arXiv subjects

Yang Zhao

Publications and source records attributed to Yang Zhao.

At least 325 records · Page 18Linked to original sources

arXiv2022

Improving End-to-End Text Image Translation From the Auxiliary Text Translation Task

End-to-end text image translation (TIT), which aims at translating the source language embedded in images to the target language, has attracted intensive attention in recent research. However, data sparsity limits the performance of end-to-end text image translation. Multi-task learning is a non-trivial way to alleviate this problem via exploring knowledge from complementary related tasks. In this paper, we propose a novel text translation enhanced text image translation, which trains the end-to-end model with text translation as an auxiliary task. By sharing model parameters and multi-task training, our model is able to take full advantage of easily-available large-scale text parallel corpus. Extensive experimental results show our proposed method outperforms existing end-to-end methods, and the joint multi-task learning with both text translation and recognition tasks achieves better results, proving translation and recognition auxiliary tasks are complementary.

cs.CL↗

arXiv2022

Understanding the Spatiotemporal Resolution of Near-Field Photoacoustics from Nanostructures

Understanding the mechanism of photoacoustic generation at the nano-scale is key to developing more efficient photoacoustic devices and agents. Unlike the far-field photoacoustic effect that has been well employed in imaging, the near-field profile leads to a complex wave-tissue interaction but is under-studied. Here we show that the spatiotemporal profile of the near-field photoacoustic waves can be shaped by laser pulses, anisotropy, and nanoparticle(s) spatial arrangement. Using a gold nanorod as an example, we discovered that the near-field photoacoustic amplitude in the short axis is ~75% stronger than the long axis, and the anisotropic spatial distribution converges to an isotropic spherical wave at ~50 nm away from the nanorod's surface. We further extend the model to asymmetric gold nanostructures by arranging isotropic nanospheres anisotropically with broken symmetry to achieve a precisely controlled near-field photoacoustic "focus" largely within an acoustic wavelength.

physics.bio-ph↗

arXiv2022

Joint Optimization of STAR-RIS Assisted UAV Communication Systems

In this letter, we study the simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) assisted unmanned aerial vehicle (UAV) communications. Our goal is to maximize the sum rate of all users by jointly optimizing the STAR-RIS's beamforming vectors, the UAV's trajectory and power allocation. We decompose the formulated non-convex problem into three subproblems and solve them alternately to obtain the solution. Simulations show that: 1) the STAR-RIS achieves a higher sum rate than traditional RIS; 2) to exploit the benefits of STAR-RIS, the UAV's trajectory is closer to STAR-RIS than that of RIS; 3) the energy splitting for reflection and transmission highly depends on the real-time trajectory of UAV.

cs.IT↗

arXiv2022

Video-Guided Curriculum Learning for Spoken Video Grounding

In this paper, we introduce a new task, spoken video grounding (SVG), which aims to localize the desired video fragments from spoken language descriptions. Compared with using text, employing audio requires the model to directly exploit the useful phonemes and syllables related to the video from raw speech. Moreover, we randomly add environmental noises to this speech audio, further increasing the difficulty of this task and better simulating real applications. To rectify the discriminative phonemes and extract video-related information from noisy audio, we develop a novel video-guided curriculum learning (VGCL) during the audio pre-training process, which can make use of the vital visual perceptions to help understand the spoken language and suppress the external noise. Considering during inference the model can not obtain ground truth video segments, we design a curriculum strategy that gradually shifts the input video from the ground truth to the entire video content during pre-training. Finally, the model can learn how to extract critical visual information from the entire video clip to help understand the spoken language. In addition, we collect the first large-scale spoken video grounding dataset based on ActivityNet, which is named as ActivityNet Speech dataset. Extensive experiments demonstrate our proposed video-guided curriculum learning can facilitate the pre-training process to obtain a mutual audio encoder, significantly promoting the performance of spoken video grounding tasks. Moreover, we prove that in the case of noisy sound, our model outperforms the method that grounding video with ASR transcripts, further demonstrating the effectiveness of our curriculum strategy.

cs.CV↗

arXiv2022

Depth-Assisted ResiDualGAN for Cross-Domain Aerial Images Semantic Segmentation

Unsupervised domain adaptation (UDA) is an approach to minimizing domain gap. Generative methods are common approaches to minimizing the domain gap of aerial images which improves the performance of the downstream tasks, e.g., cross-domain semantic segmentation. For aerial images, the digital surface model (DSM) is usually available in both the source domain and the target domain. Depth information in DSM brings external information to generative models. However, little research utilizes it. In this paper, depth-assisted ResiDualGAN (DRDG) is proposed where depth supervised loss (DSL), and depth cycle consistency loss (DCCL) are used to bring depth information into the generative model. Experimental results show that DRDG reaches state-of-the-art accuracy between generative methods in cross-domain semantic segmentation tasks.

cs.CV↗

arXiv2022

BRIGHT -- Graph Neural Networks in Real-Time Fraud Detection

Detecting fraudulent transactions is an essential component to control risk in e-commerce marketplaces. Apart from rule-based and machine learning filters that are already deployed in production, we want to enable efficient real-time inference with graph neural networks (GNNs), which is useful to catch multihop risk propagation in a transaction graph. However, two challenges arise in the implementation of GNNs in production. First, future information in a dynamic graph should not be considered in message passing to predict the past. Second, the latency of graph query and GNN model inference is usually up to hundreds of milliseconds, which is costly for some critical online services. To tackle these challenges, we propose a Batch and Real-time Inception GrapH Topology (BRIGHT) framework to conduct an end-to-end GNN learning that allows efficient online real-time inference. BRIGHT framework consists of a graph transformation module (Two-Stage Directed Graph) and a corresponding GNN architecture (Lambda Neural Network). The Two-Stage Directed Graph guarantees that the information passed through neighbors is only from the historical payment transactions. It consists of two subgraphs representing historical relationships and real-time links, respectively. The Lambda Neural Network decouples inference into two stages: batch inference of entity embeddings and real-time inference of transaction prediction. Our experiments show that BRIGHT outperforms the baseline models by >2\% in average w.r.t.~precision. Furthermore, BRIGHT is computationally efficient for real-time fraud detection. Regarding end-to-end performance (including neighbor query and inference), BRIGHT can reduce the P99 latency by >75\%. For the inference stage, our speedup is on average 7.8$\times$ compared to the traditional GNN.

cs.LG↗

arXiv2022

The fractional Chern insulator with Rydberg-dressed neutral atoms

Topological nontrivial bands can be realized via Rydberg-dressed neutral atoms. We propose a two-dimensional hard-core boson model with a topological ground enrgy at band on a honeycomb lattice, where the particle hopping is realized via van der Waals interaction that exchanges the Rydberg states of two interacting atoms, while nonzero phases associated with hopping is created by transferring the optical phase of laser fields to the atomic pair wave function. Using exactly diagonalization and infinite density matrix renormalization group simulation, we find in the system a fractional Chern insulator phase with a Chern number C = 1/2, which can persist in the presence of weak many-body interactions. Our studies indicate that fractional Chern insulators can be studied with neutral-atom arrays.

cond-mat.quant-gas↗

arXiv2022

Learning an Efficient Multimodal Depth Completion Model

With the wide application of sparse ToF sensors in mobile devices, RGB image-guided sparse depth completion has attracted extensive attention recently, but still faces some problems. First, the fusion of multimodal information requires more network modules to process different modalities. But the application scenarios of sparse ToF measurements usually demand lightweight structure and low computational cost. Second, fusing sparse and noisy depth data with dense pixel-wise RGB data may introduce artifacts. In this paper, a light but efficient depth completion network is proposed, which consists of a two-branch global and local depth prediction module and a funnel convolutional spatial propagation network. The two-branch structure extracts and fuses cross-modal features with lightweight backbones. The improved spatial propagation module can refine the completed depth map gradually. Furthermore, corrected gradient loss is presented for the depth completion problem. Experimental results demonstrate the proposed method can outperform some state-of-the-art methods with a lightweight architecture. The proposed method also wins the championship in the MIPI2022 RGB+TOF depth completion challenge.

cs.CV↗

arXiv2022

Spatio-temporal Gait Feature with Global Distance Alignment

Gait recognition is an important recognition technology, because gait is not easy to camouflage and does not need cooperation to recognize subjects. However, many existing methods are inadequate in preserving both temporal information and fine-grained information, thus reducing its discrimination. This problem is more serious when the subjects with similar walking postures are identified. In this paper, we try to enhance the discrimination of spatio-temporal gait features from two aspects: effective extraction of spatio-temporal gait features and reasonable refinement of extracted features. Thus our method is proposed, it consists of Spatio-temporal Feature Extraction (SFE) and Global Distance Alignment (GDA). SFE uses Temporal Feature Fusion (TFF) and Fine-grained Feature Extraction (FFE) to effectively extract the spatio-temporal features from raw silhouettes. GDA uses a large number of unlabeled gait data in real life as a benchmark to refine the extracted spatio-temporal features. GDA can make the extracted features have low inter-class similarity and high intra-class similarity, thus enhancing their discrimination. Extensive experiments on mini-OUMVLP and CASIA-B have proved that we have a better result than some state-of-the-art methods.

cs.CV↗

arXiv2022

e-G2C: A 0.14-to-8.31 $μ$J/Inference NN-based Processor with Continuous On-chip Adaptation for Anomaly Detection and ECG Conversion from EGM

This work presents the first silicon-validated dedicated EGM-to-ECG (G2C) processor, dubbed e-G2C, featuring continuous lightweight anomaly detection, event-driven coarse/precise conversion, and on-chip adaptation. e-G2C utilizes neural network (NN) based G2C conversion and integrates 1) an architecture supporting anomaly detection and coarse/precise conversion via time multiplexing to balance the effectiveness and power, 2) an algorithm-hardware co-designed vector-wise sparsity resulting in a 1.6-1.7$\times$ speedup, 3) hybrid dataflows for enhancing near 100% utilization for normal/depth-wise(DW)/point-wise(PW) convolutions (Convs), and 4) an on-chip detection threshold adaptation engine for continuous effectiveness. The achieved 0.14-8.31 $μ$J/inference energy efficiency outperforms prior arts under similar complexity, promising real-time detection/conversion and possibly life-critical interventions

eess.SP↗

arXiv2022

Turning to a Teacher for Timestamp Supervised Temporal Action Segmentation

Temporal action segmentation in videos has drawn much attention recently. Timestamp supervision is a cost-effective way for this task. To obtain more information to optimize the model, the existing method generated pseudo frame-wise labels iteratively based on the output of a segmentation model and the timestamp annotations. However, this practice may introduce noise and oscillation during the training, and lead to performance degeneration. To address this problem, we propose a new framework for timestamp supervised temporal action segmentation by introducing a teacher model parallel to the segmentation model to help stabilize the process of model optimization. The teacher model can be seen as an ensemble of the segmentation model, which helps to suppress the noise and to improve the stability of pseudo labels. We further introduce a segmentally smoothing loss, which is more focused and cohesive, to enforce the smooth transition of the predicted probabilities within action instances. The experiments on three datasets show that our method outperforms the state-of-the-art method and performs comparably against the fully-supervised methods at a much lower annotation cost.

cs.CV↗

arXiv2022

Penalizing Gradient Norm for Efficiently Improving Generalization in Deep Learning

How to train deep neural networks (DNNs) to generalize well is a central concern in deep learning, especially for severely overparameterized networks nowadays. In this paper, we propose an effective method to improve the model generalization by additionally penalizing the gradient norm of loss function during optimization. We demonstrate that confining the gradient norm of loss function could help lead the optimizers towards finding flat minima. We leverage the first-order approximation to efficiently implement the corresponding gradient to fit well in the gradient descent framework. In our experiments, we confirm that when using our methods, generalization performance of various models could be improved on different datasets. Also, we show that the recent sharpness-aware minimization method (Foret et al., 2021) is a special, but not the best, case of our method, where the best case of our method could give new state-of-art performance on these tasks. Code is available at {https://github.com/zhaoyang-0204/gnp}.

cs.LG↗

arXiv2022

AntPivot: Livestream Highlight Detection via Hierarchical Attention Mechanism

In recent days, streaming technology has greatly promoted the development in the field of livestream. Due to the excessive length of livestream records, it's quite essential to extract highlight segments with the aim of effective reproduction and redistribution. Although there are lots of approaches proven to be effective in the highlight detection for other modals, the challenges existing in livestream processing, such as the extreme durations, large topic shifts, much irrelevant information and so forth, heavily hamper the adaptation and compatibility of these methods. In this paper, we formulate a new task Livestream Highlight Detection, discuss and analyze the difficulties listed above and propose a novel architecture AntPivot to solve this problem. Concretely, we first encode the original data into multiple views and model their temporal relations to capture clues in a hierarchical attention mechanism. Afterwards, we try to convert the detection of highlight clips into the search for optimal decision sequences and use the fully integrated representations to predict the final results in a dynamic-programming mechanism. Furthermore, we construct a fully-annotated dataset AntHighlight to instantiate this task and evaluate the performance of our model. The extensive experiments indicate the effectiveness and validity of our proposed method.

cs.MM↗

arXiv2022

xFraud: Explainable Fraud Transaction Detection

At online retail platforms, it is crucial to actively detect the risks of transactions to improve customer experience and minimize financial loss. In this work, we propose xFraud, an explainable fraud transaction prediction framework which is mainly composed of a detector and an explainer. The xFraud detector can effectively and efficiently predict the legitimacy of incoming transactions. Specifically, it utilizes a heterogeneous graph neural network to learn expressive representations from the informative heterogeneously typed entities in the transaction logs. The explainer in xFraud can generate meaningful and human-understandable explanations from graphs to facilitate further processes in the business unit. In our experiments with xFraud on real transaction networks with up to 1.1 billion nodes and 3.7 billion edges, xFraud is able to outperform various baseline models in many evaluation metrics while remaining scalable in distributed settings. In addition, we show that xFraud explainer can generate reasonable explanations to significantly assist the business analysis via both quantitative and qualitative evaluations.

cs.LG↗

arXiv2022

Scalar Diffraction Analysis Of Dispersion In Low-Index Thin Flat Lenses

We analyze the dispersion property of low-index thin lenses by using scalar diffraction and finite difference time domain (FDTD) methods. We compare the dispersion results obtained by using these methods with reported experimental results, and the well-known analytical formula for focal length (f) of diffractive lenses as a function of wavelength (λ),f(λ)=(f_0 λ_0)/λ,where f_0 is the designed focal length for wavelength λ_0. We show that when the analytical formula is applied to thin flat lenses with low-refractive index, the results are accurate for small numerical aperture (NA) up to 0.2. For larger NA, the error between the analytical approximation and the FDTD analysis remains around 8% over a wide range of NA.

physics.optics↗

arXiv2022

Indoor simultaneous localization and mapping based on fringe projection profilometry

Simultaneous Localization and Mapping (SLAM) plays an important role in outdoor and indoor applications ranging from autonomous driving to indoor robotics. Outdoor SLAM has been widely used with the assistance of LiDAR or GPS. For indoor applications, the LiDAR technique does not satisfy the accuracy requirement and the GPS signals will be lost. An accurate and efficient scene sensing technique is required for indoor SLAM. As the most promising 3D sensing technique, the opportunities for indoor SLAM with fringe projection profilometry (FPP) systems are obvious, but methods to date have not fully leveraged the accuracy and speed of sensing that such systems offer. In this paper, we propose a novel FPP-based indoor SLAM method based on the coordinate transformation relationship of FPP, where the 2D-to-3D descriptor-assisted is used for mapping and localization. The correspondences generated by matching descriptors are used for fast and accurate mapping, and the transform estimation between the 2D and 3D descriptors is used to localize the sensor. The provided experimental results demonstrate that the proposed indoor SLAM can achieve the localization and mapping accuracy around one millimeter.

cs.RO↗

arXiv2022

Modelling graph dynamics in fraud detection with "Attention"

At online retail platforms, detecting fraudulent accounts and transactions is crucial to improve customer experience, minimize loss, and avoid unauthorized transactions. Despite the variety of different models for deep learning on graphs, few approaches have been proposed for dealing with graphs that are both heterogeneous and dynamic. In this paper, we propose DyHGN (Dynamic Heterogeneous Graph Neural Network) and its variants to capture both temporal and heterogeneous information. We first construct dynamic heterogeneous graphs from registration and transaction data from eBay. Then, we build models with diachronic entity embedding and heterogeneous graph transformer. We also use model explainability techniques to understand the behaviors of DyHGN-* models. Our findings reveal that modelling graph dynamics with heterogeneous inputs need to be conducted with "attention" depending on the data structure, distribution, and computation cost.

cs.LG↗

arXiv2022

Quantitative Performance Assessment of CNN Units via Topological Entropy Calculation

Identifying the status of individual network units is critical for understanding the mechanism of convolutional neural networks (CNNs). However, it is still challenging to reliably give a general indication of unit status, especially for units in different network models. To this end, we propose a novel method for quantitatively clarifying the status of single unit in CNN using algebraic topological tools. Unit status is indicated via the calculation of a defined topological-based entropy, called feature entropy, which measures the degree of chaos of the global spatial pattern hidden in the unit for a category. In this way, feature entropy could provide an accurate indication of status for units in different networks with diverse situations like weight-rescaling operation. Further, we show that feature entropy decreases as the layer goes deeper and shares almost simultaneous trend with loss during training. We show that by investigating the feature entropy of units on only training data, it could give discrimination between networks with different generalization ability from the view of the effectiveness of feature representations.

cs.CV↗