimal combination of visual features which is generic yet adaptive to different benchmarks is a unsoved problem, and metric learning models easily get over-fitted due to the scarcity of training data in person re-identification.
no code implementations • ICCV 2015 • Lei Zhang, Wei Wei, Yanning Zhang, Fei Li, Chunhua Shen, Qinfeng Shi
To reconstruct hyperspectral image (HSI) accurately from a few noisy compressive measurements, we present a novel manifold-structured sparsity prior based hyperspectral compressive sensing (HCS) method in this study.
no code implementations • 26 Dec 2015 • Wei Liu, Yun Gu, Chunhua Shen, Xiaogang Chen, Qiang Wu, Jie Yang
Depth maps captured by modern depth cameras such as Kinect and Time-of-Flight (ToF) are usually contaminated by missing data, noises and suffer from being of low resolution.
1 code implementation • 16 Jan 2016 • Lingqiao Liu, Peng Wang, Chunhua Shen, Lei Wang, Anton Van Den Hengel, Chao Wang, Heng Tao Shen
To handle this limitation, in this paper we break the convention which assumes that a local feature is drawn from one of few Gaussian distributions.
1 code implementation • 21 Jan 2016 • Hui Li, Chunhua Shen
Inspired by the success of deep neural networks (DNNs) in various vision applications, here we leverage DNNs to learn high-level features in a cascade framework, which lead to improved performance on both detection and recognition.
1 code implementation • 27 Jan 2016 • Lin Wu, Chunhua Shen, Anton Van Den Hengel
In this paper, we propose a deep end-to-end neu- ral network to simultaneously learn high-level features and a corresponding similarity metric for person re-identification.
no code implementations • 28 Jan 2016 • Fayao Liu, Guosheng Lin, Chunhua Shen
We exemplify the usefulness of the proposed model on multi-class semantic labelling (discrete) and the robust depth estimation (continuous) problems.
no code implementations • 31 Jan 2016 • Peng Wang, Lingqiao Liu, Chunhua Shen, Heng Tao Shen
Most video based action recognition approaches create the video-level representation by temporally pooling the features extracted at each frame.
no code implementations • 14 Feb 2016 • Peng Wang, Lingqiao Liu, Chunhua Shen, Anton Van Den Hengel, Heng Tao Shen
To address this problem, we propose a novel approach by inspecting the distribution of the detection scores at multiple image regions based on the detector trained from the "regular object" and "other objects".
no code implementations • 22 Feb 2016 • Guosheng Lin, Fayao Liu, Chunhua Shen, Jianxin Wu, Heng Tao Shen
Our column generation based method can be further generalized from the triplet loss to a general structured learning based framework that allows one to directly optimize multivariate performance measures.
no code implementations • CVPR 2016 • Bohan Zhuang, Guosheng Lin, Chunhua Shen, Ian Reid
To solve the first stage, we design a large-scale high-order binary codes inference algorithm to reduce the high-order objective to a standard binary quadratic problem such that graph cuts can be used to efficiently infer the binary code which serve as the label of each training datum.
no code implementations • 9 Mar 2016 • Qi Wu, Chunhua Shen, Anton Van Den Hengel, Peng Wang, Anthony Dick
Much recent progress in Vision-to-Language problems has been achieved through a combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs).
no code implementations • 10 Mar 2016 • Guosheng Lin, Chunhua Shen, Anton Van Den Hengel, Ian Reid
We formulate deep structured models by combining CNNs and Conditional Random Fields (CRFs) for learning the patch-patch context between image regions.
no code implementations • 15 Mar 2016 • Qichang Hu, Peng Wang, Chunhua Shen, Anton Van Den Hengel, Fatih Porikli
In this work, we show that by re-using the convolutional feature maps (CFMs) of a deep convolutional neural network (DCNN) model as image features to train an ensemble of boosted decision models, we are able to achieve the best reported accuracy without using specially designed learning algorithms.
no code implementations • 15 Mar 2016 • Yao Li, Linqiao Liu, Chunhua Shen, Anton Van Den Hengel
More specifically, we observe that given a set of object proposals extracted from an image that contains the object of interest, an accurate strongly supervised object detector should give high scores to only a small minority of proposals, and low scores to most of them.
3 code implementations • NeurIPS 2016 • Xiao-Jiao Mao, Chunhua Shen, Yu-Bin Yang
We propose to symmetrically link convolutional and de-convolutional layers with skip-layer connections, with which the training converges much faster and attains a higher-quality local optimum.
Ranked #37 on Image Super-Resolution on BSD100 - 4x upscaling
no code implementations • CVPR 2016 • Ruizhi Qiao, Lingqiao Liu, Chunhua Shen, Anton Van Den Hengel
Classifying a visual concept merely from its associated online textual source, such as a Wikipedia article, is an attractive research topic in zero-shot learning because it alleviates the burden of manually collecting semantic attributes.
no code implementations • 15 Apr 2016 • Zifeng Wu, Chunhua Shen, Anton Van Den Hengel
(i) First, we evaluate different variations of a fully convolutional residual network so as to find the best configuration, including the number of layers, the resolution of feature maps, and the size of field-of-view.
no code implementations • 29 Apr 2016 • Biyun Sheng, Chunhua Shen, Guosheng Lin, Jun Li, Wankou Yang, Changyin Sun
Crowd counting is an important task in computer vision, which has many applications in video surveillance.
no code implementations • 8 May 2016 • Yuanzhouhan Cao, Zifeng Wu, Chunhua Shen
Then we train fully convolutional deep residual networks to predict the depth label of each pixel.
no code implementations • 23 May 2016 • Zifeng Wu, Chunhua Shen, Anton Van Den Hengel
(iii) As the performance of semantic category segmentation has a significant impact on the instance-level segmentation, which is the second step of our approach, we train fully convolutional residual networks to achieve the best semantic category segmentation accuracy.
Ranked #53 on Semantic Segmentation on PASCAL Context
no code implementations • CVPR 2016 • Peng Wang, Lingqiao Liu, Chunhua Shen, Zi Huang, Anton Van Den Hengel, Heng Tao Shen
The key observation motivating our approach is that "regular object" images, "unusual object" images and "other objects" images exhibit different region-level scores in terms of both the score values and the spatial distributions.
no code implementations • 6 Jun 2016 • Lin Wu, Chunhua Shen, Anton Van Den Hengel
Person re-identification is to seek a correct match for a person of interest across views among a large number of imposters.
no code implementations • 6 Jun 2016 • Lin Wu, Chunhua Shen, Anton Van Den Hengel
In this paper, we present an end-to-end approach to simultaneously learn spatio-temporal features and corresponding similarity metric for video-based person re-identification.
no code implementations • 17 Jun 2016 • Peng Wang, Qi Wu, Chunhua Shen, Anton Van Den Hengel, Anthony Dick
We evaluate several baseline models on the FVQA dataset, and describe a novel model which is capable of reasoning about an image on the basis of supporting facts.
Ranked #2 on Visual Question Answering (VQA) on F-VQA
no code implementations • 22 Jun 2016 • Jiewei Cao, Lingqiao Liu, Peng Wang, Zi Huang, Chunhua Shen, Heng Tao Shen
Instance retrieval requires one to search for images that contain a particular object within a large corpus.
17 code implementations • 29 Jun 2016 • Xiao-Jiao Mao, Chunhua Shen, Yu-Bin Yang
In this work, we propose a very deep fully convolutional auto-encoder network for image restoration, which is a encoding-decoding framework with symmetric convolutional-deconvolutional layers.
Ranked #2 on Grayscale Image Denoising on BSD200 sigma10
1 code implementation • 20 Jul 2016 • Qi Wu, Damien Teney, Peng Wang, Chunhua Shen, Anthony Dick, Anton Van Den Hengel
Visual Question Answering (VQA) is a challenging task that has received increasing attention from both the computer vision and the natural language processing communities.
no code implementations • 6 Oct 2016 • Yuanzhouhan Cao, Chunhua Shen, Heng Tao Shen
Augmenting RGB data with measured depth has been shown to improve the performance of a range of tasks in computer vision including object detection and semantic segmentation.
13 code implementations • CVPR 2017 • Guosheng Lin, Anton Milan, Chunhua Shen, Ian Reid
Recently, very deep convolutional neural networks (CNNs) have shown outstanding performance in object recognition and have also been the first choice for dense classification problems such as semantic segmentation.
Ranked #13 on Semantic Segmentation on Trans10K
1 code implementation • 28 Nov 2016 • Jianfeng Dong, Xiao-Jiao Mao, Chunhua Shen, Yu-Bin Yang
In this paper, we investigate convolutional denoising auto-encoders to show that unsupervised pre-training can still improve the performance of high-level image related tasks such as image classification and semantic segmentation.
no code implementations • CVPR 2017 • Yao Li, Guosheng Lin, Bohan Zhuang, Lingqiao Liu, Chunhua Shen, Anton Van Den Hengel
In this work, we propose to model the relational information between people as a sequence prediction task.
3 code implementations • 30 Nov 2016 • Zifeng Wu, Chunhua Shen, Anton Van Den Hengel
As a result, we are able to derive a new, shallower, architecture of residual networks which significantly outperforms much deeper models such as ResNet-200 on the ImageNet classification dataset.
Ranked #11 on Semantic Segmentation on PASCAL VOC 2012 test
no code implementations • CVPR 2017 • Bohan Zhuang, Lingqiao Liu, Yao Li, Chunhua Shen, Ian Reid
Large-scale datasets have driven the rapid development of deep neural networks for visual recognition.
no code implementations • 4 Dec 2016 • Jun-Jie Zhang, Qi Wu, Chunhua Shen, Jian Zhang, Jianfeng Lu
Recent state-of-the-art approaches to multi-label image classification exploit the label dependencies in an image, at global level, largely improving the labeling capacity.
no code implementations • CVPR 2017 • Dong Gong, Jie Yang, Lingqiao Liu, Yanning Zhang, Ian Reid, Chunhua Shen, Anton Van Den Hengel, Qinfeng Shi
The critical observation underpinning our approach is thus that learning the motion flow instead allows the model to focus on the cause of the blur, irrespective of the image content.
no code implementations • CVPR 2017 • Peng Wang, Qi Wu, Chunhua Shen, Anton Van Den Hengel
To train a method to perform even one of these operations accurately from {image, question, answer} tuples would be challenging, but to aim to achieve them all with a limited set of such training data seems ambitious at best.
no code implementations • 18 Jan 2017 • Zetao Chen, Adam Jacobson, Niko Sunderhauf, Ben Upcroft, Lingqiao Liu, Chunhua Shen, Ian Reid, Michael Milford
The success of deep learning techniques in the computer vision domain has triggered a range of initial investigations into their utility for visual place recognition, all using generic features from networks that were trained for other types of recognition tasks.
no code implementations • 25 Jan 2017 • Tong Shen, Guosheng Lin, Chunhua Shen, Ian Reid
Semantic image segmentation is a fundamental task in image understanding.
no code implementations • 18 Mar 2017 • Bohan Zhuang, Lingqiao Liu, Chunhua Shen, Ian Reid
Recognizing how objects interact with each other is a crucial task in visual recognition.
no code implementations • 26 Mar 2017 • Fayao Liu, Guosheng Lin, Ruizhi Qiao, Chunhua Shen
In this fashion, we easily achieve nonlinear learning of potential functions on both unary and pairwise terms in CRFs.
no code implementations • 28 Mar 2017 • Wei Liu, Xiaogang Chen, Chunhua Shen, Jingyi Yu, Qiang Wu, Jie Yang
In this paper, we propose a general framework for Robust Guided Image Filtering (RGIF), which contains a data term and a smoothness term, to solve the two issues mentioned above.
1 code implementation • 4 Apr 2017 • Qichang Hu, Huibing Wang, Teng Li, Chunhua Shen
By applying our method to several fine-grained car recognition data sets, we demonstrate that the proposed method can achieve better performance than recent approaches in the literature.
Ranked #1 on Fine-Grained Image Classification on CarFlag-563
2 code implementations • ICCV 2017 • Yu Chen, Chunhua Shen, Xiu-Shen Wei, Lingqiao Liu, Jian Yang
In contrast, human vision is able to predict poses by exploiting geometric constraints of joint inter-connectivity.
Ranked #15 on Pose Estimation on MPII Human Pose
no code implementations • 8 May 2017 • Xiu-Shen Wei, Chen-Lin Zhang, Yao Li, Chen-Wei Xie, Jianxin Wu, Chunhua Shen, Zhi-Hua Zhou
Reusable model design becomes desirable with the rapid expansion of machine learning applications.
no code implementations • 25 May 2017 • Tong Shen, Guosheng Lin, Lingqiao Liu, Chunhua Shen, Ian Reid
Training a Fully Convolutional Network (FCN) for semantic segmentation requires a large number of masks with pixel level labelling, which involves a large amount of human labour and time for annotation.
no code implementations • 28 May 2017 • Bohan Zhuang, Qi Wu, Chunhua Shen, Ian Reid, Anton Van Den Hengel
In addressing this problem we first construct a large-scale human-centric visual relationship detection dataset (HCVRD), which provides many more types of relationship annotation (nearly 10K categories) than the previous released datasets.
Human-Object Interaction Detection Relationship Detection +1
no code implementations • CVPR 2017 • Peng Wang, Lingqiao Liu, Chunhua Shen, Zi Huang, Anton Van Den Hengel, Heng Tao Shen
One-shot learning is a challenging problem where the aim is to recognize a class identified by a single training image.
no code implementations • 7 Jul 2017 • Hao Lu, Zhiguo Cao, Yang Xiao, Bohan Zhuang, Chunhua Shen
To our knowledge, this is the first time that a plant-related counting problem is considered using computer vision technologies under unconstrained field-based environment.
no code implementations • 11 Jul 2017 • Xinlong Wang, Zhipeng Man, Mingyu You, Chunhua Shen
Our experimental results on a few data sets demonstrate the effectiveness of using GAN images: an improvement of 7. 5% over a strong baseline with moderate-sized real data being available.
no code implementations • ICCV 2017 • Hui Li, Peng Wang, Chunhua Shen
In this work, we jointly address the problem of text detection and recognition in natural scene images based on convolutional recurrent neural networks.
no code implementations • CVPR 2018 • Chao Ma, Chunhua Shen, Anthony Dick, Qi Wu, Peng Wang, Anton Van Den Hengel, Ian Reid
In this paper, we exploit a memory-augmented neural network to predict accurate answers to visual questions, even when those answers occur rarely in the training set.
no code implementations • 18 Jul 2017 • Ruizhi Qiao, Lingqiao Liu, Chunhua Shen, Anton Van Den Hengel
To overcome this visual-semantic discrepancy, this work proposes an objective function to re-align the distributed word embeddings with visual information by learning a neural network to map it into a new representation called visually aligned word embedding (VAWE).
1 code implementation • ICCV 2017 • Hao Lu, Lei Zhang, Zhiguo Cao, Wei Wei, Ke Xian, Chunhua Shen, Anton Van Den Hengel
Domain adaption (DA) allows machine learning methods trained on data sampled from one distribution to be applied to data sampled from another.
no code implementations • 20 Jul 2017 • Xiu-Shen Wei, Chen-Lin Zhang, Jianxin Wu, Chunhua Shen, Zhi-Hua Zhou
Reusable model design becomes desirable with the rapid expansion of computer vision and machine learning applications.
Ranked #11 on Single-object discovery on COCO_20k
no code implementations • 25 Jul 2017 • Ruoxi Deng, Tianqi Zhao, Chunhua Shen, Shengjun Liu
We study the problem of estimating the relative depth order of point pairs in a monocular image.
no code implementations • 3 Aug 2017 • Lei Zhang, Wei Wei, Qinfeng Shi, Chunhua Shen, Anton Van Den Hengel, Yanning Zhang
The prior for the non-low-rank structure is established based on a mixture of Gaussians which is shown to be flexible enough, and powerful enough, to inform the completion process for a variety of real tensor data.
no code implementations • 26 Sep 2017 • Hui Li, Peng Wang, Chunhua Shen
In contrast to existing approaches which take license plate detection and recognition as two separate tasks and settle them step by step, our method jointly solves these two tasks by a single network.
1 code implementation • ICCV 2017 • Bohan Zhuang, Lingqiao Liu, Chunhua Shen, Ian Reid
The proposed method still builds one classifier for one interaction (as per type (ii) above), but the classifier built is adaptive to context via weights which are context dependent.
2 code implementations • CVPR 2018 • Bohan Zhuang, Chunhua Shen, Mingkui Tan, Lingqiao Liu, Ian Reid
This paper tackles the problem of training a deep convolutional neural network with both low-precision weights and low-bitwidth activations.
no code implementations • 1 Nov 2017 • Yu Chen, Chunhua Shen, Hao Chen, Xiu-Shen Wei, Lingqiao Liu, Jian Yang
In contrast, human vision is able to predict poses by exploiting geometric constraints of landmark point inter-connectivity.
no code implementations • CVPR 2018 • Bohan Zhuang, Qi Wu, Chunhua Shen, Ian Reid, Anton Van Den Hengel
To this end we propose a unified framework, the ParalleL AttentioN (PLAN) network, to discover the object in an image that is being referred to in variable length natural expression descriptions, from short phrases query to long multi-round dialogs.
no code implementations • 19 Nov 2017 • Jun-Jie Zhang, Qi Wu, Jian Zhang, Chunhua Shen, Jianfeng Lu
These comments can be a description of the image, or some objects, attributes, scenes in it, which are normally used as the user-provided tags.
no code implementations • 21 Nov 2017 • Jun-Jie Zhang, Qi Wu, Chunhua Shen, Jian Zhang, Jianfeng Lu, Anton Van Den Hengel
Despite significant progress in a variety of vision-and-language problems, developing a method capable of asking intelligent, goal-oriented questions about images is proven to be an inscrutable challenge.
2 code implementations • CVPR 2018 • Xinlong Wang, Tete Xiao, Yuning Jiang, Shuai Shao, Jian Sun, Chunhua Shen
In this paper, we first explore how a state-of-the-art pedestrian detector is harmed by crowd occlusion via experimentation, providing insights into the crowd occlusion problem.
Ranked #9 on Pedestrian Detection on Caltech (using extra training data)
no code implementations • CVPR 2018 • Qi Wu, Peng Wang, Chunhua Shen, Ian Reid, Anton Van Den Hengel
The Visual Dialogue task requires an agent to engage in a conversation about an image with a human.
Ranked #4 on Visual Dialog on VisDial v0.9 val
4 code implementations • CVPR 2018 • Yu Chen, Ying Tai, Xiaoming Liu, Chunhua Shen, Jian Yang
We present a novel deep end-to-end trainable Face Super-Resolution Network (FSRNet), which makes full use of the geometry prior, i. e., facial landmark heatmaps and parsing maps, to super-resolve very low-resolution (LR) face images without well-aligned requirement.
no code implementations • 1 Dec 2017 • Zifeng Wu, Chunhua Shen, Anton Van Den Hengel
We propose an approach to semantic (image) segmentation that reduces the computational costs by a factor of 25 with limited impact on the quality of results.
no code implementations • 25 Dec 2017 • Guanjun Guo, Hanzi Wang, Chunhua Shen, Yan Yan, Hong-Yuan Mark Liao
The deep CNN model is then designed to extract features from several image cropping datasets, upon which the cropping bounding boxes are predicted by the proposed CCR method.
no code implementations • 19 Feb 2018 • Pingping Zhang, Wei Liu, Huchuan Lu, Chunhua Shen
Inspired by the intrinsic reflection of natural images, in this paper we propose a novel feature learning framework for large-scale salient object detection.
no code implementations • 20 Feb 2018 • Pingping Zhang, Luyao Wang, Dong Wang, Huchuan Lu, Chunhua Shen
This paper proposes an Agile Aggregating Multi-Level feaTure framework (Agile Amulet) for salient object detection.
no code implementations • 22 Feb 2018 • Pingping Zhang, Wei Liu, Dong Wang, Yinjie Lei, Hongyu Wang, Chunhua Shen, Huchuan Lu
Extensive experiments demonstrate that the proposed algorithm achieves competitive performance in both saliency detection and visual tracking, especially outperforming other related trackers on the non-rigid object tracking datasets.
no code implementations • 7 Mar 2018 • Tianyi Zhang, Guosheng Lin, Jianfei Cai, Tong Shen, Chunhua Shen, Alex C. Kot
In our work, we focus on the weakly supervised semantic segmentation with image label annotations.
2 code implementations • CVPR 2018 • Tong He, Zhi Tian, Weilin Huang, Chunhua Shen, Yu Qiao, Changming Sun
This allows the two tasks to work collaboratively by shar- ing convolutional features, which is critical to identify challenging text instances.
1 code implementation • 10 Apr 2018 • Dong Gong, Zhen Zhang, Qinfeng Shi, Anton Van Den Hengel, Chunhua Shen, Yanning Zhang
Extensive experiments on synthetic benchmarks and challenging real-world images demonstrate that the proposed deep optimization method is effective and robust to produce favorable results as well as practical for real-world image deblurring applications.
no code implementations • CVPR 2018 • Yibing Song, Chao Ma, Xiaohe Wu, Lijun Gong, Linchao Bao, WangMeng Zuo, Chunhua Shen, Rynson Lau, Ming-Hsuan Yang
To augment positive samples, we use a generative network to randomly generate masks, which are applied to adaptively dropout input features to capture a variety of appearance changes.
no code implementations • 14 Apr 2018 • Pingping Zhang, Huchuan Lu, Chunhua Shen
Salient object detection (SOD), which aims to find the most important region of interest and segment the relevant object/item in that area, is an important yet challenging vision task.
no code implementations • 3 May 2018 • Ni Zhuang, Yan Yan, Si Chen, Hanzi Wang, Chunhua Shen
To address the above problem, we propose a novel deep transfer neural network method based on multi-label learning for facial attribute classification, termed FMTNet, which consists of three sub-networks: the Face detection Network (FNet), the Multi-label learning Network (MNet) and the Transfer learning Network (TNet).
1 code implementation • 11 May 2018 • Xiu-Shen Wei, Peng Wang, Lingqiao Liu, Chunhua Shen, Jianxin Wu
To solve this problem, we propose an end-to-end trainable deep network which is inspired by the state-of-the-art fine-grained recognition model and is tailored for the FSFG task.
no code implementations • CVPR 2018 • Ke Xian, Chunhua Shen, Zhiguo Cao, Hao Lu, Yang Xiao, Ruibo Li, Zhenbo Luo
In this paper we study the problem of monocular relative depth perception in the wild.
1 code implementation • CVPR 2018 • Tong Shen, Guosheng Lin, Chunhua Shen, Ian Reid
In this work, we focus on weak supervision, developing a method for training a high-quality pixel-level classifier for semantic segmentation, using only image-level class labels as the provided ground-truth.
no code implementations • 2 Jun 2018 • Yuanzhouhan Cao, Tianqi Zhao, Ke Xian, Chunhua Shen, Zhiguo Cao, Shugong Xu
In this paper, we propose to improve the performance of metric depth estimation with relative depths collected from stereo movie videos using existing stereo matching algorithm.
no code implementations • 5 Jun 2018 • Lei Zhang, Peng Wang, Chunhua Shen, Lingqiao Liu, Wei Wei, Yanning Zhang, Anton Van Den Hengel
In this study, we revisit this problem from an orthog- onal view, and propose a novel learning strategy to maxi- mize the pixel-wise fitting capacity of a given lightweight network architecture.
no code implementations • ICML 2018 • Jiezhang Cao, Yong Guo, Qingyao Wu, Chunhua Shen, Junzhou Huang, Mingkui Tan
Generative adversarial networks (GANs) aim to generate realistic data from some prior distribution (e. g., Gaussian noises).
1 code implementation • 11 Jul 2018 • Ruibo Li, Ke Xian, Chunhua Shen, Zhiguo Cao, Hao Lu, Lingxiao Hang
However, robust depth prediction suffers from two challenging problems: a) How to extract more discriminative features for different scenes (compared to a single scene)?
1 code implementation • ECCV 2018 • Ruoxi Deng, Chunhua Shen, Shengjun Liu, Huibing Wang, Xinru Liu
Recent methods for boundary or edge detection built on Deep Convolutional Neural Networks (CNNs) typically suffer from the issue of predicted edges being thick and need post-processing to obtain crisp boundaries.
no code implementations • 4 Aug 2018 • Pingping Zhang, Huchuan Lu, Chunhua Shen
In addition, our work has text overlap with arXiv:1804. 06242, arXiv:1705. 00938 by other authors.
no code implementations • 8 Aug 2018 • Bohan Zhuang, Chunhua Shen, Ian Reid
In this paper, we propose to train a network with binary weights and low-bitwidth activations, designed especially for mobile devices with limited power consumption.
no code implementations • 30 Aug 2018 • Lei Zhang, Peng Wang, Lingqiao Liu, Chunhua Shen, Wei Wei, Yannning Zhang, Anton Van Den Hengel
Towards this goal, we present a simple but effective two-branch network to simultaneously map semantic descriptions and visual samples into a joint space, on which visual embeddings are forced to regress to their class-level semantic embeddings and the embeddings crossing classes are required to be distinguishable by a trainable classifier.
no code implementations • ECCV 2018 • Jun-Jie Zhang, Qi Wu, Chunhua Shen, Jian Zhang, Jianfeng Lu, Anton Van Den Hengel
Despite significant progress in a variety of vision-and-language problems, developing a method capable of asking intelligent, goal-oriented questions about images is proven to be an inscrutable challenge.
4 code implementations • 13 Sep 2018 • Vladimir Nekrasov, Thanuja Dharmasiri, Andrew Spek, Tom Drummond, Chunhua Shen, Ian Reid
Deployment of deep learning models in robotics as sensory information extractors can be a daunting task to handle, even using generic GPU cards.
Ranked #6 on Real-Time Semantic Segmentation on NYU Depth v2
no code implementations • 27 Sep 2018 • Vladimir Nekrasov, Chunhua Shen, Ian Reid
Over the past years, computer vision community has contributed to enormous progress in semantic image segmentation, a per-pixel classification task, crucial for dense scene understanding and rapidly becoming vital in lots of real-world applications, including driverless cars and medical imaging.
no code implementations • 30 Sep 2018 • Zichuan Liu, Guosheng Lin, Wang Ling Goh, Fayao Liu, Chunhua Shen, Xiaokang Yang
In this work, we propose a novel hybrid method for scene text detection namely Correlation Propagation Network (CPN).
2 code implementations • 8 Oct 2018 • Vladimir Nekrasov, Chunhua Shen, Ian Reid
We consider an important task of effective and efficient semantic image segmentation.
Ranked #2 on Real-Time Semantic Segmentation on NYU Depth v2
4 code implementations • CVPR 2019 • Vladimir Nekrasov, Hao Chen, Chunhua Shen, Ian Reid
While most results in this domain have been achieved on image classification and language modelling problems, here we concentrate on dense per-pixel tasks, in particular, semantic image segmentation using fully convolutional networks.
Ranked #13 on Semantic Segmentation on PASCAL VOC 2012 val
7 code implementations • 2 Nov 2018 • Hui Li, Peng Wang, Chunhua Shen, Guyu Zhang
Recognizing irregular text in natural scene images is challenging due to the large variance in text appearance, such as curvature, orientation and distortion.
Ranked #26 on Scene Text Recognition on ICDAR2015
no code implementations • CVPR 2019 • Bohan Zhuang, Chunhua Shen, Mingkui Tan, Lingqiao Liu, Ian Reid
In this paper, we propose to train convolutional neural networks (CNNs) with both binarized weights and activations, leading to quantized models specifically} for mobile devices with limited power capacity and computation resources.
no code implementations • 24 Nov 2018 • Haokui Zhang, Ying Li, Peng Wang, Yu Liu, Chunhua Shen
Different from RGB videos, depth data in RGB-D videos provide key complementary information for tristimulus visual data which potentially could achieve accuracy improvement for action recognition.
no code implementations • CVPR 2019 • Hui Li, Peng Wang, Chunhua Shen, Anton Van Den Hengel
In contrast to struggling on multimodal feature fusion, in this paper, we propose to unify all the input information by natural language so as to convert VQA into a machine reading comprehension problem.
no code implementations • 11 Dec 2018 • Xiu-Shen Wei, Chen-Lin Zhang, Lingqiao Liu, Chunhua Shen, Jianxin Wu
Inspired by the coarse-to-fine hierarchical process, we propose an end-to-end RNN-based Hierarchical Attention (RNN-HA) classification model for vehicle re-identification.
no code implementations • CVPR 2019 • Peng Wang, Qi Wu, Jiewei Cao, Chunhua Shen, Lianli Gao, Anton Van Den Hengel
Being composed of node attention component and edge attention component, the proposed graph attention mechanism explicitly represents inter-object relationships, and properties with a flexibility and power impossible with competing approaches.
no code implementations • 21 Jan 2019 • Pingping Zhang, Wei Liu, Huchuan Lu, Chunhua Shen
Inspired by the intrinsic reflection of natural images, in this paper we propose a novel feature learning framework for large-scale salient object detection.
3 code implementations • CVPR 2019 • Xinlong Wang, Shu Liu, Xiaoyong Shen, Chunhua Shen, Jiaya Jia
A 3D point cloud describes the real scene precisely and intuitively. To date how to segment diversified elements in such an informative 3D scene is rarely discussed.
Ranked #15 on 3D Instance Segmentation on S3DIS (mRec metric)
no code implementations • CVPR 2019 • Zhi Tian, Tong He, Chunhua Shen, Youliang Yan
In this work, we propose a data-dependent upsampling (DUpsampling) to replace bilinear, which takes advantages of the redundancy in the label space of semantic segmentation and is able to recover the pixel-wise prediction from low-resolution outputs of CNNs.
Ranked #46 on Semantic Segmentation on PASCAL Context
1 code implementation • CVPR 2019 • Chi Zhang, Guosheng Lin, Fayao Liu, Rui Yao, Chunhua Shen
Recent progress in semantic segmentation is driven by deep Convolutional Neural Networks and large-scale labeled image datasets.
Ranked #86 on Few-Shot Semantic Segmentation on PASCAL-5i (5-Shot)
1 code implementation • 8 Mar 2019 • Yutong Xie, Jianpeng Zhang, Yong Xia, Chunhua Shen
Our results suggest that it is possible to boost the performance of skin lesion segmentation and classification simultaneously via training a unified model to perform both tasks in a mutual bootstrapping way.
1 code implementation • CVPR 2019 • Yifan Liu, Changyong Shun, Jingdong Wang, Chunhua Shen
Here we propose to distill structured knowledge from large networks to compact networks, taking into account the fact that dense prediction is a structured prediction problem.
1 code implementation • CVPR 2019 • Tong He, Chunhua Shen, Zhi Tian, Dong Gong, Changming Sun, Youliang Yan
To tackle this dilemma, we propose a knowledge distillation method tailored for semantic segmentation to improve the performance of the compact FCNs with large overall stride.
no code implementations • CVPR 2020 • Bohan Zhuang, Lingqiao Liu, Mingkui Tan, Chunhua Shen, Ian Reid
In this paper, we seek to tackle a challenge in training low-precision networks: the notorious difficulty in propagating gradient through a low-precision network due to the non-differentiable quantization function.
85 code implementations • ICCV 2019 • Zhi Tian, Chunhua Shen, Hao Chen, Tong He
By eliminating the predefined set of anchor boxes, FCOS completely avoids the complicated computation related to anchor boxes such as calculating overlapping during training.
Ranked #4 on Pedestrian Detection on TJU-Ped-campus
no code implementations • 4 Apr 2019 • Vladimir Nekrasov, Hao Chen, Chunhua Shen, Ian Reid
In semantic video segmentation the goal is to acquire consistent dense semantic labelling across image frames.
1 code implementation • 4 Apr 2019 • Vladimir Nekrasov, Chunhua Shen, Ian Reid
Automatic search of neural architectures for various vision and natural language tasks is becoming a prominent tool as it allows to discover high-performing structures on any dataset of interest.
Ranked #13 on Semantic Segmentation on CamVid
5 code implementations • CVPR 2019 • Qingsen Yan, Dong Gong, Qinfeng Shi, Anton Van Den Hengel, Chunhua Shen, Ian Reid, Yanning Zhang
Ghosting artifacts caused by moving objects or misalignments is a key challenge in high dynamic range (HDR) imaging for dynamic scenes.
1 code implementation • CVPR 2020 • Yuankai Qi, Qi Wu, Peter Anderson, Xin Wang, William Yang Wang, Chunhua Shen, Anton Van Den Hengel
One of the long-term challenges of robotics is to enable robots to interact with humans in the visual world via natural language, as humans are visual animals that communicate through language.
3 code implementations • CVPR 2020 • Ning Wang, Yang Gao, Hao Chen, Peng Wang, Zhi Tian, Chunhua Shen, Yanning Zhang
The success of deep neural networks relies on significant architecture engineering.
Ranked #124 on Object Detection on COCO test-dev
no code implementations • 14 Jun 2019 • Peng Wang, Hui Li, Chunhua Shen
Text spotting in natural scene images is of great importance for many image understanding tasks.
3 code implementations • ICCV 2019 • Wei Yin, Yifan Liu, Chunhua Shen, Youliang Yan
Monocular depth prediction plays a crucial role in understanding 3D scene geometry.
Ranked #10 on Depth Estimation on NYU-Depth V2
1 code implementation • 29 Jul 2019 • Tong Shen, Dong Gong, Wei zhang, Chunhua Shen, Tao Mei
To tackle the unsupervised domain adaptation problem, we explore the possibilities to generate high-quality labels as proxy labels to supervise the training on target data.
no code implementations • 29 Jul 2019 • Damien Teney, Peng Wang, Jiewei Cao, Lingqiao Liu, Chunhua Shen, Anton Van Den Hengel
One of the primary challenges faced by deep learning is the degree to which current methods exploit superficial statistics and dataset bias, rather than learning to generalise over the specific representations they have experienced.
1 code implementation • ICCV 2019 • Xin-Yu Zhang, Jiewei Cao, Chunhua Shen, Mingyu You
In this work, we develop a self-training method with progressive augmentation framework (PAST) to promote the model performance progressively on the target dataset.
Ranked #11 on Unsupervised Domain Adaptation on Market to Duke
1 code implementation • ICCV 2019 • Hao Lu, Yutong Dai, Chunhua Shen, Songcen Xu
We show that existing upsampling operators can be unified with the notion of the index function.
no code implementations • 10 Aug 2019 • Bohan Zhuang, Jing Liu, Mingkui Tan, Lingqiao Liu, Ian Reid, Chunhua Shen
Furthermore, we propose a second progressive quantization scheme which gradually decreases the bit-width from high-precision to low-precision during training.
2 code implementations • ICCV 2019 • Haokui Zhang, Chunhua Shen, Ying Li, Yuanzhouhan Cao, Yu Liu, Youliang Yan
The temporal consistency loss is combined with the spatial loss to update the model in an end-to-end fashion.
Ranked #5 on Monocular Depth Estimation on Mid-Air Dataset
no code implementations • 11 Aug 2019 • Yang Zhao, Yifan Liu, Chunhua Shen, Yongsheng Gao, Shengwu Xiong
To this end, we propose an effective lightweight model, namely Mobile Face Alignment Network (MobileFAN), using a simple backbone MobileNetV2 as the encoder and three deconvolutional layers as the decoder.
6 code implementations • 11 Aug 2019 • Hao Lu, Yutong Dai, Chunhua Shen, Songcen Xu
By viewing the indices as a function of the feature map, we introduce the concept of "learning to index", and present a novel index-guided encoder-decoder framework where indices are self-learned adaptively from data and are used to guide the downsampling and upsampling stages, without extra training supervision.
Ranked #2 on Grayscale Image Denoising on Set12 sigma30
5 code implementations • ICCV 2019 • Haipeng Xiong, Hao Lu, Chengxin Liu, Liang Liu, Zhiguo Cao, Chunhua Shen
A dense region can always be divided until sub-region counts are within the previously observed closed set.
Ranked #3 on Crowd Counting on TRANCOS
6 code implementations • ICCV 2019 • Wenhai Wang, Enze Xie, Xiaoge Song, Yuhang Zang, Wenjia Wang, Tong Lu, Gang Yu, Chunhua Shen
Recently, some methods have been proposed to tackle arbitrary-shaped text detection, but they rarely take the speed of the entire pipeline into consideration, which may fall short in practical applications. In this paper, we propose an efficient and accurate arbitrary-shaped text detector, termed Pixel Aggregation Network (PAN), which is equipped with a low computational-cost segmentation head and a learnable post-processing.
Ranked #8 on Scene Text Detection on SCUT-CTW1500
2 code implementations • NeurIPS 2019 • Jia-Wang Bian, Zhichao Li, Naiyan Wang, Huangying Zhan, Chunhua Shen, Ming-Ming Cheng, Ian Reid
To the best of our knowledge, this is the first work to show that deep networks trained using unlabelled monocular videos can predict globally scale-consistent camera trajectories over a long video sequence.
Ranked #60 on Monocular Depth Estimation on KITTI Eigen split
no code implementations • 5 Sep 2019 • Yifan Liu, Bohan Zhuang, Chunhua Shen, Hao Chen, Wei Yin
The most current methods can be categorized as either: (i) hard parameter sharing where a subset of the parameters is shared among tasks while other parameters are task-specific; or (ii) soft parameter sharing where all parameters are task-specific but they are jointly regularized.
1 code implementation • 13 Sep 2019 • Xin-Yu Zhang, Rufeng Zhang, Jiewei Cao, Dong Gong, Mingyu You, Chunhua Shen
Finally, we aggregate the global appearance and part features to improve the feature performance further.
1 code implementation • 16 Sep 2019 • Wenjia Wang, Enze Xie, Peize Sun, Wenhai Wang, Lixun Tian, Chunhua Shen, Ping Luo
Nonetheless, most of the previous methods may not work well in recognizing text with low resolution which is often seen in natural scene images.
1 code implementation • 17 Sep 2019 • Xinlong Wang, Wei Yin, Tao Kong, Yuning Jiang, Lei LI, Chunhua Shen
In this paper, we first analyse the data distributions and interaction of foreground and background, then propose the foreground-background separated monocular depth estimation (ForeSeE) method, to estimate the foreground depth and background depth using separate optimization objectives and depth decoders.
1 code implementation • CVPR 2020 • Haokui Zhang, Ying Li, Hao Chen, Chunhua Shen
We also present analysis on the architectures found by NAS.
no code implementations • 22 Sep 2019 • Bohan Zhuang, Chunhua Shen, Mingkui Tan, Peng Chen, Lingqiao Liu, Ian Reid
Experiments on both classification, semantic segmentation and object detection tasks demonstrate the superior performance of the proposed methods over various quantized networks in the literature.