Search Results for author:
Found 83 papers, 23 papers with code
SCD-Net: Spatiotemporal Clues Disentanglement Network for Self-supervised Skeleton-based Action Recognition
Contrastive learning has achieved great success in skeleton-based action recognition.
Generative-based Fusion Mechanism for Multi-Modal Tracking
In this context, we seek to uncover the potential of harnessing generative techniques to address the critical challenge, information fusion, in multi-modal tracking.
Masked Momentum Contrastive Learning for Zero-shot Semantic Understanding
Self-supervised pretraining (SSP) has emerged as a popular technique in machine learning, enabling the extraction of meaningful feature representations without labelled data.
FusionBooster: A Unified Image Fusion Boosting Paradigm
We argue that there is a scope to improve the fusion performance with the help of the FusionBooster, a model specifically designed for the fusion task.
LRRNet: A Novel Representation Learning Guided Fusion Network for Infrared and Visible Images
In particular we adopt a learnable representation approach to the fusion task, in which the construction of the fusion network architecture is guided by the optimisation algorithm producing the learnable model.
ASiT: Audio Spectrogram vIsion Transformer for General Audio Representation
Vision transformers, which were originally developed for natural language processing, have recently generated significant interest in the computer vision and audio communities due to their flexibility in learning long-range relationships.
RGBD1K: A Large-scale Dataset and Benchmark for RGB-D Object Tracking
To demonstrate the benefits of training on a larger RGB-D data set in general, and RGBD1K in particular, we develop a transformer-based RGB-D tracker, named SPT, as a baseline for future visual object tracking studies using the new dataset.
Doubly Reparameterized Importance Weighted Structure Learning for Scene Graph Generation
As a structured prediction task, scene graph generation, given an input image, aims to explicitly model objects and their relationships by constructing a visually-grounded scene graph.
DreamNet: A Deep Riemannian Network based on SPD Manifold Learning for Visual Classification
Image set-based visual classification methods have achieved remarkable performance, via characterising the image set in terms of a non-singular covariance matrix on a symmetric positive definite (SPD) manifold.
GMML is All you Need
This has motivated the research in self-supervised transformer pretraining, which does not need to decode the semantic information conveyed by labels to link it to the image properties, but rather focuses directly on extracting a concise representation of the image data that reflects the notion of similarity, and is invariant to nuisance factors.
Importance Weighted Structure Learning for Scene Graph Generation
Scene graph generation is a structured prediction task aiming to explicitly model objects and their relationships via constructing a visually-grounded scene graph for an input image.
Constrained Structure Learning for Scene Graph Generation
As a structured prediction task, scene graph generation aims to build a visually-grounded scene graph to explicitly model objects and their relationships in an input image.
Riemannian Local Mechanism for SPD Neural Networks
The Symmetric Positive Definite (SPD) matrices have received wide attention for data representation in many scientific areas.
Exploring Fusion Strategies for Accurate RGBT Visual Object Tracking
The effectiveness of the proposed decision-level fusion strategy owes to a number of innovative contributions, including a dynamic weighting of the RGB and TIR contributions and a linear template update operation.
Neural Belief Propagation for Scene Graph Generation
Scene graph generation aims to interpret an input image by explicitly modelling the potential objects and their relationships, which is predominantly solved by the message passing neural network models in previous methods.
MC-SSL0.0: Towards Multi-Concept Self-Supervised Learning
In this aspect the proposed SSL frame-work MC-SSL0. 0 is a step towards Multi-Concept Self-Supervised Learning (MC-SSL) that goes beyond modelling single dominant label in an image to effectively utilise the information from all the concepts present in it.
Global Interaction Modelling in Vision Transformer via Super Tokens
Hence, most of the learning is independent of the image patches $(N)$ in the higher layers, and the class embedding is learned solely based on the Super tokens $(N/M^2)$ where $M^2$ is the window size.
Benchmarking Quality-Dependent and Cost-Sensitive Score-Level Multimodal Biometric Fusion Algorithms
The cost-sensitive evaluation, on the other hand, investigates how well a fusion algorithm can perform given restricted computation and in the presence of software and hardware failures, resulting in errors such as failure-to-acquire and failure-to-match.
The Multiscenario Multienvironment BioSecure Multimodal Database (BMDB)
It is comprised of more than 600 individuals acquired simultaneously in three scenarios: 1) over the Internet, 2) in an office environment with desktop PC, and 3) in indoor/outdoor environments with mobile portable hardware.
AestheticNet: Reducing bias in facial data sets under ethical considerations
Our experiments prove that human aesthetic judgements are usually biased.
Learning PAC-Bayes Priors for Probabilistic Neural Networks
We experiment on 6 datasets with different strategies and amounts of data to learn data-dependent PAC-Bayes priors, and we compare them in terms of their effect on test performance of the learnt predictors and tightness of their risk certificate.
MOON: Multi-Hash Codes Joint Learning for Cross-Media Retrieval
To this end, we develop a novel Multiple hash cOdes jOint learNing method (MOON) for cross-media retrieval.
PPT Fusion: Pyramid Patch Transformerfor a Case Study in Image Fusion
In this paper, we propose a Patch Pyramid Transformer(PPT) to effectively address the above issues. Specifically, we first design a Patch Transformer to transform the image into a sequence of patches, where transformer encoding is performed for each patch to extract local representations.
SiT: Self-supervised vIsion Transformer
We also observed that SiT is good for few shot learning and also showed that it is learning useful representation by simply training a linear classifier on top of the learned features from SiT.
RFN-Nest: An end-to-end residual fusion network for infrared and visible images
The most difficult part of the design is to choose an appropriate strategy to generate the fused image for a specific task in hand.
NPT-Loss: A Metric Loss with Implicit Mining for Face Recognition
One key ingredient of DCNN-based FR is the appropriate design of a loss function that ensures discrimination between various identities.
Differentiable Neural Architecture Learning for Efficient Neural Network Design
To address this computational complexity issue, we introduce a novel \emph{architecture parameterisation} based on scaled sigmoid function, and propose a general \emph{Differentiable Neural Architecture Learning} (DNAL) method to optimize the neural architecture without the need to evaluate candidate neural networks.
Deep Decomposition Network for Image Processing: A Case Study for Visible and Infrared Image Fusion
In this paper, we apply the image decomposition network to the image fusion task.
AXM-Net: Implicit Cross-Modal Feature Alignment for Person Re-identification
Our framework is novel in its ability to implicitly learn aligned semantics between modalities during the feature learning stage.
Ranked #9 on
Text based Person Retrieval
on CUHK-PEDES
Cross-Modal Person Re-Identification
Cross-Modal Person Re-Identification
+3
Separable Batch Normalization for Robust Facial Landmark Localization with Cross-protocol Network Training
Different from the standard BN layer that uses all the training data to calculate a single set of parameters, SepBN considers that the samples of a training dataset may belong to different sub-domains.
A Flatter Loss for Bias Mitigation in Cross-dataset Facial Age Estimation
Compared with existing loss functions, the lower gradient of the proposed loss function leads to the convergence of SGD to a better optimum point, and consequently a better generalisation.
Self-grouping Convolutional Neural Networks
To tackle this issue, we propose a novel method of designing self-grouping convolutional neural networks, called SG-CNN, in which the filters of each convolutional layer group themselves based on the similarity of their importance vectors.
Deep Convolutional Neural Network Ensembles using ECOC
Deep neural networks have enhanced the performance of decision making systems in many applications including image understanding, and further gains can be achieved by constructing ensembles.
Affine Non-negative Collaborative Representation Based Pattern Classification
Moreover, ANCR introduces an affine constraint to better represent the data from affine subspaces.
AFAT: Adaptive Failure-Aware Tracker for Robust Visual Object Tracking
To this end, we propose a failure-aware system, realised by a Quality Prediction Network (QPN), based on convolutional and LSTM modules in the decision stage, enabling online reporting of potential tracking failures.
A Convolutional Baseline for Person Re-Identification Using Vision and Language Descriptions
However, in real-world surveillance scenarios, frequently no visual information will be available about the queried person.
Adaptive Distraction Context Aware Tracking Based on Correlation Filter
In the response map obtained for the previous frame by the CF algorithm, we adaptively find the image blocks that are similar to the target and use them as negative samples.
Face Recognition via Locality Constrained Low Rank Representation and Dictionary Learning
First, a low-rank representation is introduced to handle the possible contamination of the training as well as test data.
An Accelerated Correlation Filter Tracker
Recent visual object tracking methods have witnessed a continuous improvement in the state-of-the-art with the development of efficient discriminative correlation filters (DCF) and robust deep neural network features.
Learning a Representation with the Block-Diagonal Structure for Pattern Classification
To counteract this problem, we propose an approach that learns Representation with Block-Diagonal Structure (RBDS) for robust image recognition.
Spatial Residual Layer and Dense Connection Block Enhanced Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition
In order to capture the rich spatiotemporal information and utilize features more effectively, we introduce a spatial residual layer and a dense connection block enhanced spatial temporal graph convolutional network.
Ranked #41 on
Skeleton Based Action Recognition
on NTU RGB+D
Dual Encoder-Decoder based Generative Adversarial Networks for Disentangled Facial Representation Learning
To be more specific, the encoder-decoder structured generator is used to learn a pose disentangled face representation, and the encoder-decoder structured discriminator is tasked to perform real/fake classification, face reconstruction, determining identity and estimating face pose.
More About Covariance Descriptors for Image Set Coding: Log-Euclidean Framework based Kernel Matrix Representation
We consider a family of structural descriptors for visual data, namely covariance descriptors (CovDs) that lie on a non-linear symmetric positive definite (SPD) manifold, a special type of Riemannian manifolds.
Multiple Riemannian Manifold-valued Descriptors based Image Set Classification with Multi-Kernel Metric Learning
Specifically, the covariance matrix, linear subspace, and Gaussian distribution are applied for set representation simultaneously.
Joint Group Feature Selection and Discriminative Filter Learning for Robust Visual Object Tracking
We propose a new Group Feature Selection method for Discriminative Correlation Filters (GFS-DCF) based visual object tracking.
Ranked #1 on
Visual Object Tracking
on VOT2017
Multi-Task Kernel Null-Space for One-Class Classification
The non-linear structure learning method is then extended to a sparse setting where different tasks compete in an output composition mechanism, leading to a sparse non-linear structure among multiple problems.
Transition Subspace Learning based Least Squares Regression for Image Classification
Only learning one projection matrix from original samples to the corresponding binary labels is too strict and will consequentlly lose some intrinsic geometric structures of data.
Low-Rank Discriminative Least Squares Regression for Image Classification
To solve above problems, we propose a low-rank discriminative least squares regression model (LRDLSR) for multi-class image classification.
Fisher Discriminative Least Squares Regression for Image Classification
On one hand, the Fisher criterion improves the intra-class compactness of the relaxed labels during relaxation learning.
Non-negative representation based discriminative dictionary learning for face recognition
In this paper, we propose a non-negative representation based discriminative dictionary learning algorithm (NRDL) for multicategory face classification.
Visual Semantic Information Pursuit: A Survey
Since it helps to enhance the accuracy and the consistency of the resulting interpretation, visual context reasoning is often incorporated with visual perception in current deep end-to-end visual semantic information pursuit methods.
Robust One-Class Kernel Spectral Regression
This work addresses these shortcomings by studying the effect of regularising the solution of the null-space kernel Fisher methodology in the context of its regression-based formulation (OC-KSR).
Discriminative Supervised Hashing for Cross-Modal similarity Search
With the advantage of low storage cost and high retrieval efficiency, hashing techniques have recently been an emerging topic in cross-modal similarity search.
Pose Invariant 3D Face Reconstruction
Our method solves the problem of face reconstruction of a single image of a traditional method in a large pose, works on arbitrary Pose and Expressions, greatly improves the accuracy of reconstruction.
MDLatLRR: A novel decomposition method for infrared and visible image fusion
We develop a novel image fusion framework based on MDLatLRR, which is used to decompose source images into detail parts(salient features) and base parts.
Landmark Weighting for 3DMM Shape Fitting
In this paper we show that landmark weighting is instrumental to improve the accuracy of shape reconstruction and propose a novel 3D Morphable Model Fitting method.
Learning Discriminative Hashing Codes for Cross-Modal Retrieval based on Multi-view Features
Many hashing methods based on a single view have been extensively studied for information retrieval.
Learning Adaptive Discriminative Correlation Filters via Temporal Consistency Preserving Spatial Feature Selection for Robust Visual Tracking
The key innovations of the proposed method include adaptive spatial feature selection and temporal consistent constraints, with which the new tracker enables joint spatial-temporal filter learning in a lower dimensional discriminative manifold.
One-Class Kernel Spectral Regression
The paper introduces a new efficient nonlinear one-class classifier formulated as the Rayleigh quotient criterion optimisation.
Client-Specific Anomaly Detection for Face Presentation Attack Detection
In addition, it is demonstrated that the same set of deep convolutional features used for the recognition purposes is effective for face presentation attack detection in the class-specific one-class anomaly detection paradigm.
Grassmannian Discriminant Maps (GDM) for Manifold Dimensionality Reduction with Application to Image Set Classification
The core of the method is a new discriminant function for metric learning and dimensionality reduction.
Semi-supervised Hashing for Semi-Paired Cross-View Retrieval
Recently, hashing techniques have gained importance in large-scale retrieval tasks because of their retrieval speed.
Riemannian kernel based Nyström method for approximate infinite-dimensional covariance descriptors with application to image set classification
We propose a novel framework for representing image sets by approximating infinite-dimensional CovDs in the paradigm of the Nystr\"om method based on a Riemannian kernel.
Multiple Manifolds Metric Learning with Application to Image Set Classification
In image set classification, a considerable advance has been made by modeling the original image sets by second order statistics or linear subspace, which typically lie on the Riemannian manifold.
A Simple Riemannian Manifold Network for Image Set Classification
The proposed RieMNet and DRieMNet are evaluated on three tasks: video-based face recognition, set-based object categorization, and set-based cell identification.
L1-(2D)2PCANet: A Deep Learning Network for Face Recognition
In our network, the role of L1-(2D)2PCA is to learn the filters of multiple convolution layers.
Infrared and Visible Image Fusion using a Deep Learning Framework
Then the base parts are fused by weighted-averaging.
Semi-supervised Adversarial Learning to Generate Photorealistic Face Images of New Identities from 3D Morphable Model
We propose a novel end-to-end semi-supervised adversarial framework to generate photorealistic face images of new identities with wide ranges of expressions, poses, and illuminations conditioned by a 3D morphable model.
Ranked #16 on
Face Verification
on IJB-A
Evaluation of Dense 3D Reconstruction from 2D Face Images in the Wild
To this end, we organise a competition that provides a new benchmark dataset that contains 2000 2D facial images of 135 subjects as well as their 3D ground truth face scans.
Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks
We present a new loss function, namely Wing loss, for robust facial landmark localisation with Convolutional Neural Networks (CNNs).
Ranked #1 on
Face Alignment
on 300W
(NME_inter-pupil (%, Common) metric)
Person Re-Identification with Vision and Language
We propose a joint vision and language model based on CCA and CNN architectures to match across the two modalities as well as to enrich visual examples for which there are no language descriptions.
3D Morphable Models as Spatial Transformer Networks
In this paper, we show how a 3D Morphable Model (i. e. a statistical model of the 3D shape of a class of objects such as faces) can be used to spatially transform input data as a module (a 3DMM-STN) within a convolutional neural network.
Unconstrained Face Detection and Open-Set Face Recognition Challenge
Face detection and recognition benchmarks have shifted toward more difficult environments.
Face Detection, Bounding Box Aggregation and Pose Estimation for Robust Facial Landmark Localisation in the Wild
The framework has four stages: face detection, bounding box aggregation, pose estimation and landmark localisation.
A Unified Tensor-based Active Appearance Face Model
To deal with this challenge, we present a Unified Tensor-based Active Appearance Model (UT-AAM) for jointly modelling the geometry and texture information of 2D faces.
Dynamic Attention-controlled Cascaded Shape Regression Exploiting Training Data Augmentation and Fuzzy-set Sample Weighting
We present a new Cascaded Shape Regression (CSR) architecture, namely Dynamic Attention-Controlled CSR (DAC-CSR), for robust facial landmark detection on unconstrained faces.
Ranked #17 on
Face Alignment
on AFLW-19
Dictionary Integration using 3D Morphable Face Models for Pose-invariant Collaborative-representation-based Classification
The paper presents a dictionary integration algorithm using 3D morphable face models (3DMM) for pose-invariant collaborative-representation-based face classification.
3D Face Tracking and Texture Fusion in the Wild
We present a fully automatic approach to real-time 3D face reconstruction from monocular in-the-wild videos.
Delta divergence: A novel decision cognizant measure of classifier incongruence
In this paper, we postulate the properties that a divergence measure should satisfy and propose a novel divergence measure, referred to as Delta divergence.
A Multiresolution 3D Morphable Face Model and Fitting Framework
In this paper, we present the Surrey Face Model, a multi-resolution 3D Morphable Model that we make available to the public for non-commercial purposes.
When Face Recognition Meets with Deep Learning: an Evaluation of Convolutional Neural Networks for Face Recognition
In this work, we conduct an extensive evaluation of CNN-based face recognition systems (CNN-FRS) on a common ground to make our work easily reproducible.
Fitting 3D Morphable Models using Local Features
Our approach is unique in that we are the first to use local features to fit a Morphable Model.
Assessment of algorithms for mitosis detection in breast cancer histopathology images
The proliferative activity of breast tumors, which is routinely estimated by counting of mitotic figures in hematoxylin and eosin stained histology sections, is considered to be one of the most important prognostic markers.
