arXiv subjects

Jun Zhang

Publications and source records attributed to Jun Zhang.

At least 703 records · Page 39Linked to original sources

arXiv2022

Joint Deep Reversible Regression Model and Physics-Informed Unsupervised Learning for Temperature Field Reconstruction

Temperature monitoring during the life time of heat source components in engineering systems becomes essential to guarantee the normal work and the working life of these components. However, prior methods, which mainly use the interpolate estimation to reconstruct the temperature field from limited monitoring points, require large amounts of temperature tensors for an accurate estimation. This may decrease the availability and reliability of the system and sharply increase the monitoring cost. To solve this problem, this work develops a novel physics-informed deep reversible regression models for temperature field reconstruction of heat-source systems (TFR-HSS), which can better reconstruct the temperature field with limited monitoring points unsupervisedly. First, we define the TFR-HSS task mathematically, and numerically model the task, and hence transform the task as an image-to-image regression problem. Then this work develops the deep reversible regression model which can better learn the physical information, especially over the boundary. Finally, considering the physical characteristics of heat conduction as well as the boundary conditions, this work proposes the physics-informed reconstruction loss including four training losses and jointly learns the deep surrogate model with these losses unsupervisedly. Experimental studies have conducted over typical two-dimensional heat-source systems to demonstrate the effectiveness of the proposed method.

cs.LG↗

arXiv2022

Multi-dataset Training of Transformers for Robust Action Recognition

We study the task of robust feature representations, aiming to generalize well on multiple datasets for action recognition. We build our method on Transformers for its efficacy. Although we have witnessed great progress for video action recognition in the past decade, it remains challenging yet valuable how to train a single model that can perform well across multiple datasets. Here, we propose a novel multi-dataset training paradigm, MultiTrain, with the design of two new loss terms, namely informative loss and projection loss, aiming to learn robust representations for action recognition. In particular, the informative loss maximizes the expressiveness of the feature embedding while the projection loss for each dataset mines the intrinsic relations between classes across datasets. We verify the effectiveness of our method on five challenging datasets, Kinetics-400, Kinetics-700, Moments-in-Time, Activitynet and Something-something-v2 datasets. Extensive experimental results show that our method can consistently improve state-of-the-art performance. Code and models are released.

cs.CV↗

arXiv2022

Token-level Speaker Change Detection Using Speaker Difference and Speech Content via Continuous Integrate-and-fire

In multi-talker scenarios such as meetings and conversations, speech processing systems are usually required to segment the audio and then transcribe each segmentation. These two stages are addressed separately by speaker change detection (SCD) and automatic speech recognition (ASR). Most previous SCD systems rely solely on speaker information and ignore the importance of speech content. In this paper, we propose a novel SCD system that considers both cues of speaker difference and speech content. These two cues are converted into token-level representations by the continuous integrate-and-fire (CIF) mechanism and then combined for detecting speaker changes on the token acoustic boundaries. We evaluate the performance of our approach on a public real-recorded meeting dataset, AISHELL-4. The experiment results show that our method outperforms a competitive frame-level baseline system by 2.45% equal coverage-purity (ECP). In addition, we demonstrate the importance of speech content and speaker difference to the SCD task, and the advantages of conducting SCD on the token acoustic boundaries compared with conducting SCD frame by frame.

cs.SD↗

arXiv2022

Negative differential thermal resistance of fluids induced by heat baths

It has recently been shown that in one-dimensional hard-point gases, there is a mechanism that induces negative differential thermal resistance (NDTR) between heat baths. We examine this mechanism in more general higher dimensional fluids described by multiparticle collision dynamics. We consider fluids in a finite cuboid region of three-dimensional space with each end in contact with a heat bath. Based on analytical results and numerical models, we find that the mechanism underlying NDTR also works for high-dimensional fluidic systems with weak interactions and is very robust to mixed fluids. Our results significantly advance knowledge of NDTR induced by heat bath and illuminate new directions to explore in fabricating fluid thermal transistors in micro- and nanosystems.

cond-mat.stat-mech↗

arXiv2022

On twisted generalized Reed-Solomon codes with l twists

In this paper, we study a class of twisted generalized Reed-Solomon (TGRS) codes with general l twists. A sufficient and necessary condition for the TGRS codes to be MDS or l-MDS (l<k and l<n-k) is determined. A sufficient and necessary condition that such a TGRS code is self-dual for 3l<k-1 is also presented. Finally, we give an explicit construction of self-dual TGRS codes. And examples of self-dual MDS TGRS codes for small l are given.

cs.IT↗

arXiv2022

Dark Matter In Extreme Astrophysical Environments

Exploring dark matter via observations of extreme astrophysical environments -- defined here as heavy compact objects such as white dwarfs, neutron stars, and black holes, as well as supernovae and compact object merger events -- has been a major field of growth since the last Snowmass process. Theoretical work has highlighted the utility of current and near-future observatories to constrain novel dark matter parameter space across the full mass range. This includes gravitational wave instruments and observatories spanning the electromagnetic spectrum, from radio to gamma-rays. While recent searches already provide leading sensitivity to various dark matter models, this work also highlights the need for theoretical astrophysics research to better constrain the properties of these extreme astrophysical systems. The unique potential of these search signatures to probe dark matter adds motivation to proposed next-generation astronomical and gravitational wave instruments.

hep-ph↗

arXiv2022

Graph Neural Networks for Wireless Communications: From Theory to Practice

Deep learning-based approaches have been developed to solve challenging problems in wireless communications, leading to promising results. Early attempts adopted neural network architectures inherited from applications such as computer vision. They often yield poor performance in large scale networks (i.e., poor scalability) and unseen network settings (i.e., poor generalization). To resolve these issues, graph neural networks (GNNs) have been recently adopted, as they can effectively exploit the domain knowledge, i.e., the graph topology in wireless communications problems. GNN-based methods can achieve near-optimal performance in large-scale networks and generalize well under different system settings, but the theoretical underpinnings and design guidelines remain elusive, which may hinder their practical implementations. This paper endeavors to fill both the theoretical and practical gaps. For theoretical guarantees, we prove that GNNs achieve near-optimal performance in wireless networks with much fewer training samples than traditional neural architectures. Specifically, to solve an optimization problem on an $n$-node graph (where the nodes may represent users, base stations, or antennas), GNNs' generalization error and required number of training samples are $\mathcal{O}(n)$ and $\mathcal{O}(n^2)$ times lower than the unstructured multi-layer perceptrons. For design guidelines, we propose a unified framework that is applicable to general design problems in wireless networks, which includes graph modeling, neural architecture design, and theory-guided performance enhancement. Extensive simulations, which cover a variety of important problems and network settings, verify our theory and the effectiveness of the proposed design framework.

cs.IT↗

arXiv2022

Deep Latent Mixture Model for Recommendation

Recent advances in neural networks have been successfully applied to many tasks in online recommendation applications. We propose a new framework called cone latent mixture model which makes use of hand-crafted state being able to factor distinct dependencies among multiple related documents. Specifically, it uses discriminative optimization techniques in order to generate effective multi-level knowledge bases, and uses online discriminative learning techniques in order to leverage these features. And for this joint model which uses confidence estimates for each topic and is able to learn a discriminatively trained jointly to automatically extracted salient features where discriminative training is only uses features and then is able to accurately trained.

cs.IR↗

arXiv2022

Influence of Pre-bottleneck Diversion Devices on Pedestrian Flow

The existence of bottlenecks often leads to the stagnation of pedestrian gatherings, which seriously affects the efficiency of traffic and reduces the flow of pedestrians. Some studies have shown that setting devices in front of bottlenecks can promote pedestrian evacuation under certain conditions. In this paper, the effect of setting diversion devices in front of the exit on pedestrian flow is studied. From our observation, these diversion devices can form a buffer zone before the exit and affect pedestrian behaviors. The evacuation times are found to decrease as the devices became farther away from the exit. In our experiments, it is found that the effect of shunt piles on evacuation is better than in the case of safety barriers and without device conditions. Under the condition of setting up safety barriers approximately 1m and 3m in front of the exit, the evacuation times are extended by 0.88% and 2.67%. For shunt piles, the evacuation times are 11.53% and 14.96% shorter than that of those without a device regarding the different distances to exit (1m and 3m, respectively). In addition, setting up shunt piles reduces the time interval between two consecutive pedestrians. To sum up, in our experimental settings, the diversion devices can effectively improve the average speed ahead of the exit and promote evacuation to become more orderly, which reduces the congestion in the later period of evacuation. In other words, this study demonstrates that a reasonable layout of facilities can not only meet the daily functional requirements but also improve the efficient use of space in emergencies, reducing the probability of crowd conventions and jams.

physics.soc-ph↗

arXiv2022

Rayleigh-Bénard thermal convection perturbed by a horizontal heat flux

In Rayleigh-Bénard convection, it has been found that the amount of heat passing through the fluid has a power law dependence on the imposed temperature difference. Modifying this dependence, either enhancing or reducing the heat transfer capability of fluids, is important in many scientific and practical applications. Here, we present a simple means to control the vertical heat transfer in Rayleigh-Bénard convection by injecting heat through one lateral side of the fluid domain and extracting the same amount of heat from the opposite side. This horizontal heat flux regulates the large-scale circulation, and increases the heat transfer rate in the vertical direction. Our numerical and theoretical studies demonstrate how a classical Rayleigh-Bénard convection responds to such a perturbation, when the system is near or well above the onset of convection.

physics.flu-dyn↗

arXiv2022

PARAGEN : A Parallel Generation Toolkit

PARAGEN is a PyTorch-based NLP toolkit for further development on parallel generation. PARAGEN provides thirteen types of customizable plugins, helping users to experiment quickly with novel ideas across model architectures, optimization, and learning strategies. We implement various features, such as unlimited data loading and automatic model selection, to enhance its industrial usage. ParaGen is now deployed to support various research and industry applications at ByteDance. PARAGEN is available at https://github.com/bytedance/ParaGen.

cs.CL↗

arXiv2022

DReS-FL: Dropout-Resilient Secure Federated Learning for Non-IID Clients via Secret Data Sharing

Federated learning (FL) strives to enable collaborative training of machine learning models without centrally collecting clients' private data. Different from centralized training, the local datasets across clients in FL are non-independent and identically distributed (non-IID). In addition, the data-owning clients may drop out of the training process arbitrarily. These characteristics will significantly degrade the training performance. This paper proposes a Dropout-Resilient Secure Federated Learning (DReS-FL) framework based on Lagrange coded computing (LCC) to tackle both the non-IID and dropout problems. The key idea is to utilize Lagrange coding to secretly share the private datasets among clients so that each client receives an encoded version of the global dataset, and the local gradient computation over this dataset is unbiased. To correctly decode the gradient at the server, the gradient function has to be a polynomial in a finite field, and thus we construct polynomial integer neural networks (PINNs) to enable our framework. Theoretical analysis shows that DReS-FL is resilient to client dropouts and provides privacy protection for the local datasets. Furthermore, we experimentally demonstrate that DReS-FL consistently leads to significant performance gains over baseline methods.

cs.LG↗

arXiv2022

Parity-doublet bands in the odd-\bm{$A$} isotones \element{237}U and \element{239}Pu by a particle-number-conserving method based on the cranked shell model

Based on the reflection-asymmetric Nilsson potential, the parity-doublet rotational bands in odd-$A$ isotones \element{237}U and \element{239}Pu have been investigated by using the particle-number-conserving (PNC) method in the framework of the cranked shell model (CSM). The experimental kinematic moments of inertia (MOIs) and angular momentum alignments are reproduced very well by the PNC-CSM calculations. The significant differences of rotational properties between \element{237}U and \element{239}Pu are explained with the contribution of nucleons occupying proton octupole-correlation pairs of $π^{2} i_{13/2}f_{7/2}$. The upbendings of moments of inertia of the parity-doublet bands in \element{237}U are due to the interference terms of alignments of protons occupying $πf_{7/2}$ (${1/2}$) and the high-$j$ intruder $πi_{13/2}$ $(1/2, 3/2)$ orbitals. The splittings between the simplex partner bands of the parity-doublet bands in both \element{237}U and \element{239}Pu result from the contribution of alignment of neutron occupying the $νd_{5/2}$ ($1/2$) orbital.

nucl-th↗

arXiv2022

SoccerNet 2022 Challenges Results

The SoccerNet 2022 challenges were the second annual video understanding challenges organized by the SoccerNet team. In 2022, the challenges were composed of 6 vision-based tasks: (1) action spotting, focusing on retrieving action timestamps in long untrimmed videos, (2) replay grounding, focusing on retrieving the live moment of an action shown in a replay, (3) pitch localization, focusing on detecting line and goal part elements, (4) camera calibration, dedicated to retrieving the intrinsic and extrinsic camera parameters, (5) player re-identification, focusing on retrieving the same players across multiple views, and (6) multiple object tracking, focusing on tracking players and the ball through unedited video streams. Compared to last year's challenges, tasks (1-2) had their evaluation metrics redefined to consider tighter temporal accuracies, and tasks (3-6) were novel, including their underlying data and annotations. More information on the tasks, challenges and leaderboards are available on https://www.soccer-net.org. Baselines and development kits are available on https://github.com/SoccerNet.

cs.CV↗

arXiv2022

Stellar Chromospheric Activity Database of Solar-like Stars Based on the LAMOST Low-Resolution Spectroscopic Survey

$\require{mediawiki-texvc}$A stellar chromospheric activity database of solar-like stars is constructed based on the Large Sky Area Multi-Object Fiber Spectroscopic Telescope (LAMOST) Low-Resolution Spectroscopic Survey (LRS). The database contains spectral bandpass fluxes and indexes of Ca II H&K lines derived from 1,330,654 high-quality LRS spectra of solar-like stars. We measure the mean fluxes at line cores of the Ca II H&K lines using a 1 $Å$ rectangular bandpass as well as a 1.09 $Å$ full width at half maximum (FWHM) triangular bandpass, and the mean fluxes of two 20 $Å$ pseudo-continuum bands on the two sides of the lines. Three activity indexes, $S_{\rm rec}$ based on the 1 $Å$ rectangular bandpass, and $S_{\rm tri}$ and $S_L$ based on the 1.09 $Å$ FWHM triangular bandpass, are evaluated from the measured fluxes to quantitatively indicate the chromospheric activity level. The uncertainties of all the obtained parameters are estimated. We also produce spectrum diagrams of Ca II H&K lines for all the spectra in the database. The entity of the database is composed of a catalog of spectral sample and activity parameters, and a library of spectrum diagrams. Statistics reveal that the solar-like stars with high level of chromospheric activity ($S_{\rm rec}>0.6$) tend to appear in the parameter range of $T_{\rm eff}\text{ (effective temperature)}<5500\,{\rm K}$, $4.3<\log\,g\text{ (surface gravity)}<4.6$, and $-0.2<[{\rm Fe/H}]\text{ (metallicity)}<0.3$. This database with more than one million high-quality LAMOST LRS spectra of Ca II H&K lines and basal chromospheric activity parameters can be further used for investigating activity characteristics of solar-like stars and solar-stellar connection.

astro-ph.SR↗

arXiv2022

Text-Adaptive Multiple Visual Prototype Matching for Video-Text Retrieval

Cross-modal retrieval between videos and texts has gained increasing research interest due to the rapid emergence of videos on the web. Generally, a video contains rich instance and event information and the query text only describes a part of the information. Thus, a video can correspond to multiple different text descriptions and queries. We call this phenomenon the ``Video-Text Correspondence Ambiguity'' problem. Current techniques mostly concentrate on mining local or multi-level alignment between contents of a video and text (\textit{e.g.}, object to entity and action to verb). It is difficult for these methods to alleviate the video-text correspondence ambiguity by describing a video using only one single feature, which is required to be matched with multiple different text features at the same time. To address this problem, we propose a Text-Adaptive Multiple Visual Prototype Matching model, which automatically captures multiple prototypes to describe a video by adaptive aggregation of video token features. Given a query text, the similarity is determined by the most similar prototype to find correspondence in the video, which is termed text-adaptive matching. To learn diverse prototypes for representing the rich information in videos, we propose a variance loss to encourage different prototypes to attend to different contents of the video. Our method outperforms state-of-the-art methods on four public video retrieval datasets.

cs.CV↗

arXiv2022

Overtwisting and Coiling Highly Enhances Strain Generation of Twisted String Actuators

Twisted string actuators (TSAs) have exhibited great promise in robotic applications by generating high translational force with low input torque. To further facilitate their robotic applications, it is strongly desirable but challenging to enhance their consistent strain generation while maintaining compliance. Existing studies predominantly considered overtwisting and coiling after the regular twisting stage to be undesirable non-uniform and unpredictable knots, entanglements, and coils formed to create an unstable and failure-prone structure. Overtwisting would work well for TSAs when uniform coils can be consistently formed. In this study, we realize uniform and consistent coil formation in overtwisted TSAs, which greatly increases their strain. Furthermore, we investigate methods for enabling uniform coil formation upon overtwisting the strings in a TSA and present a procedure to systematically "train" the strings. To the authors' best knowledge, this is the first study to experimentally investigate overtwisting for TSAs with different stiffnesses and realize consistent uniform coil formation. Ultra-high molecular-weight polyethylene (UHMWPE) strings form the stiff TSAs whereas compliant TSAs are realized with stretchable and conductive supercoiled polymer (SCP) strings. The strain, force, velocity, and torque of each overtwisted TSA was studied. Overtwisting and coiling resulted in approximately 70% strain in stiff TSAs and approximately 60% strain in compliant TSAs. This is more than twice the strain achieved through regular twisting. Lastly, the overtwisted TSA was successfully demonstrated in a robotic bicep.

cs.RO↗

arXiv2022

Anthropomorphic Twisted String-Actuated Soft Robotic Gripper with Tendon-Based Stiffening

Realizing high-performance soft robotic grippers is challenging because of the inherent limitations of the soft actuators and artificial muscles that drive them, including low force output, small actuation range, and poor compactness. Despite advances in this area, realizing compact soft grippers with high dexterity and force output is still challenging. This paper explores twisted string actuators (TSAs) to drive a soft robotic gripper. TSAs have been used in numerous robotic applications, but their inclusion in soft robots has been limited. The proposed design of the gripper was inspired by the human hand. Tunable stiffness was implemented in the fingers with antagonistic TSAs. The fingers' bending angles, actuation speed, blocked force output, and stiffness tuning were experimentally characterized. The gripper achieved a score of 6 on the Kapandji test and recreated 31 of the 33 grasps of the Feix GRASP taxonomy. It exhibited a maximum grasping force of 72 N, which was almost 13 times its own weight. A comparison study revealed that the proposed gripper exhibited equivalent or superior performance compared to other similar soft grippers.

cs.RO↗