Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks115 from public data
- When Face Recognition Meets with Deep Learning: An Evaluation of Convolutional Neural Networks for Face Recognition334
An extensive evaluation of CNN-based face recognition systems (CNN-FRS) and proposes three CNN architectures which are the first reported architectures trained using LFW data to make the work easily reproducible.
- Ranked List Loss for Deep Metric Learning279
This work presents two limitations of existing ranking-motivated structured losses and proposes a novel ranked list loss to solve both of them and proposes to learn a hypersphere for each class in order to preserve the similarity structure inside it.
- A Multiresolution 3D Morphable Face Model and Fitting Framework248
The Surrey Face Model is presented, a multi-resolution 3D Morphable Model that is made available to the public for non-commercial purposes and a lightweight open-source C++ library designed with simplicity and ease of integration as its foremost goals.
- 202
- 183
- DPT: Deformable Patch-based Transformer for Visual Recognition141
A new Deformable Patch (DePatch) module is proposed which learns to adaptively split the images into patches with different positions and scales in a data-driven way rather than using predefined fixed patches, which can well preserve the semantics in patches.
- Frankenstein: Learning Deep Face Representations Using Small Data137
This paper proposes a method to generate very large training data sets of synthetic images by compositing real face images in a given data set and shows that this method enables to learn models from as few as 10 000 training images, which perform on par with models trained from 500 000 images.
- Differentiable Automatic Data Augmentation120
Differentiable Automatic Data Augmentation is proposed which dramatically reduces the cost, relaxes the discrete DA policy selection to a differentiable optimization problem via Gumbel-Softmax, and introduces an unbiased gradient estimator, RELAX, leading to an efficient and effective one-pass optimization strategy to learn an efficient and accurate DA policy.
- Conv-Adapter: Exploring Parameter Efficient Transfer Learning for ConvNets113
Conv-Adapter, a PET module designed for ConvNets, is light-weight, domain-transferable, and architecture-agnostic with generalized performance on different tasks with comparable or surpasses the performance of full fine-tuning on 23 classification tasks of various domains.
- 99
- 93
- 86
- MAMBA: Multi-level Aggregation via Memory Bank for Video Object Detection81
This paper proposes a multi-level aggregation architecture via memory bank called MAMBA, which employs two novel operations to eliminate disadvantages of existing methods: light-weight key-set construction which can significantly reduce the computational cost and fine-grained feature-wise updating strategy which enables the method to utilize knowledge from the whole video.
- Adaptive Variance Based Label Distribution Learning for Facial Age Estimation71
An adaptive variance based distribution learning (AVDL) method for facial age estimation that introduces the data-driven optimization framework, meta-learning, to achieve this and can approximate the true age probability distribution more e-ectively.
- Semantic Alignment: Finding Semantically Consistent Ground-Truth for Facial Landmark Detection71
A novel probabilistic model is proposed which introduces a latent variable, i.e. ‘real’ groundtruth which is semantically consistent, to optimize the landmark detection accuracy and achieves state-of-the-art performance.
- OPANAS: One-Shot Path Aggregation Network Architecture Search for Object Detection69
A novel One-Shot Path Aggregation Network Architecture Search (OPANAS) algorithm, which significantly improves both searching efficiency and detection accuracy, and an efficient one-shot search method to find the optimal path aggregation architecture.
- 60
- Face Recognition Using a Unified 3D Morphable Model56
The proposed solution involves a novel approach to learn a subspace spanned by perturbations caused by the missing modes of variation and image degradations, using 3D face data reconstructed from 2D images rather than 3D capture.
- CRSSC: Salvage Reusable Samples from Noisy Data for Robust Learning55
This work proposes a certainty-based reusable sample selection and correction approach, termed as CRSSC, for coping with label noise in training deep FG models with web images, which is to additionally identify and correct reusable samples, and then leverage them together with clean examples to update the networks.
- 53
- Deep Metric Learning by Online Soft Mining and Class-Aware Attention53
This work proposes a novel sample mining method, called Online Soft Mining (OSM), which assigns one continuous score to each sample to make use of all samples in the mini-batch, and introduces Class-Aware Attention (CAA) that assigns little attention to abnormal data samples.
- MetaMixUp: Learning Adaptive Interpolation Policy of MixUp With Metalearning52
A metalearning-based online optimization approach to dynamically learn the interpolation policy in a data-adaptive way (learning to learn better) and extensive experiments show that the MetaMixUp adapted SSL greatly outperforms MixUp and many state-of-the-art methods on CIFAR-10 and SVHN benchmarks under the SSL configuration.
- 52
- Deep Stock Representation Learning: From Candlestick Charts to Investment Decisions51
This work applies Convolutional AutoEncoder to learn a stock representation, based on which a novel portfolio construction strategy is proposed, using the deeply learned representation and modularity optimisation to cluster stocks and identify diverse sectors.
- Deep Multi-task Learning to Recognise Subtle Facial Expressions of Mental States47
This work addresses subtle expression recognition through convolutional neural networks (CNNs) by developing multi-task learning (MTL) methods to effectively leverage a side task: facial landmark detection and achieves very competitive performance on Oulu-Casia NIR&Vis and CK+ databases via transfer learning.
- 44
- Boosting Active Learning via Improving Test Performance43
This work theoretically proves that selecting unlabeled data of higher gradient norm leads to a lower upper-bound of test loss, resulting in a better test performance, and proposes two schemes, namely expected-grad norm and entropy-gradnorm, which are integrated in a universal AL framework.
- Efficient 3D morphable face model fitting42
An efficient stepwise 3DMM-to-2D image-fitting procedure, which sequentially optimises the pose, shape, light direction, light strength and skin texture parameters in separate steps leading to an accurate and efficient fitting is presented.
- 39
- 37
- 3D Morphable Face Models and Their Applications36
Recent developments in 3D face modelling and model fitting will be overviewed, and their merits in the context of diverse applications illustrated on several examples, including pose and illumination invariant face recognition, and3D face reconstruction from video.
- 34
- Learning Flow-Based Feature Warping for Face Frontalization with Illumination Inconsistent Supervision33
A novel Flow-based Feature Warping Model (FFWM) which can learn to synthesize photo-realistic and illumination preserving frontal images with illumination inconsistent supervision is proposed and performs favorably against the state-of-the-art results.
- 31
- Learning Symmetry Consistent Deep CNNs for Face Completion31
Two kinds of symmetry-enforcing modules are Leveraged to form a symmetry-consistent CNN model (i.e., SymmFCNet) for effective face completion and can generate globally consistent results on images with synthetic and real occlusions, and performs favorably against state-of-the-arts.
- Collaborative representation based face classification exploiting block weighted LBP and analysis dictionary learning31
A block weighted LBP histogram algorithm is designed to form a set of local histogram-based feature vectors instead of using raw images to effectively decrease data redundancy and uncertainty derived from image noises and appearance variations.
- Diverse Person: Customize Your Own Dataset for Text-Based Person Search30
This paper proposes to leverage available images of clothing and accessories as reference attribute images to edit the original dataset images through diffusion models, and employs a Large Language Model (LLM) to produce annotations that are both high in quality and stylistically consistent with those found in real-world datasets.
- 30
- 29
- Dictionary Integration Using 3D Morphable Face Models for Pose-Invariant Collaborative-Representation-Based Classification29
A dictionary integration algorithm using 3D morphable face models (3DMM) for pose-invariant collaborative-representation-based face classification and an on-line pruning strategy under the CRC framework is presented.
- 26
- Reducing Distributional Uncertainty by Mutual Information Maximisation and Transferable Feature Learning25
This paper proposes to formulate the distributional uncertainty both between the source and target domain and within each domain using mutual information, and proposes a transferable feature learning scheme, balancing two complementary and discriminative feature learning processes according to the uncertainty.
- Cross-Modal Distillation for Speaker Recognition23
This work introduces a multimodal learning framework, VGSR (Vision-Guided Speaker Recognition), and proposes a MKD (Margin-based Knowledge Distillation) strategy for cross-modality distillation by introducing a loose constrain to align the teacher and student, greatly reducing overfitting.
- Efficient One-Stage Video Object Detection by Exploiting Temporal Consistency21
This paper presents a simple yet efficient framework to address the computational bottlenecks and achieve efficient one-stage VOD by exploiting the temporal consistency in video frames and consists of a location-prior network and size-prior network to skip unnecessary computations on low-level feature maps for specific frames.
- Half-Face Dictionary Integration for Representation-Based Classification21
The proposed HFDI algorithm measures residuals between an input signal and the reconstructed one, using both the original and the synthesized dual-column (row) half-face training samples, and proposes an elimination strategy to gain the most robust training atoms.
- 21
- 20
- 17
- Resolution-Aware 3D Morphable Model17
A Resolution-Aware 3DMM (RA-3DMM) is proposed, which consists of 3 different resolution 3DMMs: High-Resolution 2D Morphable Model (HR- 2DMM), Medium-Res resolution 3D MM (MR-3 DMM) and Low-Resolved 3D MMR (LR-3dMM), which automatically select the best model to fit the input images of different resolutions.
- Design of Wireless Sensor Network Bidirectional Nodes for Intelligent Monitoring System of Micro-irrigation in Litchi Orchards16
Wireless sensor network (WSN) bidirectional nodes, including the sensing node and the solenoid valve control node, were developed for information collection and micro-irrigation monitoring system in a litchi orchard, aimed at improving the problem of wireless communication barriers and the micro-IRrigation management efficiency.
- Colour face recognition using fuzzy quaternion-based discriminant analysis16
A novel fuzzy supervised learning approach to reconstruct the quaternion-based discriminant vector space is provided, thus showing the importance of the FQD characteristic from colour spaces for colour-image-based face recognition.
- 15
- 15
- 15
- The 3rd Workshop on UAVs in Multimedia: Capturing the World from a New Perspective13
This workshop will cover various topics related to UAV multimedia, including aerial image and video processing, machine learning for UAV data analysis, UAV swarm technology, and UAV-based multimedia applications.
- 13
- 13
- Neighborhood-Enhanced 3D Human Pose Estimation with Monocular LiDAR in Long-Range Outdoor Scenes12
This work deeply investigates the 3D neighbor in the background (3BN) which serves as a spatial coherence cue for inferring reliable motion since it provides physical laws to limit motion targets and introduces a novel 3D scanning neighbor (3SN) generated during the data collection and 3SN implies structural edge coherence cues.
- 12
- 9
- 7
- 7
- 6
- 6
- 5
- Fast SRC using quadratic optimisation in downsized coefficient solution subspace5
Experimental results conducted on a set of well-known face datasets, including AR, FERET, LFW and FRGC, demonstrate the merits of the proposed methods, especially in computational efficiency.
- 5
- 5
- 5
- 4
- 4
- 4
- Progressive sparse representation-based classification using local discrete cosine transform evaluation for image recognition4
The final goal of the proposed method is to determine an optimal weighted sum of nearest neighbors that are obtained under the local correlative degree evaluation, which is approximately equal to the test sample, and it can use this weighted linear combination to perform robust classification.
- 4
- 4
- 3
- 3
- 3
- 3
- 3
- 2
- Cap2Sum: Learning to Summarize Videos by Generating Captions2
The use of dense video captions as a supervision signal to train video summarization models and a CLIP (a strong vision-language model) Prior mechanism to enhance the learning of important objects that captions may ignore in the videos are introduced.
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-16. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.