arXiv subjects

He Wang

Publications and source records attributed to He Wang.

At least 253 records · Page 14Linked to original sources

arXiv2024

ICMC-ASR: The ICASSP 2024 In-Car Multi-Channel Automatic Speech Recognition Challenge

To promote speech processing and recognition research in driving scenarios, we build on the success of the Intelligent Cockpit Speech Recognition Challenge (ICSRC) held at ISCSLP 2022 and launch the ICASSP 2024 In-Car Multi-Channel Automatic Speech Recognition (ICMC-ASR) Challenge. This challenge collects over 100 hours of multi-channel speech data recorded inside a new energy vehicle and 40 hours of noise for data augmentation. Two tracks, including automatic speech recognition (ASR) and automatic speech diarization and recognition (ASDR) are set up, using character error rate (CER) and concatenated minimum permutation character error rate (cpCER) as evaluation metrics, respectively. Overall, the ICMC-ASR Challenge attracts 98 participating teams and receives 53 valid results in both tracks. In the end, first-place team USTCiflytek achieves a CER of 13.16% in the ASR track and a cpCER of 21.48% in the ASDR track, showing an absolute improvement of 13.08% and 51.4% compared to our challenge baseline, respectively.

cs.SD↗

arXiv2024

WaveFormer: transformer-based denoising method for gravitational-wave data

With the advent of gravitational-wave astronomy and the discovery of more compact binary coalescences, data quality improvement techniques are desired to handle the complex and overwhelming noise in gravitational wave (GW) observational data. Though recent machine learning-based studies have shown promising results for data denoising, they are unable to precisely recover both the GW signal amplitude and phase. To address such an issue, we develop a deep neural network centered workflow, WaveFormer, for significant noise suppression and signal recovery on observational data from the Laser Interferometer Gravitational-Wave Observatory (LIGO). The WaveFormer has a science-driven architecture design with hierarchical feature extraction across a broad frequency spectrum. As a result, the overall noise and glitch are decreased by more than one order of magnitude and the signal recovery error is roughly 1% and 7% for the phase and amplitude, respectively. Moreover, on 75 reported binary black hole (BBH) events of LIGO we obtain a significant improvement of inverse false alarm rate. Our work highlights the potential of large neural networks in gravitational wave data analysis and, while primarily demonstrated on LIGO data, its adaptable design indicates promise for broader application within the International Gravitational-Wave Observatories Network (IGWN) in future observational runs.

gr-qc↗

arXiv2024

Advancing Space-Based Gravitational Wave Astronomy: Rapid Parameter Estimation via Normalizing Flows

Gravitational wave (GW) astronomy is witnessing a transformative shift from terrestrial to space-based detection, with missions like Taiji at the forefront. While the transition brings unprecedented opportunities for exploring massive black hole binaries (MBHBs), it also imposes complex challenges in data analysis, particularly in parameter estimation amidst confusion noise. Addressing this gap, we utilize scalable normalizing flow models to achieve rapid and accurate inference within the Taiji environment. Innovatively, our approach simplifies the data's complexity, employs a transformation mapping to overcome the year-period time-dependent response function, and unveils additional multimodality in the arrival time parameter. Our method estimates MBHBs several orders of magnitude faster than conventional techniques, maintaining high accuracy even in complex backgrounds. These findings significantly enhance the efficiency of GW data analysis, paving the way for rapid detection and alerting systems and enriching our ability to explore the universe through space-based GW observation.

astro-ph.IM↗

arXiv2024

ControlUDA: Controllable Diffusion-assisted Unsupervised Domain Adaptation for Cross-Weather Semantic Segmentation

Data generation is recognized as a potent strategy for unsupervised domain adaptation (UDA) pertaining semantic segmentation in adverse weathers. Nevertheless, these adverse weather scenarios encompass multiple possibilities, and high-fidelity data synthesis with controllable weather is under-researched in previous UDA works. The recent strides in large-scale text-to-image diffusion models (DM) have ushered in a novel avenue for research, enabling the generation of realistic images conditioned on semantic labels. This capability proves instrumental for cross-domain data synthesis from source to target domain owing to their shared label space. Thus, source domain labels can be paired with those generated pseudo target data for training UDA. However, from the UDA perspective, there exists several challenges for DM training: (i) ground-truth labels from target domain are missing; (ii) the prompt generator may produce vague or noisy descriptions of images from adverse weathers; (iii) existing arts often struggle to well handle the complex scene structure and geometry of urban scenes when conditioned only on semantic labels. To tackle the above issues, we propose ControlUDA, a diffusion-assisted framework tailored for UDA segmentation under adverse weather conditions. It first leverages target prior from a pre-trained segmentor for tuning the DM, compensating the missing target domain labels; It also contains UDAControlNet, a condition-fused multi-scale and prompt-enhanced network targeted at high-fidelity data generation in adverse weathers. Training UDA with our generated data brings the model performances to a new milestone (72.0 mIoU) on the popular Cityscapes-to-ACDC benchmark for adverse weathers. Furthermore, ControlUDA helps to achieve good model generalizability on unseen data.

cs.CV↗

arXiv2024

Catch the Butterfly: Peeking into the Terms and Conflicts among SPDX Licenses

The widespread adoption of third-party libraries (TPLs) in software development has accelerated the creation of modern software. However, this convenience comes with potential legal risks. Developers may inadvertently violate the licenses of TPLs, leading to legal issues. While existing studies have explored software licenses and potential incompatibilities, these studies often focus on a limited set of licenses or rely on low-quality license data, which may affect their conclusions. To address this gap, there is a need for a high-quality license dataset that encompasses a broad range of mainstream licenses to help developers navigate the complex landscape of software licenses, avoid potential legal pitfalls, and guide solutions for managing license compliance and compatibility in software development. To this end, we conduct the first work to understand the mainstream software licenses based on term granularity and obtain a high-quality dataset of 453 SPDX licenses with well-labeled terms and conflicts. Specifically, we first conduct a differential analysis of the mainstream platforms to understand the terms and attitudes of each license. Next, we propose a standardized set of license terms to capture and label existing mainstream licenses with high quality. Moreover, we include copyleft conflicts and conclude the three major types of license conflicts among the 453 SPDX licenses. Based on these, we carry out two empirical studies to reveal the concerns and threats from the perspectives of both licensors and licensees. One study provides an in-depth analysis of the similarities, differences, and conflicts among SPDX licenses, revisits the usage and conflicts of licenses in the NPM ecosystem, and draws conclusions that differ from previous work. Our studies reveal some insightful findings and disclose relevant analytical data, which set the stage for further research.

cs.SE↗

arXiv2024

Physics-informed Deep Learning to Solve Three-dimensional Terzaghi Consolidation Equation: Forward and Inverse Problems

The emergence of neural networks constrained by physical governing equations has sparked a new trend in deep learning research, which is known as Physics-Informed Neural Networks (PINNs). However, solving high-dimensional problems with PINNs is still a substantial challenge, the space complexity brings difficulty to solving large multidirectional problems. In this paper, a novel PINN framework to quickly predict several three-dimensional Terzaghi consolidation cases under different conditions is proposed. Meanwhile, the loss functions for different cases are introduced, and their differences in three-dimensional consolidation problems are highlighted. The tuning strategies for the PINNs framework for three-dimensional consolidation problems are introduced. Then, the performance of PINNs is tested and compared with traditional numerical methods adopted in forward problems, and the coefficients of consolidation and the impact of noisy data in inverse problems are identified. Finally, the results are summarized and presented from three-dimensional simulations of PINNs, which show an accuracy rate of over 99% compared with ground truth for both forward and inverse problems. These results are desirable with good accuracy and can be used for soil settlement prediction, which demonstrates that the proposed PINNs framework can learn the three-dimensional consolidation PDE well. Keywords: Three-dimensional Terzaghi consolidation; Physics-informed neural networks (PINNs); Forward problems; Inverse problems; soil settlement

cs.LG↗

arXiv2024

HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction

We present HOI4D, a large-scale 4D egocentric dataset with rich annotations, to catalyze the research of category-level human-object interaction. HOI4D consists of 2.4M RGB-D egocentric video frames over 4000 sequences collected by 4 participants interacting with 800 different object instances from 16 categories over 610 different indoor rooms. Frame-wise annotations for panoptic segmentation, motion segmentation, 3D hand pose, category-level object pose and hand action have also been provided, together with reconstructed object meshes and scene point clouds. With HOI4D, we establish three benchmarking tasks to promote category-level HOI from 4D visual signals including semantic segmentation of 4D dynamic point cloud sequences, category-level object pose tracking, and egocentric action segmentation with diverse interaction targets. In-depth analysis shows HOI4D poses great challenges to existing methods and produces great research opportunities.

cs.CV↗

arXiv2023

Enhancing Generalizable 6D Pose Tracking of an In-Hand Object with Tactile Sensing

When manipulating an object to accomplish complex tasks, humans rely on both vision and touch to keep track of the object's 6D pose. However, most existing object pose tracking systems in robotics rely exclusively on visual signals, which hinder a robot's ability to manipulate objects effectively. To address this limitation, we introduce TEG-Track, a tactile-enhanced 6D pose tracking system that can track previously unseen objects held in hand. From consecutive tactile signals, TEG-Track optimizes object velocities from marker flows when slippage does not occur, or regresses velocities using a slippage estimation network when slippage is detected. The estimated object velocities are integrated into a geometric-kinematic optimization scheme to enhance existing visual pose trackers. To evaluate our method and to facilitate future research, we construct a real-world dataset for visual-tactile in-hand object pose tracking. Experimental results demonstrate that TEG-Track consistently enhances state-of-the-art generalizable 6D pose trackers in synthetic and real-world scenarios. Our code and dataset are available at https://github.com/leolyliu/TEG-Track.

cs.CV↗

arXiv2023

Full-Body Articulated Human-Object Interaction

Fine-grained capturing of 3D HOI boosts human activity understanding and facilitates downstream visual tasks, including action recognition, holistic scene reconstruction, and human motion synthesis. Despite its significance, existing works mostly assume that humans interact with rigid objects using only a few body parts, limiting their scope. In this paper, we address the challenging problem of f-AHOI, wherein the whole human bodies interact with articulated objects, whose parts are connected by movable joints. We present CHAIRS, a large-scale motion-captured f-AHOI dataset, consisting of 16.2 hours of versatile interactions between 46 participants and 81 articulated and rigid sittable objects. CHAIRS provides 3D meshes of both humans and articulated objects during the entire interactive process, as well as realistic and physically plausible full-body interactions. We show the value of CHAIRS with object pose estimation. By learning the geometrical relationships in HOI, we devise the very first model that leverage human pose estimation to tackle the estimation of articulated object poses and shapes during whole-body interactions. Given an image and an estimated human pose, our model first reconstructs the pose and shape of the object, then optimizes the reconstruction according to a learned interaction prior. Under both evaluation settings (e.g., with or without the knowledge of objects' geometries/structures), our model significantly outperforms baselines. We hope CHAIRS will promote the community towards finer-grained interaction understanding. We will make the data/code publicly available.

cs.CV↗

arXiv2023

Open quantum system in the indefinite environment

In this paper, we investigate the interference engineering of the open quantum system, where the environment is made indefinite either through the use of an interferometer or the introduction of auxiliary qubits. The environments are modeled by fully connected qubit baths with exact analytical dynamics. As the system passes through the interferometer or is controlled by auxiliary qubits, it is propagated along different paths or their superpositions, leading to distinct interactions with the environment in each path. This results in the superposition of the environments, which can be detected through specific measurements that retain certain coherent information about the paths. Our results demonstrate that the indefiniteness of the environment can significantly enhance the quantum correlations. However, only the statistical mixture of the influences from the environments preserves provided that the path coherence is destructed. We also examine the serviceability of the indefiniteness as a resource for teleportation and quantum parameter estimation. Additionally, we discuss how to quantify the indefiniteness and the ways in which it affects the system's dynamics from the perspective of wave-particle-entanglement-ignorance complementarity. Overall, our study highlights the potential benefits of an indefinite environment in quantum information processing and sheds light on the fundamental principles underlying its effects.

quant-ph↗

arXiv2023

The detection, extraction and parameter estimation of extreme-mass-ratio inspirals with deep learning

One of the primary goals of space-borne gravitational wave detectors is to detect and analyze extreme-mass-ratio inspirals (EMRIs). This endeavor presents a significant challenge due to the complex and lengthy EMRI signals, further compounded by their inherently faint nature. In this letter, we introduce a 2-layer Convolutional Neural Network (CNN) approach to detect EMRI signals for space-borne detectors, achieving a true positive rate (TPR) of 96.9 % at a 1 % false positive rate (FPR) for signal-to-noise ratio (SNR) from 50 to 100. Especially, the key intrinsic parameters of EMRIs such as mass and spin of the supermassive black hole (SMBH) and the initial eccentricity of the orbit can be inferred directly by employing a VGG network. The mass and spin of the SMBH can be determined at 99 % and 92 % respectively. This will greatly reduce the parameter spaces and computing cost for the following Bayesian parameter estimation. Our model also has a low dependency on the accuracy of the waveform model. This study underscores the potential of deep learning methods in EMRI data analysis, enabling the rapid detection of EMRI signals and efficient parameter estimation .

gr-qc↗

arXiv2023

Affective and Dynamic Beam Search for Story Generation

Storytelling's captivating potential makes it a fascinating research area, with implications for entertainment, education, therapy, and cognitive studies. In this paper, we propose Affective Story Generator (AffGen) for generating interesting narratives. AffGen introduces "intriguing twists" in narratives by employing two novel techniques-Dynamic Beam Sizing and Affective Reranking. Dynamic Beam Sizing encourages less predictable, more captivating word choices using a contextual multi-arm bandit model. Affective Reranking prioritizes sentence candidates based on affect intensity. Our empirical evaluations, both automatic and human, demonstrate AffGen's superior performance over existing baselines in generating affectively charged and interesting narratives. Our ablation study and analysis provide insights into the strengths and weaknesses of AffGen.

cs.CL↗

arXiv2023

Reconstructing 3D Human Pose from RGB-D Data with Occlusions

We propose a new method to reconstruct the 3D human body from RGB-D images with occlusions. The foremost challenge is the incompleteness of the RGB-D data due to occlusions between the body and the environment, leading to implausible reconstructions that suffer from severe human-scene penetration. To reconstruct a semantically and physically plausible human body, we propose to reduce the solution space based on scene information and prior knowledge. Our key idea is to constrain the solution space of the human body by considering the occluded body parts and visible body parts separately: modeling all plausible poses where the occluded body parts do not penetrate the scene, and constraining the visible body parts using depth data. Specifically, the first component is realized by a neural network that estimates the candidate region named the "free zone", a region carved out of the open space within which it is safe to search for poses of the invisible body parts without concern for penetration. The second component constrains the visible body parts using the "truncated shadow volume" of the scanned body point cloud. Furthermore, we propose to use a volume matching strategy, which yields better performance than surface matching, to match the human body with the confined region. We conducted experiments on the PROX dataset, and the results demonstrate that our method produces more accurate and plausible results compared with other methods.

cs.CV↗

arXiv2023

STOPNet: Multiview-based 6-DoF Suction Detection for Transparent Objects on Production Lines

In this work, we present STOPNet, a framework for 6-DoF object suction detection on production lines, with a focus on but not limited to transparent objects, which is an important and challenging problem in robotic systems and modern industry. Current methods requiring depth input fail on transparent objects due to depth cameras' deficiency in sensing their geometry, while we proposed a novel framework to reconstruct the scene on the production line depending only on RGB input, based on multiview stereo. Compared to existing works, our method not only reconstructs the whole 3D scene in order to obtain high-quality 6-DoF suction poses in real time but also generalizes to novel environments, novel arrangements and novel objects, including challenging transparent objects, both in simulation and the real world. Extensive experiments in simulation and the real world show that our method significantly surpasses the baselines and has better generalizability, which caters to practical industrial needs.

cs.RO↗

arXiv2023

FG-NeRF: Flow-GAN based Probabilistic Neural Radiance Field for Independence-Assumption-Free Uncertainty Estimation

Neural radiance fields with stochasticity have garnered significant interest by enabling the sampling of plausible radiance fields and quantifying uncertainty for downstream tasks. Existing works rely on the independence assumption of points in the radiance field or the pixels in input views to obtain tractable forms of the probability density function. However, this assumption inadvertently impacts performance when dealing with intricate geometry and texture. In this work, we propose an independence-assumption-free probabilistic neural radiance field based on Flow-GAN. By combining the generative capability of adversarial learning and the powerful expressivity of normalizing flow, our method explicitly models the density-radiance distribution of the whole scene. We represent our probabilistic NeRF as a mean-shifted probabilistic residual neural model. Our model is trained without an explicit likelihood function, thereby avoiding the independence assumption. Specifically, We downsample the training images with different strides and centers to form fixed-size patches which are used to train the generator with patch-based adversarial learning. Through extensive experiments, our method demonstrates state-of-the-art performance by predicting lower rendering errors and more reliable uncertainty on both synthetic and real-world datasets.

cs.CV↗

arXiv2023

Unlearnable Examples Give a False Sense of Security: Piercing through Unexploitable Data with Learnable Examples

Safeguarding data from unauthorized exploitation is vital for privacy and security, especially in recent rampant research in security breach such as adversarial/membership attacks. To this end, \textit{unlearnable examples} (UEs) have been recently proposed as a compelling protection, by adding imperceptible perturbation to data so that models trained on them cannot classify them accurately on original clean distribution. Unfortunately, we find UEs provide a false sense of security, because they cannot stop unauthorized users from utilizing other unprotected data to remove the protection, by turning unlearnable data into learnable again. Motivated by this observation, we formally define a new threat by introducing \textit{learnable unauthorized examples} (LEs) which are UEs with their protection removed. The core of this approach is a novel purification process that projects UEs onto the manifold of LEs. This is realized by a new joint-conditional diffusion model which denoises UEs conditioned on the pixel and perceptual similarity between UEs and LEs. Extensive experiments demonstrate that LE delivers state-of-the-art countering performance against both supervised UEs and unsupervised UEs in various scenarios, which is the first generalizable countermeasure to UEs across supervised learning and unsupervised learning. Our code is available at \url{https://github.com/jiangw-0/LE_JCDP}.

cs.LG↗

arXiv2023

CMRxRecon: An open cardiac MRI dataset for the competition of accelerated image reconstruction

Cardiac magnetic resonance imaging (CMR) has emerged as a valuable diagnostic tool for cardiac diseases. However, a limitation of CMR is its slow imaging speed, which causes patient discomfort and introduces artifacts in the images. There has been growing interest in deep learning-based CMR imaging algorithms that can reconstruct high-quality images from highly under-sampled k-space data. However, the development of deep learning methods requires large training datasets, which have not been publicly available for CMR. To address this gap, we released a dataset that includes multi-contrast, multi-view, multi-slice and multi-coil CMR imaging data from 300 subjects. Imaging studies include cardiac cine and mapping sequences. Manual segmentations of the myocardium and chambers of all the subjects are also provided within the dataset. Scripts of state-of-the-art reconstruction algorithms were also provided as a point of reference. Our aim is to facilitate the advancement of state-of-the-art CMR image reconstruction by introducing standardized evaluation criteria and making the dataset freely accessible to the research community. Researchers can access the dataset at https://www.synapse.org/#!Synapse:syn51471091/wiki/.

cs.CV↗

arXiv2023

Detecting extreme-mass-ratio inspirals for space-borne detectors with deep learning

One of the primary objectives for space-borne gravitational wave detectors is the detection of extreme-mass-ratio inspirals (EMRIs). This undertaking poses a substantial challenge because of the complex and long EMRI signals, further complicated by their inherently faint signal. In this research, we introduce a 2-layer Convolutional Neural Network (CNN) approach to detect EMRI signals for space-borne detectors. Our method employs the Q-transform for data preprocessing, effectively preserving EMRI signal characteristics while minimizing data size. By harnessing the robust capabilities of CNNs, we can reliably distinguish EMRI signals from noise, particularly when the signal-to-noise~(SNR) ratio reaches 50, a benchmark considered a ``golden'' EMRI. At the meantime, we incorporate time-delay interferometry (TDI) to ensure practical utility. We assess our model's performance using a 0.5-year dataset, achieving a true positive rate~(TPR) of 94.2\% at a 1\% false positive rate~(FPR) across various signal-to-noise ratio form 50-100, with 91\% TPR and 1\% FPR at an SNR of 50. This study underscores the promise of incorporating deep learning methods to advance EMRI data analysis, potentially leading to rapid EMRI signal detection.

gr-qc↗