Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Alex Chichung KotSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works66 from public data
- 330
- 328
- 79
- Towards Automatic Screening of Typical and Atypical Behaviors in Children With Autism66
A preliminary non-intrusive approach based on skeleton keypoint identification using pretrained deep neural networks on human body video clips to extract features and perform body movement analysis that differentiates typical and atypical behaviors of children is proposed.
- 54
- Deep residual network with regularised fisher framework for detection of melanoma52
A deep convolutional neural network-based regularised discriminant learning framework which extracts low-dimensional discriminative features for melanoma detection is proposed and minimises the whole of within-class variance information and maximises the total class variance information.
- Egocentric activity recognition with multimodal fisher vector47
A novel strategy to extract temporal trajectory-like features from sensor data and propose to apply the Fisher Kernel framework to fuse video and temporal enhanced sensor features to enhance information-rich video data is presented.
- A Wearable Face Recognition System on Google Glass for Assisting Social Interactions47
This paper proposes a wearable face recognition system on Google Glass, which acts as a social interaction assistant, the application includes face detection, eye localization, face recognition and a user interface for personal information display.
- Complete discriminant evaluation and feature extraction in kernel space for face recognition40
This work proposes a method to decompose the kernel within-class eigenspace into two subspaces: a reliable subspace spanned mainly by the facial variation and an unreliable subspace due to limited number of training samples.
- Multi-sensor Self-Quantification of Presentations34
This work proposes a novel multi-sensor self-quantification framework for presentations and conducts a user study with the speakers to verify the effectiveness of the system generated analytics, which has received positive and promising feedback.
- Enhanced maximum likelihood face recognition31
A method to enhance maximum likelihood face recognition is presented, which selects a more robust weighting parameter and discards unreliable dimensions to circumvent problems of the unreliable small and zero eigenvalues.
- Deep convolutional neural network-based patch classification for retinal nerve fiber layer defect detection in early glaucoma29
A deep convolutional neural network (CNN) based patch classification strategy for RNFLD boundary localization is formulated, which is found to achieve enhanced R NFLD detection performance with sensitivity and false positive per image on a newly created early glaucomatic fundus image database.
- Performance evaluation of local descriptors and distance measures on benchmarks and first-person-view videos for face identification27
Comparative analysis on these databases using various descriptors shows the superiority of BSIF with Cosine, Chi square and Cityblock distance measures using 1-NN as classifier over other descriptors and distance measures and even some of the current state-of-art benchmark database results.
- 24
- Prediction of eigenvalues and regularization of eigenfeatures for human face verification23
Experimental results on popular face databases show that the proposed prediction and regularization strategy for alleviating the conventional problems of LDA and its variants consistently outperforms others.
- 22
- 21
- 21
- GlaucoNet: Patch-Based Residual Deep Learning Network for Optic Disc and Cup Segmentation Towards Glaucoma Assessment20
Experimental results showing better or comparable segmentation performance and decrease in cup-to-disc height ratio estimation errors demonstrate the efficacy of the proposed GlaucoNet-based segmentation methodology.
- Variance-guided attention-based twin deep network for cross-spectral periocular recognition20
Ablation studies and experimental results on three publicly available cross-spectral periocular datasets containing images from VIS, near-infrared (NIR), and night vision domains show that the proposed deep network achieves the state-of-the-art recognition performances on all three datasets.
- 19
- Exploring users' attitudes towards social interaction assistance on Google Glass19
It is found that users in general appreciated the usefulness of wearable assistance for social interactions and highlighted a few key issues of how wearable devices affect user experience in social interaction.
- Deep Adaptive Temporal Pooling for Activity Recognition18
A learnable and differentiable module: Deep Adaptive Temporal Pooling (DATP), which applies a self-attention mechanism to adaptively pool the classification scores of different video segments to improve training of frame-level feature extractor.
- 18
- Face recognition: Perspectives from the real world16
The gaps between expectations of the user and what the system can deliver are discussed and the existing algorithms with modifications are evaluated for applications including FR on wearable devices (like Google Glass) for improving social interactions.
- 16
- Rotation insensitive implantable wireless power transfer system for medical devices using metamaterial-polarization converter15
The measured results confirm the feasibility of the introduced approach, exhibiting improved efficiency due to use of the MTM-PC, and the PTE of the proposed MTM-PC integrated implantable WPT system is increased significantly compared to the system without MTM-PC.
- 15
- SocioGlass: social interaction assistance with face recognition on google glass14
SocioGlass is a system built on Google Glass paired with a mobile phone that provides a user with in-situ information about an acquaintance in face-to-face communication that can be used to help acquaintances build relationships, or to assist people with memory problems.
- Evaluation of Descriptors and Distance Measures on Benchmarks and First-Person-View Videos for Face Identification14
Comparative analysis on these databases using various descriptors shows the superiority of BSIF with Cosine, Chi square and Cityblock distance measures using 1-NN as classifier over other descriptors and distance measures and even some of the current state-of-art benchmark database results.
- Trends in Machine and Human Face Recognition13
This chapter reviews two aspects of FR: machine recognition of faces and how human beings recognize human faces and the recent benchmark studies, their protocols and databases, and psychophysical studies of FR abilities of human beings.
- Deep Residual Network with Subclass Discriminant Analysis for Crowd Behavior Recognition11
Experimental results on large crowd behavior video database show the superior performance of the proposed framework as compared to the baseline and current state-of-the-art methodologies for the crowd behavior recognition task.
- Distinguishing Posed and Spontaneous Smiles by Facial Dynamics11
This work proposes a cluster of approaches to classify posed and spontaneous smiles using deep convolutional neural network face features, local phase quantization (LPQ), dense optical flow and histogram of gradient (HOG).
- 11
- Markerless video analysis for movement quantification in pediatric epilepsy monitoring11
A markerless video analytic system for quantifying body part movements in pediatric epilepsy monitoring that utilizes colored pajamas worn by a patient in bed to extract body part movement trajectories, from which various features can be obtained for seizure detection and analysis.
- 10
- Spontaneous Versus Posed Smiles—Can We Tell the Difference?10
This work aims to distinguish spontaneous (felt) smile expressions from posed (deliberate) smiles by extracting and analyzing both global motion of the face and subtle changes in the facial expression features through both tracking a series of facial fiducial markers as well as using dense optical flow.
- 9
- Recovering Social Interaction Spatial Structure from Multiple First-Person Views9
This work proposes a search-based structure recovery method in a small group conversational social interaction scenario to reconstruct the social interaction structure from multiple first-person views, where each of them contributes to the multifaceted understanding of thesocial interaction.
- MedHelp: enhancing medication compliance for demented elderly people with wearable visual intelligence8
A wearable system that provides personal assistance to enhance the independence and well-being of elderly people with dementia and an application called MedHelp was developed on Google Glass paired with a mobile phone to improve medication compliance.
- Design of AI-driven microwave imaging for lung tumor monitoring7
It is found that the XGBoost-based classifier with S-parameters outperforms the CNN-based classifier on reconstructed microwave images for tumor detection and a CNN-based model on reconstructed microwave images performs much better than a CNN-based model designed on the raw S-parameters for tumor size prediction.
- 7
- Cross-Spectral Periocular Recognition: A Survey7
Current state-of-the-art techniques in cross-spectral periocular recognition including various methodologies, databases, their protocols and current state of theart recognition performances are analyzed and reviewed.
- 6
- Storages Are Not Forever6
The main aim of this paper is to raise awareness on the storage limitation the authors are about to face if current technology is adopted and the storage utilization growth rate persists and to propose some storage solutions and a better utilization of storage capacity through a global DIKW hierarchy.
- Enhancing Social Interaction with Seamless Face Recognition on Google Glass6
Leveraging on the computing power of a connected mobile device, a new multi-threaded asynchronous structure is proposed to implement opportunistic multi-tasking and an application is demonstrated for seamless face recognition for social interactions.
- Vision and Memory: Looking Beyond Immediate Visual Perception5
This chapter explains how for real-world visual tasks, immediate visual perception is not sufficient, and it interacts with visual memory virtually all the time.
- 4
- StructureNet: Deep Context Attention Learning for Structural Component Recognition4
Tensor decomposition is used to design a context attention framework that acquires crucial information across various dimensions by fusing the class contexts and 3-D attention map.
- 3
- Improved Bayesian Approach for Face Recognition3
A new methodology for selecting the eigenvalues in the face subspace which can be used for measuring the residual reconstruction error in the partial Karhunen-Loeve transformation (KLT) for Bayesian face recognition is proposed.
- 2
- 2
- 2
- Deep Neural Network Based Attention Model for Structural Component Recognition1
This work proposes a novel deep neural network-based attention model (DNNAM) architecture, which comprises synchronous dual attention modules (SDAM) and residual modules to recognise structural components and shows that the proposed architecture outperforms current state-of-the-art methodologies for structural component recognition.
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- Feature regularization and extraction in eigenspace for face recognition–
This thesis proposes various algorithms which are based on statistical pattern recognition and computer vision for robust face recognition with high accuracy and study numerous holistic/appearance based face recognition methods among which, PCA, FDA, Bayesian maximum likelihood, NDA and their variations are the popular ones.
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 2026-10-12. 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.