Searcharxiv⌕ Search

arXiv subjects

Zitong Yu

Publications and source records attributed to Zitong Yu.

At least 163 records · Page 9Linked to original sources

PhysFormer: Facial Video-based Physiological Measurement with Temporal Difference Transformer

Remote photoplethysmography (rPPG), which aims at measuring heart activities and physiological signals from facial video without any contact, has great potential in many applications (e.g., remote healthcare and affective computing). Recent deep learning approaches focus on mining subtle rPPG clues using convolutional neural networks with limited spatio-temporal receptive fields, which neglect the long-range spatio-temporal perception and interaction for rPPG modeling. In this paper, we propose the PhysFormer, an end-to-end video transformer based architecture, to adaptively aggregate both local and global spatio-temporal features for rPPG representation enhancement. As key modules in PhysFormer, the temporal difference transformers first enhance the quasi-periodic rPPG features with temporal difference guided global attention, and then refine the local spatio-temporal representation against interference. Furthermore, we also propose the label distribution learning and a curriculum learning inspired dynamic constraint in frequency domain, which provide elaborate supervisions for PhysFormer and alleviate overfitting. Comprehensive experiments are performed on four benchmark datasets to show our superior performance on both intra- and cross-dataset testings. One highlight is that, unlike most transformer networks needed pretraining from large-scale datasets, the proposed PhysFormer can be easily trained from scratch on rPPG datasets, which makes it promising as a novel transformer baseline for the rPPG community. The codes will be released at https://github.com/ZitongYu/PhysFormer.

cs.CV↗

Domain Generalization via Shuffled Style Assembly for Face Anti-Spoofing

With diverse presentation attacks emerging continually, generalizable face anti-spoofing (FAS) has drawn growing attention. Most existing methods implement domain generalization (DG) on the complete representations. However, different image statistics may have unique properties for the FAS tasks. In this work, we separate the complete representation into content and style ones. A novel Shuffled Style Assembly Network (SSAN) is proposed to extract and reassemble different content and style features for a stylized feature space. Then, to obtain a generalized representation, a contrastive learning strategy is developed to emphasize liveness-related style information while suppress the domain-specific one. Finally, the representations of the correct assemblies are used to distinguish between living and spoofing during the inferring. On the other hand, despite the decent performance, there still exists a gap between academia and industry, due to the difference in data quantity and distribution. Thus, a new large-scale benchmark for FAS is built up to further evaluate the performance of algorithms in reality. Both qualitative and quantitative results on existing and proposed benchmarks demonstrate the effectiveness of our methods. The codes will be available at https://github.com/wangzhuo2019/SSAN.

cs.CV↗

ViTransPAD: Video Transformer using convolution and self-attention for Face Presentation Attack Detection

Face Presentation Attack Detection (PAD) is an important measure to prevent spoof attacks for face biometric systems. Many works based on Convolution Neural Networks (CNNs) for face PAD formulate the problem as an image-level binary classification task without considering the context. Alternatively, Vision Transformers (ViT) using self-attention to attend the context of an image become the mainstreams in face PAD. Inspired by ViT, we propose a Video-based Transformer for face PAD (ViTransPAD) with short/long-range spatio-temporal attention which can not only focus on local details with short attention within a frame but also capture long-range dependencies over frames. Instead of using coarse image patches with single-scale as in ViT, we propose the Multi-scale Multi-Head Self-Attention (MsMHSA) architecture to accommodate multi-scale patch partitions of Q, K, V feature maps to the heads of transformer in a coarse-to-fine manner, which enables to learn a fine-grained representation to perform pixel-level discrimination for face PAD. Due to lack inductive biases of convolutions in pure transformers, we also introduce convolutions to the proposed ViTransPAD to integrate the desirable properties of CNNs by using convolution patch embedding and convolution projection. The extensive experiments show the effectiveness of our proposed ViTransPAD with a preferable accuracy-computation balance, which can serve as a new backbone for face PAD.

cs.CV↗

Ideal-observer computation with anthropomorphic phantoms using Markov Chain Monte Carlo

In medical imaging, it is widely recognized that image quality should be objectively evaluated based on performance in clinical tasks. To evaluate performance in signal-detection tasks, the ideal observer (IO) is optimal but also challenging to compute in clinically realistic settings. Markov Chain Monte Carlo (MCMC)-based strategies have demonstrated the ability to compute the IO using pre-computed projections of an anatomical database. To evaluate image quality in clinically realistic scenarios, the observer performance should be measured for realistic patient distribution. This implies that the anatomical database should also be derived from a realistic population. In this manuscript, we propose to advance the MCMC-based approach to achieve these goals. We then use the proposed approach to study the effect of anatomical database size on IO computation for the task of detecting perfusion defects in simulated myocardial perfusion SPECT images. Our preliminary results provide evidence that the size of the anatomical database affects the computation of IO.

physics.med-ph↗

Investigating the limited performance of a deep-learning-based SPECT denoising approach: An observer-study-based characterization

Multiple objective assessment of image-quality-based studies have reported that several deep-learning-based denoising methods show limited performance on signal-detection tasks. Our goal was to investigate the reasons for this limited performance. To achieve this goal, we conducted a task-based characterization of a DL-based denoising approach for individual signal properties. We conducted this study in the context of evaluating a DL-based approach for denoising SPECT images. The training data consisted of signals of different sizes and shapes within a clustered-lumpy background, imaged with a 2D parallel-hole-collimator SPECT system. The projections were generated at normal and 20% low count level, both of which were reconstructed using an OSEM algorithm. A CNN-based denoiser was trained to process the low-count images. The performance of this CNN was characterized for five different signal sizes and four different SBR by designing each evaluation as an SKE/BKS signal-detection task. Performance on this task was evaluated using an anthropomorphic CHO. As in previous studies, we observed that the DL-based denoising method did not improve performance on signal-detection tasks. Evaluation using the idea of observer-study-based characterization demonstrated that the DL-based denoising approach did not improve performance on the signal-detection task for any of the signal types. Overall, these results provide new insights on the performance of the DL-based denoising approach as a function of signal size and contrast. More generally, the observer study-based characterization provides a mechanism to evaluate the sensitivity of the method to specific object properties and may be explored as analogous to characterizations such as modulation transfer function for linear systems. Finally, this work underscores the need for objective task-based evaluation of DL-based denoising approaches.

physics.med-ph↗

Non-contact Pain Recognition from Video Sequences with Remote Physiological Measurements Prediction

Automatic pain recognition is paramount for medical diagnosis and treatment. The existing works fall into three categories: assessing facial appearance changes, exploiting physiological cues, or fusing them in a multi-modal manner. However, (1) appearance changes are easily affected by subjective factors which impedes objective pain recognition. Besides, the appearance-based approaches ignore long-range spatial-temporal dependencies that are important for modeling expressions over time; (2) the physiological cues are obtained by attaching sensors on human body, which is inconvenient and uncomfortable. In this paper, we present a novel multi-task learning framework which encodes both appearance changes and physiological cues in a non-contact manner for pain recognition. The framework is able to capture both local and long-range dependencies via the proposed attention mechanism for the learned appearance representations, which are further enriched by temporally attended physiological cues (remote photoplethysmography, rPPG) that are recovered from videos in the auxiliary task. This framework is dubbed rPPG-enriched Spatio-Temporal Attention Network (rSTAN) and allows us to establish the state-of-the-art performance of non-contact pain recognition on publicly available pain databases. It demonstrates that rPPG predictions can be used as an auxiliary task to facilitate non-contact automatic pain recognition.

cs.CV↗

Review of Face Presentation Attack Detection Competitions

Face presentation attack detection (PAD) has received increasing attention ever since the vulnerabilities to spoofing have been widely recognized. The state of the art in unimodal and multi-modal face anti-spoofing has been assessed in eight international competitions organized in conjunction with major biometrics and computer vision conferences in 2011, 2013, 2017, 2019, 2020 and 2021, each introducing new challenges to the research community. In this chapter, we present the design and results of the five latest competitions from 2019 until 2021. The first two challenges aimed to evaluate the effectiveness of face PAD in multi-modal setup introducing near-infrared (NIR) and depth modalities in addition to colour camera data, while the latest three competitions focused on evaluating domain and attack type generalization abilities of face PAD algorithms operating on conventional colour images and videos. We also discuss the lessons learnt from the competitions and future challenges in the field in general.

cs.CV↗

Geometry-Contrastive Transformer for Generalized 3D Pose Transfer

We present a customized 3D mesh Transformer model for the pose transfer task. As the 3D pose transfer essentially is a deformation procedure dependent on the given meshes, the intuition of this work is to perceive the geometric inconsistency between the given meshes with the powerful self-attention mechanism. Specifically, we propose a novel geometry-contrastive Transformer that has an efficient 3D structured perceiving ability to the global geometric inconsistencies across the given meshes. Moreover, locally, a simple yet efficient central geodesic contrastive loss is further proposed to improve the regional geometric-inconsistency learning. At last, we present a latent isometric regularization module together with a novel semi-synthesized dataset for the cross-dataset 3D pose transfer task towards unknown spaces. The massive experimental results prove the efficacy of our approach by showing state-of-the-art quantitative performances on SMPL-NPT, FAUST and our new proposed dataset SMG-3D datasets, as well as promising qualitative results on MG-cloth and SMAL datasets. It's demonstrated that our method can achieve robust 3D pose transfer and be generalized to challenging meshes from unknown spaces on cross-dataset tasks. The code and dataset are made available. Code is available: https://github.com/mikecheninoulu/CGT.

cs.CV↗

Consistency Regularization for Deep Face Anti-Spoofing

Face anti-spoofing (FAS) plays a crucial role in securing face recognition systems. Empirically, given an image, a model with more consistent output on different views of this image usually performs better, as shown in Fig.1. Motivated by this exciting observation, we conjecture that encouraging feature consistency of different views may be a promising way to boost FAS models. In this paper, we explore this way thoroughly by enhancing both Embedding-level and Prediction-level Consistency Regularization (EPCR) in FAS. Specifically, at the embedding-level, we design a dense similarity loss to maximize the similarities between all positions of two intermediate feature maps in a self-supervised fashion; while at the prediction-level, we optimize the mean square error between the predictions of two views. Notably, our EPCR is free of annotations and can directly integrate into semi-supervised learning schemes. Considering different application scenarios, we further design five diverse semi-supervised protocols to measure semi-supervised FAS techniques. We conduct extensive experiments to show that EPCR can significantly improve the performance of several supervised and semi-supervised tasks on benchmark datasets. The codes and protocols will be released at https://github.com/clks-wzz/EPCR.

cs.CV↗

Meta-Teacher For Face Anti-Spoofing

Face anti-spoofing (FAS) secures face recognition from presentation attacks (PAs). Existing FAS methods usually supervise PA detectors with handcrafted binary or pixel-wise labels. However, handcrafted labels may are not the most adequate way to supervise PA detectors learning sufficient and intrinsic spoofing cues. Instead of using the handcrafted labels, we propose a novel Meta-Teacher FAS (MT-FAS) method to train a meta-teacher for supervising PA detectors more effectively. The meta-teacher is trained in a bi-level optimization manner to learn the ability to supervise the PA detectors learning rich spoofing cues. The bi-level optimization contains two key components: 1) a lower-level training in which the meta-teacher supervises the detector's learning process on the training set; and 2) a higher-level training in which the meta-teacher's teaching performance is optimized by minimizing the detector's validation loss. Our meta-teacher differs significantly from existing teacher-student models because the meta-teacher is explicitly trained for better teaching the detector (student), whereas existing teachers are trained for outstanding accuracy neglecting teaching ability. Extensive experiments on five FAS benchmarks show that with the proposed MT-FAS, the trained meta-teacher 1) provides better-suited supervision than both handcrafted labels and existing teacher-student models; and 2) significantly improves the performances of PA detectors.

cs.CV↗

3D High-Fidelity Mask Face Presentation Attack Detection Challenge

The threat of 3D masks to face recognition systems is increasingly serious and has been widely concerned by researchers. To facilitate the study of the algorithms, a large-scale High-Fidelity Mask dataset, namely CASIA-SURF HiFiMask (briefly HiFiMask) has been collected. Specifically, it consists of a total amount of 54, 600 videos which are recorded from 75 subjects with 225 realistic masks under 7 new kinds of sensors. Based on this dataset and Protocol 3 which evaluates both the discrimination and generalization ability of the algorithm under the open set scenarios, we organized a 3D High-Fidelity Mask Face Presentation Attack Detection Challenge to boost the research of 3D mask-based attack detection. It attracted 195 teams for the development phase with a total of 18 teams qualifying for the final round. All the results were verified and re-run by the organizing team, and the results were used for the final ranking. This paper presents an overview of the challenge, including the introduction of the dataset used, the definition of the protocol, the calculation of the evaluation criteria, and the summary and publication of the competition results. Finally, we focus on introducing and analyzing the top ranking algorithms, the conclusion summary, and the research ideas for mask attack detection provided by this competition.

cs.CV↗

Pixel Difference Networks for Efficient Edge Detection

Recently, deep Convolutional Neural Networks (CNNs) can achieve human-level performance in edge detection with the rich and abstract edge representation capacities. However, the high performance of CNN based edge detection is achieved with a large pretrained CNN backbone, which is memory and energy consuming. In addition, it is surprising that the previous wisdom from the traditional edge detectors, such as Canny, Sobel, and LBP are rarely investigated in the rapid-developing deep learning era. To address these issues, we propose a simple, lightweight yet effective architecture named Pixel Difference Network (PiDiNet) for efficient edge detection. Extensive experiments on BSDS500, NYUD, and Multicue are provided to demonstrate its effectiveness, and its high training and inference efficiency. Surprisingly, when training from scratch with only the BSDS500 and VOC datasets, PiDiNet can surpass the recorded result of human perception (0.807 vs. 0.803 in ODS F-measure) on the BSDS500 dataset with 100 FPS and less than 1M parameters. A faster version of PiDiNet with less than 0.1M parameters can still achieve comparable performance among state of the arts with 200 FPS. Results on the NYUD and Multicue datasets show similar observations. The codes are available at https://github.com/zhuoinoulu/pidinet.

cs.CV↗

Confining photonic nanojet in a microwell on microsphere lens for highly efficient light focusing, signal amplification and quantitative detection

Dielectric microspheres or microbeads can squeeze light into the subwavelength scale via photonic nanojet (PNJ) focusing. This enables strong light-matter interactions within its focus and induces extraordinary effects such as enhancements in light emission, signal collection and various other applications. However, critical challenges exist on how to efficiently and precisely loading the studied objects into the desired location of the PNJ focusing, and subsequently measure the field and signal of interests precisely and reliably. Such technique is currently missing. We present for the first time a unique microwell-decorated microsphere lens (u-well lens), with a semi-open microwell sample compartment directly fabricated on top of the microsphere lens. The u-well lens confines PNJ in a semi-open microwell and allows passive trapping of individual micro-object into the PNJ focusing area with high efficiency and spatial accuracy. We demonstrate that individual fluorescent microsphere of different sizes can be readily introduced to the designated location with loading efficiency >70% and generates reproducible enhanced fluorescence signals with standard deviation better than that can be quantitatively measured. A comprehensive analysis on the optical properties of the u-well lens reveals the synergistic effect of field enhancement and collection efficiency on the optical enhancement. We finally employ this special microsphere lens for fluorescent-bead-based biotin concentration analysis. The results suggest a greatly enhanced sensitivity and highly improved detection limit, opening the door for its application in highly sensitive and quantitative detection.

physics.optics↗

iMiGUE: An Identity-free Video Dataset for Micro-Gesture Understanding and Emotion Analysis

We introduce a new dataset for the emotional artificial intelligence research: identity-free video dataset for Micro-Gesture Understanding and Emotion analysis (iMiGUE). Different from existing public datasets, iMiGUE focuses on nonverbal body gestures without using any identity information, while the predominant researches of emotion analysis concern sensitive biometric data, like face and speech. Most importantly, iMiGUE focuses on micro-gestures, i.e., unintentional behaviors driven by inner feelings, which are different from ordinary scope of gestures from other gesture datasets which are mostly intentionally performed for illustrative purposes. Furthermore, iMiGUE is designed to evaluate the ability of models to analyze the emotional states by integrating information of recognized micro-gesture, rather than just recognizing prototypes in the sequences separately (or isolatedly). This is because the real need for emotion AI is to understand the emotional states behind gestures in a holistic way. Moreover, to counter for the challenge of imbalanced sample distribution of this dataset, an unsupervised learning method is proposed to capture latent representations from the micro-gesture sequences themselves. We systematically investigate representative methods on this dataset, and comprehensive experimental results reveal several interesting insights from the iMiGUE, e.g., micro-gesture-based analysis can promote emotion understanding. We confirm that the new iMiGUE dataset could advance studies of micro-gesture and emotion AI.

cs.CV↗

Dual-Cross Central Difference Network for Face Anti-Spoofing

Face anti-spoofing (FAS) plays a vital role in securing face recognition systems. Recently, central difference convolution (CDC) has shown its excellent representation capacity for the FAS task via leveraging local gradient features. However, aggregating central difference clues from all neighbors/directions simultaneously makes the CDC redundant and sub-optimized in the training phase. In this paper, we propose two Cross Central Difference Convolutions (C-CDC), which exploit the difference of the center and surround sparse local features from the horizontal/vertical and diagonal directions, respectively. It is interesting to find that, with only five ninth parameters and less computational cost, C-CDC even outperforms the full directional CDC. Based on these two decoupled C-CDC, a powerful Dual-Cross Central Difference Network (DC-CDN) is established with Cross Feature Interaction Modules (CFIM) for mutual relation mining and local detailed representation enhancement. Furthermore, a novel Patch Exchange (PE) augmentation strategy for FAS is proposed via simply exchanging the face patches as well as their dense labels from random samples. Thus, the augmented samples contain richer live/spoof patterns and diverse domain distributions, which benefits the intrinsic and robust feature learning. Comprehensive experiments are performed on four benchmark datasets with three testing protocols to demonstrate our state-of-the-art performance.

cs.CV↗

TransRPPG: Remote Photoplethysmography Transformer for 3D Mask Face Presentation Attack Detection

3D mask face presentation attack detection (PAD) plays a vital role in securing face recognition systems from emergent 3D mask attacks. Recently, remote photoplethysmography (rPPG) has been developed as an intrinsic liveness clue for 3D mask PAD without relying on the mask appearance. However, the rPPG features for 3D mask PAD are still needed expert knowledge to design manually, which limits its further progress in the deep learning and big data era. In this letter, we propose a pure rPPG transformer (TransRPPG) framework for learning intrinsic liveness representation efficiently. At first, rPPG-based multi-scale spatial-temporal maps (MSTmap) are constructed from facial skin and background regions. Then the transformer fully mines the global relationship within MSTmaps for liveness representation, and gives a binary prediction for 3D mask detection. Comprehensive experiments are conducted on two benchmark datasets to demonstrate the efficacy of the TransRPPG on both intra- and cross-dataset testings. Our TransRPPG is lightweight and efficient (with only 547K parameters and 763M FLOPs), which is promising for mobile-level applications.

cs.CV↗

Contrastive Context-Aware Learning for 3D High-Fidelity Mask Face Presentation Attack Detection

Face presentation attack detection (PAD) is essential to secure face recognition systems primarily from high-fidelity mask attacks. Most existing 3D mask PAD benchmarks suffer from several drawbacks: 1) a limited number of mask identities, types of sensors, and a total number of videos; 2) low-fidelity quality of facial masks. Basic deep models and remote photoplethysmography (rPPG) methods achieved acceptable performance on these benchmarks but still far from the needs of practical scenarios. To bridge the gap to real-world applications, we introduce a largescale High-Fidelity Mask dataset, namely CASIA-SURF HiFiMask (briefly HiFiMask). Specifically, a total amount of 54,600 videos are recorded from 75 subjects with 225 realistic masks by 7 new kinds of sensors. Together with the dataset, we propose a novel Contrastive Context-aware Learning framework, namely CCL. CCL is a new training methodology for supervised PAD tasks, which is able to learn by leveraging rich contexts accurately (e.g., subjects, mask material and lighting) among pairs of live faces and high-fidelity mask attacks. Extensive experimental evaluations on HiFiMask and three additional 3D mask datasets demonstrate the effectiveness of our method.

cs.CV↗

A physics and learning-based transmission-less attenuation compensation method for SPECT

Attenuation compensation (AC) is a pre-requisite for reliable quantification and beneficial for visual interpretation tasks in single-photon emission computed tomography (SPECT). Typical AC methods require the availability of an attenuation map obtained using a transmission scan, such as a CT scan. This has several disadvantages such as increased radiation dose, higher costs, and possible misalignment between SPECT and CT scans. Also, often a CT scan is unavailable. In this context, we and others are showing that scattered photons in SPECT contain information to estimate the attenuation distribution. To exploit this observation, we propose a physics and learning-based method that uses the SPECT emission data in the photopeak and scatter windows to perform transmission-less AC in SPECT. The proposed method uses data acquired in the scatter window to reconstruct an initial estimate of the attenuation map using a physics-based approach. A convolutional neural network is then trained to segment this initial estimate into different regions. Pre-defined attenuation coefficients are assigned to these regions, yielding the reconstructed attenuation map, which is then used to reconstruct the activity map using an ordered subsets expectation maximization-based reconstruction approach. We objectively evaluated the performance of this method using a highly realistic simulation study conducted on the clinically relevant task of detecting perfusion defects in myocardial perfusion SPECT. Our results showed no statistically significant differences between the performance achieved using the proposed method and that with the true attenuation maps. Visually, the images reconstructed using the proposed method looked similar to those with the true attenuation map. Overall, these results provide evidence of the capability of the proposed method to perform transmission-less AC and motivate further evaluation.

physics.med-ph↗