Search Results for author: Anton Van Den Hengel

Found 173 papers, 42 papers with code

CAPE: CAM as a Probabilistic Ensemble for Enhanced DNN Interpretation

1 code implementation CVPR 2024 Townim Faisal Chowdhury, Kewen Liao, Vu Minh Hieu Phan, Minh-Son To, Yutong Xie, Kevin Hung, David Ross, Anton Van Den Hengel, Johan W. Verjans, Zhibin Liao

Deep Neural Networks (DNNs) are widely used for visual classification tasks, but their complex computation process and black-box nature hinder decision transparency and interpretability.

Decision Making

Identifiable Latent Neural Causal Models

no code implementations23 Mar 2024 Yuhang Liu, Zhen Zhang, Dong Gong, Mingming Gong, Biwei Huang, Anton Van Den Hengel, Kun Zhang, Javen Qinfeng Shi

This work establishes a {sufficient} and {necessary} condition characterizing the types of distribution shifts for identifiability in the context of latent additive noise models.

Representation Learning

Premonition: Using Generative Models to Preempt Future Data Changes in Continual Learning

1 code implementation12 Mar 2024 Mark D. McDonnell, Dong Gong, Ehsan Abbasnejad, Anton Van Den Hengel

We show here that the combination of a large language model and an image generation model can similarly provide useful premonitions as to how a continual learning challenge might develop over time.

Continual Learning Fine-Grained Image Classification +3

StyleDubber: Towards Multi-Scale Style Learning for Movie Dubbing

no code implementations20 Feb 2024 Gaoxiang Cong, Yuankai Qi, Liang Li, Amin Beheshti, Zhedong Zhang, Anton Van Den Hengel, Ming-Hsuan Yang, Chenggang Yan, Qingming Huang

It contains three main components: (1) A multimodal style adaptor operating at the phoneme level to learn pronunciation style from the reference audio, and generate intermediate representations informed by the facial emotion presented in the video; (2) An utterance-level style learning module, which guides both the mel-spectrogram decoding and the refining processes from the intermediate embeddings to improve the overall style expression; And (3) a phoneme-guided lip aligner to maintain lip sync.

Voice Cloning

Revealing Multimodal Contrastive Representation Learning through Latent Partial Causal Models

no code implementations9 Feb 2024 Yuhang Liu, Zhen Zhang, Dong Gong, Biwei Huang, Mingming Gong, Anton Van Den Hengel, Kun Zhang, Javen Qinfeng Shi

Multimodal contrastive representation learning methods have proven successful across a range of domains, partly due to their ability to generate meaningful shared representations of complex phenomena.

Representation Learning

Source-Free Unsupervised Domain Adaptation with Hypothesis Consolidation of Prediction Rationale

1 code implementation2 Feb 2024 Yangyang Shu, Xiaofeng Cao, Qi Chen, BoWen Zhang, Ziqin Zhou, Anton Van Den Hengel, Lingqiao Liu

Source-Free Unsupervised Domain Adaptation (SFUDA) is a challenging task where a model needs to be adapted to a new domain without access to target domain labels or source domain data.

Unsupervised Domain Adaptation

Weakly Supervised Video Individual Counting

no code implementations CVPR 2024 Xinyan Liu, Guorong Li, Yuankai Qi, Ziheng Yan, Zhenjun Han, Anton Van Den Hengel, Ming-Hsuan Yang, Qingming Huang

To provide a more realistic reflection of the underlying practical challenge we introduce a weakly supervised VIC task wherein trajectory labels are not provided.

Contrastive Learning Video Individual Counting

Weakly Supervised Video Individual CountingWeakly Supervised Video Individual Counting

1 code implementation10 Dec 2023 Xinyan Liu, Guorong Li, Yuankai Qi, Ziheng Yan, Zhenjun Han, Anton Van Den Hengel, Ming-Hsuan Yang, Qingming Huang

% To provide a more realistic reflection of the underlying practical challenge, we introduce a weakly supervised VIC task, wherein trajectory labels are not provided.

Contrastive Learning Video Individual Counting

Zero-shot Retrieval: Augmenting Pre-trained Models with Search Engines

no code implementations29 Nov 2023 Hamed Damirchi, Cristian Rodríguez-Opazo, Ehsan Abbasnejad, Damien Teney, Javen Qinfeng Shi, Stephen Gould, Anton Van Den Hengel

Large pre-trained models can dramatically reduce the amount of task-specific data required to solve a problem, but they often fail to capture domain-specific nuances out of the box.

Retrieval

Identifiable Latent Polynomial Causal Models Through the Lens of Change

no code implementations24 Oct 2023 Yuhang Liu, Zhen Zhang, Dong Gong, Mingming Gong, Biwei Huang, Anton Van Den Hengel, Kun Zhang, Javen Qinfeng Shi

However, this progress rests on the assumption that the causal relationships among latent causal variables adhere strictly to linear Gaussian models.

Representation Learning

Domain Generalization via Rationale Invariance

1 code implementation ICCV 2023 Liang Chen, Yong Zhang, Yibing Song, Anton Van Den Hengel, Lingqiao Liu

Specifically, we propose treating the element-wise contributions to the final results as the rationale for making a decision and representing the rationale for each sample as a matrix.

Decision Making Domain Generalization

Provably Efficient Bayesian Optimization with Unknown Gaussian Process Hyperparameter Estimation

no code implementations12 Jun 2023 Huong Ha, Vu Nguyen, Hung Tran-The, Hongyu Zhang, Xiuzhen Zhang, Anton Van Den Hengel

To address this issue, we propose a new BO method that can sub-linearly converge to the objective function's global optimum even when the true GP hyperparameters are unknown in advance and need to be estimated from the observed data.

Bayesian Optimization

Knowledge Combination to Learn Rotated Detection Without Rotated Annotation

1 code implementation CVPR 2023 Tianyu Zhu, Bryce Ferenczi, Pulak Purkait, Tom Drummond, Hamid Rezatofighi, Anton Van Den Hengel

Annotating rotated bounding boxes is such a laborious process that they are not provided in many detection datasets where axis-aligned annotations are used instead.

Adaptive Cross Batch Normalization for Metric Learning

no code implementations30 Mar 2023 Thalaiyasingam Ajanthan, Matt Ma, Anton Van Den Hengel, Stephen Gould

In particular, it is necessary to circumvent the representational drift between the accumulated embeddings and the feature embeddings at the current training iteration as the learnable parameters are being updated.

Image Retrieval Metric Learning +1

Learning Common Rationale to Improve Self-Supervised Representation for Fine-Grained Visual Recognition Problems

1 code implementation CVPR 2023 Yangyang Shu, Anton Van Den Hengel, Lingqiao Liu

Specifically, we fit the GradCAM with a branch with limited fitting capacity, which allows the branch to capture the common rationales and discard the less common discriminative patterns.

Fine-Grained Visual Recognition Self-Supervised Learning

BLiRF: Bandlimited Radiance Fields for Dynamic Scene Modeling

no code implementations27 Feb 2023 Sameera Ramasinghe, Violetta Shevchenko, Gil Avraham, Anton Van Den Hengel

Reasoning the 3D structure of a non-rigid dynamic scene from a single moving camera is an under-constrained problem.

Novel View Synthesis

Program Generation from Diverse Video Demonstrations

no code implementations1 Feb 2023 Anthony Manchin, Jamie Sherrah, Qi Wu, Anton Van Den Hengel

The ability to use inductive reasoning to extract general rules from multiple observations is a vital indicator of intelligence.

Understanding and Improving the Role of Projection Head in Self-Supervised Learning

no code implementations22 Dec 2022 Kartik Gupta, Thalaiyasingam Ajanthan, Anton Van Den Hengel, Stephen Gould

Most current contrastive learning approaches append a parametrized projection head to the end of some backbone network to optimize the InfoNCE objective and then discard the learned projection head after training.

Contrastive Learning Image Classification +1

Identifying Weight-Variant Latent Causal Models

no code implementations30 Aug 2022 Yuhang Liu, Zhen Zhang, Dong Gong, Mingming Gong, Biwei Huang, Anton Van Den Hengel, Kun Zhang, Javen Qinfeng Shi

The task of causal representation learning aims to uncover latent higher-level causal representations that affect lower-level observations.

Representation Learning

Identifiable Latent Causal Content for Domain Adaptation under Latent Covariate Shift

no code implementations30 Aug 2022 Yuhang Liu, Zhen Zhang, Dong Gong, Mingming Gong, Biwei Huang, Anton Van Den Hengel, Kun Zhang, Javen Qinfeng Shi

Within this new paradigm, we present an intricate causal generative model by introducing latent noises across domains, along with a latent content variable and a latent style variable to achieve more nuanced rendering of observational data.

Domain Adaptation

ClusTR: Exploring Efficient Self-attention via Clustering for Vision Transformers

no code implementations28 Aug 2022 Yutong Xie, Jianpeng Zhang, Yong Xia, Anton Van Den Hengel, Qi Wu

Besides, we further extend the clustering-guided attention from single-scale to multi-scale, which is conducive to dense prediction tasks.

Clustering Language Modelling

EBMs vs. CL: Exploring Self-Supervised Visual Pretraining for Visual Question Answering

no code implementations29 Jun 2022 Violetta Shevchenko, Ehsan Abbasnejad, Anthony Dick, Anton Van Den Hengel, Damien Teney

In a simple setting similar to CLEVR, we find that CL representations also improve systematic generalization, and even match the performance of representations from a larger, supervised, ImageNet-pretrained model.

Contrastive Learning Out of Distribution (OOD) Detection +4

Confident Sinkhorn Allocation for Pseudo-Labeling

1 code implementation13 Jun 2022 Vu Nguyen, Hisham Husain, Sachin Farfade, Anton Van Den Hengel

CSA outperforms the current state-of-the-art in this practically important area of semi-supervised learning.

Data Augmentation Pseudo Label

PointInst3D: Segmenting 3D Instances by Points

no code implementations25 Apr 2022 Tong He, Wei Yin, Chunhua Shen, Anton Van Den Hengel

The current state-of-the-art methods in 3D instance segmentation typically involve a clustering step, despite the tendency towards heuristics, greedy algorithms, and a lack of robustness to the changes in data statistics.

3D Instance Segmentation Clustering +2

CNN Attention Guidance for Improved Orthopedics Radiographic Fracture Classification

1 code implementation21 Mar 2022 Zhibin Liao, Kewen Liao, Haifeng Shen, Marouska F. van Boxel, Jasper Prijs, Ruurd L. Jaarsma, Job N. Doornberg, Anton Van Den Hengel, Johan W. Verjans

Convolutional neural networks (CNNs) have gained significant popularity in orthopedic imaging in recent years due to their ability to solve fracture classification problems.

Classification

Active Learning by Feature Mixing

3 code implementations CVPR 2022 Amin Parvaneh, Ehsan Abbasnejad, Damien Teney, Reza Haffari, Anton Van Den Hengel, Javen Qinfeng Shi

We identify unlabelled instances with sufficiently-distinct features by seeking inconsistencies in predictions resulting from interventions on their representations.

Active Learning

Deep Learning for Hate Speech Detection: A Comparative Study

1 code implementation19 Feb 2022 Jitendra Singh Malik, Hezhe Qiao, Guansong Pang, Anton Van Den Hengel

Automated hate speech detection is an important tool in combating the spread of hate speech, particularly in social media.

Computational Efficiency Domain Generalization +1

Scaling up Multi-domain Semantic Segmentation with Sentence Embeddings

no code implementations4 Feb 2022 Wei Yin, Yifan Liu, Chunhua Shen, Baichuan Sun, Anton Van Den Hengel

The resulting merged semantic segmentation dataset of over 2 Million images enables training a model that achieves performance equal to that of state-of-the-art supervised methods on 7 benchmark datasets, despite not using any images therefrom.

Instance Segmentation Monocular Depth Estimation +4

Deep Graph-level Anomaly Detection by Glocal Knowledge Distillation

1 code implementation19 Dec 2021 Rongrong Ma, Guansong Pang, Ling Chen, Anton Van Den Hengel

Graph-level anomaly detection (GAD) describes the problem of detecting graphs that are abnormal in their structure and/or the features of their nodes, as compared to other graphs.

Anomaly Detection Knowledge Distillation

Explainable Deep Few-shot Anomaly Detection with Deviation Networks

1 code implementation1 Aug 2021 Guansong Pang, Choubo Ding, Chunhua Shen, Anton Van Den Hengel

Here, we study the problem of few-shot anomaly detection, in which we aim at using a few labeled anomaly examples to train sample-efficient discriminative detection models.

Ranked #5 on Supervised Anomaly Detection on MVTec AD (using extra training data)

Multiple Instance Learning Supervised Anomaly Detection +1

Dynamic Convolution for 3D Point Cloud Instance Segmentation

1 code implementation18 Jul 2021 Tong He, Chunhua Shen, Anton Van Den Hengel

The proposed approach is proposal-free, and instead exploits a convolution process that adapts to the spatial and semantic characteristics of each instance.

Instance Segmentation Semantic Segmentation

The Road to Know-Where: An Object-and-Room Informed Sequential BERT for Indoor Vision-Language Navigation

1 code implementation ICCV 2021 Yuankai Qi, Zizheng Pan, Yicong Hong, Ming-Hsuan Yang, Anton Van Den Hengel, Qi Wu

Vision-and-Language Navigation (VLN) requires an agent to find a path to a remote location on the basis of natural-language instructions and a set of photo-realistic panoramas.

Vision and Language Navigation Vision-Language Navigation

Learning for Visual Navigation by Imagining the Success

no code implementations28 Feb 2021 Mahdi Kazemi Moghaddam, Ehsan Abbasnejad, Qi Wu, Javen Shi, Anton Van Den Hengel

ForeSIT is trained to imagine the recurrent latent representation of a future state that leads to success, e. g. either a sub-goal state that is important to reach before the target, or the goal state itself.

Navigate Reinforcement Learning (RL) +1

Reasoning over Vision and Language: Exploring the Benefits of Supplemental Knowledge

no code implementations EACL (LANTERN) 2021 Violetta Shevchenko, Damien Teney, Anthony Dick, Anton Van Den Hengel

The technique brings clear benefits to knowledge-demanding question answering tasks (OK-VQA, FVQA) by capturing semantic and relational knowledge absent from existing models.

Question Answering Visual Question Answering (VQA) +1

Memory-Augmented Dynamic Neural Relational Inference

no code implementations ICCV 2021 Dong Gong, Frederic Z. Zhang, Javen Qinfeng Shi, Anton Van Den Hengel

This motivates us to propose a memory-augmented dynamic neural relational inference method, which maintains two associative memory pools: one for the interactive relations and the other for the individual entities.

Trajectory Prediction

Deep Depression Prediction on Longitudinal Data via Joint Anomaly Ranking and Classification

no code implementations5 Dec 2020 Guansong Pang, Ngoc Thien Anh Pham, Emma Baker, Rebecca Bentley, Anton Van Den Hengel

A wide variety of methods have been developed for identifying depression, but they focus primarily on measuring the degree to which individuals are suffering from depression currently.

Depression Detection Metric Learning +1

Counterfactual Vision-and-Language Navigation: Unravelling the Unseen

no code implementations NeurIPS 2020 Amin Parvaneh, Ehsan Abbasnejad, Damien Teney, Qinfeng Shi, Anton Van Den Hengel

The task of vision-and-language navigation (VLN) requires an agent to follow text instructions to find its way through simulated household environments.

counterfactual Embodied Question Answering +2

DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution

1 code implementation CVPR 2021 Tong He, Chunhua Shen, Anton Van Den Hengel

Previous top-performing approaches for point cloud instance segmentation involve a bottom-up strategy, which often includes inefficient operations or complex pipelines, such as grouping over-segmented components, introducing additional steps for refining, or designing complicated loss functions.

Instance Segmentation Semantic Segmentation

Object-and-Action Aware Model for Visual Language Navigation

no code implementations ECCV 2020 Yuankai Qi, Zizheng Pan, Shengping Zhang, Anton Van Den Hengel, Qi Wu

The first is object description (e. g., 'table', 'door'), each presenting as a tip for the agent to determine the next action by finding the item visible in the environment, and the second is action specification (e. g., 'go straight', 'turn left') which allows the robot to directly predict the next movements without relying on visual perceptions.

Object Vision and Language Navigation

Deep Learning for Anomaly Detection: A Review

no code implementations6 Jul 2020 Guansong Pang, Chunhua Shen, Longbing Cao, Anton Van Den Hengel

This paper surveys the research of deep anomaly detection with a comprehensive taxonomy, covering advancements in three high-level categories and 11 fine-grained categories of the methods.

Anomaly Detection Novelty Detection +1

Structured Multimodal Attentions for TextVQA

2 code implementations1 Jun 2020 Chenyu Gao, Qi Zhu, Peng Wang, Hui Li, Yuliang Liu, Anton Van Den Hengel, Qi Wu

In this paper, we propose an end-to-end structured multimodal attention (SMA) neural network to mainly solve the first two issues above.

Graph Attention Optical Character Recognition (OCR) +3

On the Value of Out-of-Distribution Testing: An Example of Goodhart's Law

no code implementations NeurIPS 2020 Damien Teney, Kushal Kafle, Robik Shrestha, Ehsan Abbasnejad, Christopher Kanan, Anton Van Den Hengel

Out-of-distribution (OOD) testing is increasingly popular for evaluating a machine learning system's ability to generalize beyond the biases of a training set.

Model Selection Question Answering +1

Learning What Makes a Difference from Counterfactual Examples and Gradient Supervision

no code implementations ECCV 2020 Damien Teney, Ehsan Abbasnedjad, Anton Van Den Hengel

One of the primary challenges limiting the applicability of deep learning is its susceptibility to learning spurious correlations rather than the underlying mechanisms of the task of interest.

counterfactual Multi-Label Image Classification +4

Self-trained Deep Ordinal Regression for End-to-End Video Anomaly Detection

no code implementations CVPR 2020 Guansong Pang, Cheng Yan, Chunhua Shen, Anton Van Den Hengel, Xiao Bai

Video anomaly detection is of critical practical importance to a variety of real applications because it allows human attention to be focused on events that are likely to be of interest, in spite of an otherwise overwhelming volume of video.

Anomaly Detection regression +2

Unshuffling Data for Improved Generalization

no code implementations27 Feb 2020 Damien Teney, Ehsan Abbasnejad, Anton Van Den Hengel

subsets treated as multiple training environments can guide the learning of models with better out-of-distribution generalization.

Clustering Data Augmentation +3

Learning to Zoom-in via Learning to Zoom-out: Real-world Super-resolution by Generating and Adapting Degradation

no code implementations8 Jan 2020 Dong Gong, Wei Sun, Qinfeng Shi, Anton Van Den Hengel, Yanning Zhang

Most learning-based super-resolution (SR) methods aim to recover high-resolution (HR) image from a given low-resolution (LR) image via learning on LR-HR image pairs.

Super-Resolution

Deep Anomaly Detection with Deviation Networks

6 code implementations19 Nov 2019 Guansong Pang, Chunhua Shen, Anton Van Den Hengel

Instead of representation learning, our method fulfills an end-to-end learning of anomaly scores by a neural deviation learning, in which we leverage a few (e. g., multiple to dozens) labeled anomalies and a prior probability to enforce statistically significant deviations of the anomaly scores of anomalies from that of normal data objects in the upper tail.

Anomaly Detection Cyber Attack Detection +3

Deep Weakly-supervised Anomaly Detection

3 code implementations30 Oct 2019 Guansong Pang, Chunhua Shen, Huidong Jin, Anton Van Den Hengel

To detect both seen and unseen anomalies, we introduce a novel deep weakly-supervised approach, namely Pairwise Relation prediction Network (PReNet), that learns pairwise relation features and anomaly scores by predicting the relation of any two randomly sampled training instances, in which the pairwise relation can be anomaly-anomaly, anomaly-unlabeled, or unlabeled-unlabeled.

Relation Semi-supervised Anomaly Detection +3

On Incorporating Semantic Prior Knowledge in Deep Learning Through Embedding-Space Constraints

no code implementations30 Sep 2019 Damien Teney, Ehsan Abbasnejad, Anton Van Den Hengel

We also show that incorporating this type of prior knowledge with our method brings consistent improvements, independently from the amount of supervised data used.

Data Augmentation Question Answering +1

On Incorporating Semantic Prior Knowlegde in Deep Learning Through Embedding-Space Constraints

no code implementations25 Sep 2019 Damien Teney, Ehsan Abbasnejad, Anton Van Den Hengel

We also show that incorporating this type of prior knowledge with our method brings consistent improvements, independently from the amount of supervised data used.

Data Augmentation Question Answering +1

V-PROM: A Benchmark for Visual Reasoning Using Visual Progressive Matrices

no code implementations29 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.

Visual Reasoning

An Effective Two-Branch Model-Based Deep Network for Single Image Deraining

no code implementations14 May 2019 Yinglong Wang, Dong Gong, Jie Yang, Qinfeng Shi, Anton Van Den Hengel, Dehua Xie, Bing Zeng

Removing rain effects from an image is of importance for various applications such as autonomous driving, drone piloting, and photo editing.

Autonomous Driving Single Image Deraining

Show, Price and Negotiate: A Negotiator with Online Value Look-Ahead

no code implementations7 May 2019 Amin Parvaneh, Ehsan Abbasnejad, Qi Wu, Javen Qinfeng Shi, Anton Van Den Hengel

Negotiation, as an essential and complicated aspect of online shopping, is still challenging for an intelligent agent.

REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environments

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.

Referring Expression Vision and Language Navigation

Actively Seeking and Learning from Live Data

no code implementations CVPR 2019 Damien Teney, Anton Van Den Hengel

One of the key limitations of traditional machine learning methods is their requirement for training data that exemplifies all the information to be learned.

Domain Adaptation Meta-Learning +3

What's to know? Uncertainty as a Guide to Asking Goal-oriented Questions

no code implementations CVPR 2019 Ehsan Abbasnejad, Qi Wu, Javen Shi, Anton Van Den Hengel

We propose a solution to this problem based on a Bayesian model of the uncertainty in the implicit model maintained by the visual dialogue agent, and in the function used to select an appropriate output.

Visual Dialog

Gold Seeker: Information Gain from Policy Distributions for Goal-oriented Vision-and-Langauge Reasoning

no code implementations CVPR 2020 Ehsan Abbasnejad, Iman Abbasnejad, Qi Wu, Javen Shi, Anton Van Den Hengel

For each potential action a distribution of the expected outcomes is calculated, and the value of the potential information gain assessed.

Visual Dialog

Neighbourhood Watch: Referring Expression Comprehension via Language-guided Graph Attention Networks

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.

Graph Attention Object +2

Visual Question Answering as Reading Comprehension

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.

Common Sense Reasoning General Knowledge +4

MPTV: Matching Pursuit Based Total Variation Minimization for Image Deconvolution

no code implementations12 Oct 2018 Dong Gong, Mingkui Tan, Qinfeng Shi, Anton Van Den Hengel, Yanning Zhang

Compared to existing methods, MPTV is less sensitive to the choice of the trade-off parameter between data fitting and regularization.

Image Deconvolution

Goal-Oriented Visual Question Generation via Intermediate Rewards

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.

Informativeness Question Generation +2

Towards Effective Deep Embedding for Zero-Shot Learning

no code implementations30 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.

Zero-Shot Learning

Adaptive Importance Learning for Improving Lightweight Image Super-resolution Network

no code implementations5 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.

Image Super-Resolution

Learning Deep Gradient Descent Optimization for Image Deconvolution

1 code implementation10 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.

Blind Image Deblurring Image Deblurring +1

Deep Lipschitz networks and Dudley GANs

no code implementations ICLR 2018 Ehsan Abbasnejad, Javen Shi, Anton Van Den Hengel

To facilitate this, we develop both theoretical and practical building blocks, using which one can construct different neural networks using a large range of metrics, as well as ensure Lipschitz condition and sufficient capacity of the networks.

Real-time Semantic Image Segmentation via Spatial Sparsity

no code implementations1 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.

Image Segmentation Segmentation +1

Visual Question Answering as a Meta Learning Task

no code implementations ECCV 2018 Damien Teney, Anton Van Den Hengel

At test time, the method is provided with a support set of example questions/answers, over which it reasons to resolve the given question.

Meta-Learning Question Answering +1

Asking the Difficult Questions: Goal-Oriented Visual Question Generation via Intermediate Rewards

no code implementations21 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.

Informativeness Question Generation +2

Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments

8 code implementations CVPR 2018 Peter Anderson, Qi Wu, Damien Teney, Jake Bruce, Mark Johnson, Niko Sünderhauf, Ian Reid, Stephen Gould, Anton Van Den Hengel

This is significant because a robot interpreting a natural-language navigation instruction on the basis of what it sees is carrying out a vision and language process that is similar to Visual Question Answering.

Translation Vision and Language Navigation +2

Parallel Attention: A Unified Framework for Visual Object Discovery through Dialogs and Queries

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.

Object Object Discovery +2

Self-Paced Kernel Estimation for Robust Blind Image Deblurring

no code implementations ICCV 2017 Dong Gong, Mingkui Tan, Yanning Zhang, Anton Van Den Hengel, Qinfeng Shi

Rather than attempt to identify outliers to the model a priori, we instead propose to sequentially identify inliers, and gradually incorporate them into the estimation process.

Blind Image Deblurring Image Deblurring

Beyond Low Rank: A Data-Adaptive Tensor Completion Method

no code implementations3 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.

When Unsupervised Domain Adaptation Meets Tensor Representations

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.

Unsupervised Domain Adaptation

Visually Aligned Word Embeddings for Improving Zero-shot Learning

no code implementations18 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).

Semantic Similarity Semantic Textual Similarity +2

Visual Question Answering with Memory-Augmented 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.

Question Answering Visual Question Answering

Multi-Attention Network for One Shot Learning

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.

One-Shot Learning TAG +1

Bayesian Conditional Generative Adverserial Networks

no code implementations17 Jun 2017 M. Ehsan Abbasnejad, Qinfeng Shi, Iman Abbasnejad, Anton Van Den Hengel, Anthony Dick

Traditional GANs use a deterministic generator function (typically a neural network) to transform a random noise input $z$ to a sample $\mathbf{x}$ that the discriminator seeks to distinguish.

Care about you: towards large-scale human-centric visual relationship detection

no code implementations28 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

The VQA-Machine: Learning How to Use Existing Vision Algorithms to Answer New Questions

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.

BIG-bench Machine Learning Question Answering +1

From Motion Blur to Motion Flow: a Deep Learning Solution for Removing Heterogeneous Motion Blur

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.

Wider or Deeper: Revisiting the ResNet Model for Visual Recognition

3 code implementations30 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.

Semantic Segmentation

Infinite Variational Autoencoder for Semi-Supervised Learning

no code implementations CVPR 2017 Ehsan Abbasnejad, Anthony Dick, Anton Van Den Hengel

This paper presents an infinite variational autoencoder (VAE) whose capacity adapts to suit the input data.

Zero-Shot Visual Question Answering

no code implementations17 Nov 2016 Damien Teney, Anton Van Den Hengel

Answering general questions about images requires methods capable of Zero-Shot VQA, that is, methods able to answer questions beyond the scope of the training questions.

Question Answering Retrieval +2

The Shallow End: Empowering Shallower Deep-Convolutional Networks through Auxiliary Outputs

1 code implementation6 Nov 2016 Yong Guo, Jian Chen, Qing Du, Anton Van Den Hengel, Qinfeng Shi, Mingkui Tan

As a result, the representation power of intermediate layers can be very weak and the model becomes very redundant with limited performance.

Model Compression Model Selection

Visual Question Answering: A Survey of Methods and Datasets

1 code implementation20 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.

General Knowledge Visual Question Answering

FVQA: Fact-based Visual Question Answering

no code implementations17 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.

Common Sense Reasoning Question Answering +1

Deep Recurrent Convolutional Networks for Video-based Person Re-identification: An End-to-End Approach

no code implementations6 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.

Metric Learning Time Series +2

Deep Linear Discriminant Analysis on Fisher Networks: A Hybrid Architecture for Person Re-identification

no code implementations6 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.

Person Re-Identification

What's Wrong With That Object? Identifying Images of Unusual Objects by Modelling the Detection Score Distribution

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.

Gaussian Processes Object +2

Blind Image Deconvolution by Automatic Gradient Activation

no code implementations CVPR 2016 Dong Gong, Mingkui Tan, Yanning Zhang, Anton Van Den Hengel, Qinfeng Shi

We show here that a subset of the image gradients are adequate to estimate the blur kernel robustly, no matter the gradient image is sparse or not.

Image Deconvolution

Bridging Category-level and Instance-level Semantic Image Segmentation

no code implementations23 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.

Image Segmentation Instance Segmentation +2

High-performance Semantic Segmentation Using Very Deep Fully Convolutional Networks

no code implementations15 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.

Image Segmentation Semantic Segmentation +1

Less is more: zero-shot learning from online textual documents with noise suppression

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.

Zero-Shot Learning

Image Co-localization by Mimicking a Good Detector's Confidence Score Distribution

no code implementations15 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.

Object

Pushing the Limits of Deep CNNs for Pedestrian Detection

no code implementations15 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.

Occlusion Handling Optical Flow Estimation +1

Exploring Context with Deep Structured models for Semantic Segmentation

no code implementations10 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.

Image Segmentation Segmentation +1

Hi Detector, What's Wrong with that Object? Identifying Irregular Object From Images by Modelling the Detection Score Distribution

no code implementations14 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".

Gaussian Processes Object

PersonNet: Person Re-identification with Deep Convolutional Neural Networks

1 code implementation27 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.

Person Re-Identification

Compositional Model based Fisher Vector Coding for Image Classification

1 code implementation16 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.

Classification General Classification +1

Structured learning of metric ensembles with application to person re-identification

no code implementations27 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.

Metric Learning Person Re-Identification

Ask Me Anything: Free-form Visual Question Answering Based on Knowledge from External Sources

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.

General Knowledge Question Answering +1

Explicit Knowledge-based Reasoning for Visual Question Answering

no code implementations9 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.

Question Answering Visual Question Answering

Cross-convolutional-layer Pooling for Image Recognition

no code implementations4 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.

General Classification Image Classification

Mining Mid-level Visual Patterns with Deep CNN Activations

1 code implementation21 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.

Image-based Recommendations on Styles and Substitutes

no code implementations15 Jun 2015 Julian McAuley, Christopher Targett, Qinfeng Shi, Anton Van Den Hengel

Humans inevitably develop a sense of the relationships between objects, some of which are based on their appearance.

Deeply Learning the Messages in Message Passing Inference

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.

Image Segmentation Semantic Segmentation +1

What value do explicit high level concepts have in vision to language problems?

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).

Image Captioning Question Answering +1

Part-Based Modelling of Compound Scenes From Images

no code implementations CVPR 2015 Anton van den Hengel, Chris Russell, Anthony Dick, John Bastian, Daniel Pooley, Lachlan Fleming, Lourdes Agapito

We propose a method to recover the structure of a compound scene from multiple silhouettes.

Robust Multiple Homography Estimation: An Ill-Solved Problem

no code implementations CVPR 2015 Zygmunt L. Szpak, Wojciech Chojnacki, Anton Van Den Hengel

The estimation of multiple homographies between two piecewise planar views of a rigid scene is often assumed to be a solved problem.

Homography Estimation

A model-based approach to recovering the structure of a plant from images

no code implementations11 Mar 2015 Ben Ward, John Bastian, Anton Van Den Hengel, Daniel Pooley, Rajendra Bari, Bettina Berger, Mark Tester

We present a method for recovering the structure of a plant directly from a small set of widely-spaced images.

Scalable Nuclear-norm Minimization by Subspace Pursuit Proximal Riemannian Gradient

no code implementations10 Mar 2015 Mingkui Tan, Shijie Xiao, Junbin Gao, Dong Xu, Anton Van Den Hengel, Qinfeng Shi

Nuclear-norm regularization plays a vital role in many learning tasks, such as low-rank matrix recovery (MR), and low-rank representation (LRR).

Clustering Matrix Completion

Learning to rank in person re-identification with metric ensembles

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.

Learning-To-Rank Person Re-Identification

Hashing on Nonlinear Manifolds

no code implementations2 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.

Image Classification Quantization +2

The Treasure beneath Convolutional Layers: Cross-convolutional-layer Pooling for Image Classification

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.

General Classification Image Classification

Large-scale Binary Quadratic Optimization Using Semidefinite Relaxation and Applications

no code implementations27 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.

Clustering Image Segmentation +2

Encoding High Dimensional Local Features by Sparse Coding Based Fisher Vectors

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).

Fine-Grained Image Classification General Classification +2

Mid-level Deep Pattern Mining

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.

Pedestrian Detection with Spatially Pooled Features and Structured Ensemble Learning

no code implementations18 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.

Ensemble Learning object-detection +2

Supervised Hashing Using Graph Cuts and Boosted Decision Trees

1 code implementation24 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.

Descriptive Image Retrieval +1

Strengthening the Effectiveness of Pedestrian Detection with Spatially Pooled Features

no code implementations3 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.

Pedestrian Detection

Efficient Semidefinite Branch-and-Cut for MAP-MRF Inference

no code implementations20 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.

Fast Supervised Hashing with Decision Trees for High-Dimensional Data

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.

Retrieval Vocal Bursts Intensity Prediction

Deconstruction of compound objects from image sets

no code implementations26 Feb 2014 Anton van den Hengel, John Bastian, Anthony Dick, Lachlan Fleming

We propose a method to recover the structure of a compound object from multiple silhouettes.

A Hybrid Loss for Multiclass and Structured Prediction

no code implementations9 Feb 2014 Qinfeng Shi, Mark Reid, Tiberio Caetano, Anton Van Den Hengel, Zhenhua Wang

We propose a novel hybrid loss for multiclass and structured prediction problems that is a convex combination of a log loss for Conditional Random Fields (CRFs) and a multiclass hinge loss for Support Vector Machines (SVMs).

Action Recognition Structured Prediction +1

Constraint Reduction using Marginal Polytope Diagrams for MAP LP Relaxations

no code implementations17 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.

Fast Training of Effective Multi-class Boosting Using Coordinate Descent Optimization

no code implementations23 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).

Multi-class Classification

Contextual Hypergraph Modelling for Salient Object Detection

no code implementations22 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.

Object object-detection +2

Online Unsupervised Feature Learning for Visual Tracking

no code implementations7 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.

Dictionary Learning Visual Tracking

Efficient pedestrian detection by directly optimize the partial area under the ROC curve

no code implementations3 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.

Ensemble Learning object-detection +2

Characterness: An Indicator of Text in the Wild

no code implementations25 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.

Saliency Detection Scene Text Detection +1

A General Two-Step Approach to Learning-Based Hashing

no code implementations7 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.

Vocal Bursts Valence Prediction

A scalable stage-wise approach to large-margin multi-class loss based boosting

no code implementations21 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.

Classification General Classification +1

Bilinear Programming for Human Activity Recognition with Unknown MRF Graphs

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.

Human Activity Recognition

Part-Based Visual Tracking with Online Latent Structural Learning

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.

Structured Prediction Visual Tracking

Learning Compact Binary Codes for Visual Tracking

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.

Visual Tracking

Fast Approximate L_infty Minimization: Speeding Up Robust Regression

no code implementations4 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.

regression

A Fast Semidefinite Approach to Solving Binary Quadratic Problems

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.

Clustering Image Segmentation +2