Kha Gia Quach

Pha Nguyen, Kha Gia Quach, John Gauch et al.

Multiple Object Tracking (MOT) aims to find bounding boxes and identities of targeted objects in consecutive video frames. While fully-supervised MOT methods have achieved high accuracy on existing datasets, they cannot generalize well on a newly obtained dataset or a new unseen domain. In this work, we first address the MOT problem from the cross-domain point of view, imitating the process of new data acquisition in practice. Then, a new cross-domain MOT adaptation from existing datasets is proposed without any pre-defined human knowledge in understanding and modeling objects. It can also learn and update itself from the target data feedback. The intensive experiments are designed on four challenging settings, including MOTSynth to MOT17, MOT17 to MOT20, MOT17 to VisDrone, and MOT17 to DanceTrack. We then prove the adaptability of the proposed self-supervised learning strategy. The experiments also show superior performance on tracking metrics MOTA and IDF1, compared to fully supervised, unsupervised, and self-supervised state-of-the-art methods.

Pha Nguyen, Kha Gia Quach, Chi Nhan Duong et al.

The development of autonomous vehicles provides an opportunity to have a complete set of camera sensors capturing the environment around the car. Thus, it is important for object detection and tracking to address new challenges, such as achieving consistent results across views of cameras. To address these challenges, this work presents a new Global Association Graph Model with Link Prediction approach to predict existing tracklets location and link detections with tracklets via cross-attention motion modeling and appearance re-identification. This approach aims at solving issues caused by inconsistent 3D object detection. Moreover, our model exploits to improve the detection accuracy of a standard 3D object detector in the nuScenes detection challenge. The experimental results on the nuScenes dataset demonstrate the benefits of the proposed method to produce SOTA performance on the existing vision-based tracking dataset.

Pha Nguyen, Kha Gia Quach, Chi Nhan Duong et al.

The development of autonomous vehicles generates a tremendous demand for a low-cost solution with a complete set of camera sensors capturing the environment around the car. It is essential for object detection and tracking to address these new challenges in multi-camera settings. In order to address these challenges, this work introduces novel Single-Stage Global Association Tracking approaches to associate one or more detection from multi-cameras with tracked objects. These approaches aim to solve fragment-tracking issues caused by inconsistent 3D object detection. Moreover, our models also improve the detection accuracy of the standard vision-based 3D object detectors in the nuScenes detection challenge. The experimental results on the nuScenes dataset demonstrate the benefits of the proposed method by outperforming prior vision-based tracking methods in multi-camera settings.

Kha Gia Quach, Huu Le, Pha Nguyen et al.

This paper aims to tackle Multiple Object Tracking (MOT), an important problem in computer vision but remains challenging due to many practical issues, especially occlusions. Indeed, we propose a new real-time Depth Perspective-aware Multiple Object Tracking (DP-MOT) approach to tackle the occlusion problem in MOT. A simple yet efficient Subject-Ordered Depth Estimation (SODE) is first proposed to automatically order the depth positions of detected subjects in a 2D scene in an unsupervised manner. Using the output from SODE, a new Active pseudo-3D Kalman filter, a simple but effective extension of Kalman filter with dynamic control variables, is then proposed to dynamically update the movement of objects. In addition, a new high-order association approach is presented in the data association step to incorporate first-order and second-order relationships between the detected objects. The proposed approach consistently achieves state-of-the-art performance compared to recent MOT methods on standard MOT benchmarks.

Pha Nguyen, Kha Gia Quach, Kris Kitani et al.

One of the recent trends in vision problems is to use natural language captions to describe the objects of interest. This approach can overcome some limitations of traditional methods that rely on bounding boxes or category annotations. This paper introduces a novel paradigm for Multiple Object Tracking called Type-to-Track, which allows users to track objects in videos by typing natural language descriptions. We present a new dataset for that Grounded Multiple Object Tracking task, called GroOT, that contains videos with various types of objects and their corresponding textual captions describing their appearance and action in detail. Additionally, we introduce two new evaluation protocols and formulate evaluation metrics specifically for this task. We develop a new efficient method that models a transformer-based eMbed-ENcoDE-extRact framework (MENDER) using the third-order tensor decomposition. The experiments in five scenarios show that our MENDER approach outperforms another two-stage design in terms of accuracy and efficiency, up to 14.7% accuracy and 4$\times$ speed faster.

Kha Gia Quach, Pha Nguyen, Huu Le et al.

Multi-Camera Multiple Object Tracking (MC-MOT) is a significant computer vision problem due to its emerging applicability in several real-world applications. Despite a large number of existing works, solving the data association problem in any MC-MOT pipeline is arguably one of the most challenging tasks. Developing a robust MC-MOT system, however, is still highly challenging due to many practical issues such as inconsistent lighting conditions, varying object movement patterns, or the trajectory occlusions of the objects between the cameras. To address these problems, this work, therefore, proposes a new Dynamic Graph Model with Link Prediction (DyGLIP) approach to solve the data association task. Compared to existing methods, our new model offers several advantages, including better feature representations and the ability to recover from lost tracks during camera transitions. Moreover, our model works gracefully regardless of the overlapping ratios between the cameras. Experimental results show that we outperform existing MC-MOT algorithms by a large margin on several practical datasets. Notably, our model works favorably on online settings but can be extended to an incremental approach for large-scale datasets.

Ngan Le, Kashu Yamazaki, Dat Truong et al.

In recent years, deep neural networks have achieved state-of-the-art performance in a variety of recognition and segmentation tasks in medical imaging including brain tumor segmentation. We investigate that segmenting a brain tumor is facing to the imbalanced data problem where the number of pixels belonging to the background class (non tumor pixel) is much larger than the number of pixels belonging to the foreground class (tumor pixel). To address this problem, we propose a multi-task network which is formed as a cascaded structure. Our model consists of two targets, i.e., (i) effectively differentiate the brain tumor regions and (ii) estimate the brain tumor mask. The first objective is performed by our proposed contextual brain tumor detection network, which plays a role of an attention gate and focuses on the region around brain tumor only while ignoring the far neighbor background which is less correlated to the tumor. The second objective is built upon a 3D atrous residual network and under an encode-decode network in order to effectively segment both large and small objects (brain tumor). Our 3D atrous residual network is designed with a skip connection to enables the gradient from the deep layers to be directly propagated to shallow layers, thus, features of different depths are preserved and used for refining each other. In order to incorporate larger contextual information from volume MRI data, our network utilizes the 3D atrous convolution with various kernel sizes, which enlarges the receptive field of filters. Our proposed network has been evaluated on various datasets including BRATS2015, BRATS2017 and BRATS2018 datasets with both validation set and testing set. Our performance has been benchmarked by both region-based metrics and surface-based metrics. We also have conducted comparisons against state-of-the-art approaches.

Thanh-Dat Truong, Chi Nhan Duong, Kha Gia Quach et al.

Disentangled representations have been commonly adopted to Age-invariant Face Recognition (AiFR) tasks. However, these methods have reached some limitations with (1) the requirement of large-scale face recognition (FR) training data with age labels, which is limited in practice; (2) heavy deep network architectures for high performance; and (3) their evaluations are usually taken place on age-related face databases while neglecting the standard large-scale FR databases to guarantee robustness. This work presents a novel Lightweight Attentive Angular Distillation (LIAAD) approach to Large-scale Lightweight AiFR that overcomes these limitations. Given two high-performance heavy networks as teachers with different specialized knowledge, LIAAD introduces a learning paradigm to efficiently distill the age-invariant attentive and angular knowledge from those teachers to a lightweight student network making it more powerful with higher FR accuracy and robust against age factor. Consequently, LIAAD approach is able to take the advantages of both FR datasets with and without age labels to train an AiFR model. Far apart from prior distillation methods mainly focusing on accuracy and compression ratios in closed-set problems, our LIAAD aims to solve the open-set problem, i.e. large-scale face recognition. Evaluations on LFW, IJB-B and IJB-C Janus, AgeDB and MegaFace-FGNet with one million distractors have demonstrated the efficiency of the proposed approach on light-weight structure. This work also presents a new longitudinal face aging (LogiFace) database \footnote{This database will be made available} for further studies in age-related facial problems in future.

Chi Nhan Duong, Thanh-Dat Truong, Kha Gia Quach et al.

Unveiling face images of a subject given his/her high-level representations extracted from a blackbox Face Recognition engine is extremely challenging. It is because the limitations of accessible information from that engine including its structure and uninterpretable extracted features. This paper presents a novel generative structure with Bijective Metric Learning, namely Bijective Generative Adversarial Networks in a Distillation framework (DiBiGAN), for synthesizing faces of an identity given that person's features. In order to effectively address this problem, this work firstly introduces a bijective metric so that the distance measurement and metric learning process can be directly adopted in image domain for an image reconstruction task. Secondly, a distillation process is introduced to maximize the information exploited from the blackbox face recognition engine. Then a Feature-Conditional Generator Structure with Exponential Weighting Strategy is presented for a more robust generator that can synthesize realistic faces with ID preservation. Results on several benchmarking datasets including CelebA, LFW, AgeDB, CFP-FP against matching engines have demonstrated the effectiveness of DiBiGAN on both image realism and ID preservation properties.

Chi Nhan Duong, Khoa Luu, Kha Gia Quach et al.

Large-scale face recognition in-the-wild has been recently achieved matured performance in many real work applications. However, such systems are built on GPU platforms and mostly deploy heavy deep network architectures. Given a high-performance heavy network as a teacher, this work presents a simple and elegant teacher-student learning paradigm, namely ShrinkTeaNet, to train a portable student network that has significantly fewer parameters and competitive accuracy against the teacher network. Far apart from prior teacher-student frameworks mainly focusing on accuracy and compression ratios in closed-set problems, our proposed teacher-student network is proved to be more robust against open-set problem, i.e. large-scale face recognition. In addition, this work introduces a novel Angular Distillation Loss for distilling the feature direction and the sample distributions of the teacher's hypersphere to its student. Then ShrinkTeaNet framework can efficiently guide the student's learning process with the teacher's knowledge presented in both intermediate and last stages of the feature embedding. Evaluations on LFW, CFP-FP, AgeDB, IJB-B and IJB-C Janus, and MegaFace with one million distractors have demonstrated the efficiency of the proposed approach to learn robust student networks which have satisfying accuracy and compact sizes. Our ShrinkTeaNet is able to support the light-weight architecture achieving high performance with 99.77% on LFW and 95.64% on large-scale Megaface protocols.

Kha Gia Quach, Ngan Le, Chi Nhan Duong et al.

Group-level emotion recognition (ER) is a growing research area as the demands for assessing crowds of all sizes are becoming an interest in both the security arena as well as social media. This work extends the earlier ER investigations, which focused on either group-level ER on single images or within a video, by fully investigating group-level expression recognition on crowd videos. In this paper, we propose an effective deep feature level fusion mechanism to model the spatial-temporal information in the crowd videos. In our approach, the fusing process is performed on the deep feature domain by a generative probabilistic model, Non-Volume Preserving Fusion (NVPF), that models spatial information relationships. Furthermore, we extend our proposed spatial NVPF approach to the spatial-temporal NVPF approach to learn the temporal information between frames. To demonstrate the robustness and effectiveness of each component in the proposed approach, three experiments were conducted: (i) evaluation on AffectNet database to benchmark the proposed EmoNet for recognizing facial expression; (ii) evaluation on EmotiW2018 to benchmark the proposed deep feature level fusion mechanism NVPF; and, (iii) examine the proposed TNVPF on an innovative Group-level Emotion on Crowd Videos (GECV) dataset composed of 627 videos collected from publicly available sources. GECV dataset is a collection of videos containing crowds of people. Each video is labeled with emotion categories at three levels: individual faces, group of people, and the entire video frame.

Chi Nhan Duong, Khoa Luu, Kha Gia Quach et al.

This paper presents a novel approach to synthesize automatically age-progressed facial images in video sequences using Deep Reinforcement Learning. The proposed method models facial structures and the longitudinal face-aging process of given subjects coherently across video frames. The approach is optimized using a long-term reward, Reinforcement Learning function with deep feature extraction from Deep Convolutional Neural Network. Unlike previous age-progression methods that are only able to synthesize an aged likeness of a face from a single input image, the proposed approach is capable of age-progressing facial likenesses in videos with consistently synthesized facial features across frames. In addition, the deep reinforcement learning method guarantees preservation of the visual identity of input faces after age-progression. Results on videos of our new collected aging face AGFW-v2 database demonstrate the advantages of the proposed solution in terms of both quality of age-progressed faces, temporal smoothness, and cross-age face verification.

Chi Nhan Duong, Kha Gia Quach, Ibsa Jalata et al.

Deep neural networks have been widely used in numerous computer vision applications, particularly in face recognition. However, deploying deep neural network face recognition on mobile devices has recently become a trend but still limited since most high-accuracy deep models are both time and GPU consumption in the inference stage. Therefore, developing a lightweight deep neural network is one of the most practical solutions to deploy face recognition on mobile devices. Such the lightweight deep neural network requires efficient memory with small number of weights representation and low cost operators. In this paper, a novel deep neural network named MobiFace, a simple but effective approach, is proposed for productively deploying face recognition on mobile devices. The experimental results have shown that our lightweight MobiFace is able to achieve high performance with 99.73% on LFW database and 91.3% on large-scale challenging Megaface database. It is also eventually competitive against large-scale deep-networks face recognition while significant reducing computational time and memory consumption.

Chi Nhan Duong, Khoa Luu, Kha Gia Quach et al.

Face Aging has raised considerable attentions and interest from the computer vision community in recent years. Numerous approaches ranging from purely image processing techniques to deep learning structures have been proposed in literature. In this paper, we aim to give a review of recent developments of modern deep learning based approaches, i.e. Deep Generative Models, for Face Aging task. Their structures, formulation, learning algorithms as well as synthesized results are also provided with systematic discussions. Moreover, the aging databases used in most methods to learn the aging process are also reviewed.

Chi Nhan Duong, Kha Gia Quach, Khoa Luu et al.

This paper presents a novel Subject-dependent Deep Aging Path (SDAP), which inherits the merits of both Generative Probabilistic Modeling and Inverse Reinforcement Learning to model the facial structures and the longitudinal face aging process of a given subject. The proposed SDAP is optimized using tractable log-likelihood objective functions with Convolutional Neural Networks (CNNs) based deep feature extraction. Instead of applying a fixed aging development path for all input faces and subjects, SDAP is able to provide the most appropriate aging development path for individual subject that optimizes the reward aging formulation. Unlike previous methods that can take only one image as the input, SDAP further allows multiple images as inputs, i.e. all information of a subject at either the same or different ages, to produce the optimal aging path for the given subject. Finally, SDAP allows efficiently synthesizing in-the-wild aging faces. The proposed model is experimented in both tasks of face aging synthesis and cross-age face verification. The experimental results consistently show SDAP achieves the state-of-the-art performance on numerous face aging databases, i.e. FG-NET, MORPH, AginG Faces in the Wild (AGFW), and Cross-Age Celebrity Dataset (CACD). Furthermore, we also evaluate the performance of SDAP on large-scale Megaface challenge to demonstrate the advantages of the proposed solution.

Ngan Le, Kha Gia Quach, Khoa Luu et al.

Variational Level Set (LS) has been a widely used method in medical segmentation. However, it is limited when dealing with multi-instance objects in the real world. In addition, its segmentation results are quite sensitive to initial settings and highly depend on the number of iterations. To address these issues and boost the classic variational LS methods to a new level of the learnable deep learning approaches, we propose a novel definition of contour evolution named Recurrent Level Set (RLS)} to employ Gated Recurrent Unit under the energy minimization of a variational LS functional. The curve deformation process in RLS is formed as a hidden state evolution procedure and updated by minimizing an energy functional composed of fitting forces and contour length. By sharing the convolutional features in a fully end-to-end trainable framework, we extend RLS to Contextual RLS (CRLS) to address semantic segmentation in the wild. The experimental results have shown that our proposed RLS improves both computational time and segmentation accuracy against the classic variations LS-based method, whereas the fully end-to-end system CRLS achieves competitive performance compared to the state-of-the-art semantic segmentation approaches.

Chi Nhan Duong, Kha Gia Quach, Khoa Luu et al.

Modeling the long-term facial aging process is extremely challenging due to the presence of large and non-linear variations during the face development stages. In order to efficiently address the problem, this work first decomposes the aging process into multiple short-term stages. Then, a novel generative probabilistic model, named Temporal Non-Volume Preserving (TNVP) transformation, is presented to model the facial aging process at each stage. Unlike Generative Adversarial Networks (GANs), which requires an empirical balance threshold, and Restricted Boltzmann Machines (RBM), an intractable model, our proposed TNVP approach guarantees a tractable density function, exact inference and evaluation for embedding the feature transformations between faces in consecutive stages. Our model shows its advantages not only in capturing the non-linear age related variance in each stage but also producing a smooth synthesis in age progression across faces. Our approach can model any face in the wild provided with only four basic landmark points. Moreover, the structure can be transformed into a deep convolutional network while keeping the advantages of probabilistic models with tractable log-likelihood density estimation. Our method is evaluated in both terms of synthesizing age-progressed faces and cross-age face verification and consistently shows the state-of-the-art results in various face aging databases, i.e. FG-NET, MORPH, AginG Faces in the Wild (AGFW), and Cross-Age Celebrity Dataset (CACD). A large-scale face verification on Megaface challenge 1 is also performed to further show the advantages of our proposed approach.

Chi Nhan Duong, Khoa Luu, Kha Gia Quach et al.

The "interpretation through synthesis" approach to analyze face images, particularly Active Appearance Models (AAMs) method, has become one of the most successful face modeling approaches over the last two decades. AAM models have ability to represent face images through synthesis using a controllable parameterized Principal Component Analysis (PCA) model. However, the accuracy and robustness of the synthesized faces of AAM are highly depended on the training sets and inherently on the generalizability of PCA subspaces. This paper presents a novel Deep Appearance Models (DAMs) approach, an efficient replacement for AAMs, to accurately capture both shape and texture of face images under large variations. In this approach, three crucial components represented in hierarchical layers are modeled using the Deep Boltzmann Machines (DBM) to robustly capture the variations of facial shapes and appearances. DAMs are therefore superior to AAMs in inferencing a representation for new face images under various challenging conditions. The proposed approach is evaluated in various applications to demonstrate its robustness and capabilities, i.e. facial super-resolution reconstruction, facial off-angle reconstruction or face frontalization, facial occlusion removal and age estimation using challenging face databases, i.e. Labeled Face Parts in the Wild (LFPW), Helen and FG-NET. Comparing to AAMs and other deep learning based approaches, the proposed DAMs achieve competitive results in those applications, thus this showed their advantages in handling occlusions, facial representation, and reconstruction.

Kha Gia Quach, Chi Nhan Duong, Khoa Luu et al.

This paper presents a novel Robust Deep Appearance Models to learn the non-linear correlation between shape and texture of face images. In this approach, two crucial components of face images, i.e. shape and texture, are represented by Deep Boltzmann Machines and Robust Deep Boltzmann Machines (RDBM), respectively. The RDBM, an alternative form of Robust Boltzmann Machines, can separate corrupted/occluded pixels in the texture modeling to achieve better reconstruction results. The two models are connected by Restricted Boltzmann Machines at the top layer to jointly learn and capture the variations of both facial shapes and appearances. This paper also introduces new fitting algorithms with occlusion awareness through the mask obtained from the RDBM reconstruction. The proposed approach is evaluated in various applications by using challenging face datasets, i.e. Labeled Face Parts in the Wild (LFPW), Helen, EURECOM and AR databases, to demonstrate its robustness and capabilities.

Chi Nhan Duong, Khoa Luu, Kha Gia Quach et al.

Modeling the face aging process is a challenging task due to large and non-linear variations present in different stages of face development. This paper presents a deep model approach for face age progression that can efficiently capture the non-linear aging process and automatically synthesize a series of age-progressed faces in various age ranges. In this approach, we first decompose the long-term age progress into a sequence of short-term changes and model it as a face sequence. The Temporal Deep Restricted Boltzmann Machines based age progression model together with the prototype faces are then constructed to learn the aging transformation between faces in the sequence. In addition, to enhance the wrinkles of faces in the later age ranges, the wrinkle models are further constructed using Restricted Boltzmann Machines to capture their variations in different facial regions. The geometry constraints are also taken into account in the last step for more consistent age-progressed results. The proposed approach is evaluated using various face aging databases, i.e. FG-NET, Cross-Age Celebrity Dataset (CACD) and MORPH, and our collected large-scale aging database named AginG Faces in the Wild (AGFW). In addition, when ground-truth age is not available for input image, our proposed system is able to automatically estimate the age of the input face before aging process is employed.