arXiv subjects

Lei Jin

Publications and source records attributed to Lei Jin.

At least 55 records · Page 3Linked to original sources

arXiv2024

A Multimodal Dangerous State Recognition and Early Warning System for Elderly with Intermittent Dementia

In response to the social issue of the increasing number of elderly vulnerable groups going missing due to the aggravating aging population in China, our team has developed a wearable anti-loss device and intelligent early warning system for elderly individuals with intermittent dementia using artificial intelligence and IoT technology. This system comprises an anti-loss smart helmet, a cloud computing module, and an intelligent early warning application on the caregiver's mobile device. The smart helmet integrates a miniature camera module, a GPS module, and a 5G communication module to collect first-person images and location information of the elderly. Data is transmitted remotely via 5G, FTP, and TCP protocols. In the cloud computing module, our team has proposed for the first time a multimodal dangerous state recognition network based on scene and location information to accurately assess the risk of elderly individuals going missing. Finally, the application software interface designed for the caregiver's mobile device implements multi-level early warnings. The system developed by our team requires no operation or response from the elderly, achieving fully automatic environmental perception, risk assessment, and proactive alarming. This overcomes the limitations of traditional monitoring devices, which require active operation and response, thus avoiding the issue of the digital divide for the elderly. It effectively prevents accidental loss and potential dangers for elderly individuals with dementia.

cs.CV↗

arXiv2024

The SkatingVerse Workshop & Challenge: Methods and Results

The SkatingVerse Workshop & Challenge aims to encourage research in developing novel and accurate methods for human action understanding. The SkatingVerse dataset used for the SkatingVerse Challenge has been publicly released. There are two subsets in the dataset, i.e., the training subset and testing subset. The training subsets consists of 19,993 RGB video sequences, and the testing subsets consists of 8,586 RGB video sequences. Around 10 participating teams from the globe competed in the SkatingVerse Challenge. In this paper, we provide a brief summary of the SkatingVerse Workshop & Challenge including brief introductions to the top three methods. The submission leaderboard will be reopened for researchers that are interested in the human action understanding challenge. The benchmark dataset and other information can be found at: https://skatingverse.github.io/.

cs.CV↗

arXiv2024

UniParser: Multi-Human Parsing with Unified Correlation Representation Learning

Multi-human parsing is an image segmentation task necessitating both instance-level and fine-grained category-level information. However, prior research has typically processed these two types of information through separate branches and distinct output formats, leading to inefficient and redundant frameworks. This paper introduces UniParser, which integrates instance-level and category-level representations in three key aspects: 1) we propose a unified correlation representation learning approach, allowing our network to learn instance and category features within the cosine space; 2) we unify the form of outputs of each modules as pixel-level segmentation results while supervising instance and category features using a homogeneous label accompanied by an auxiliary loss; and 3) we design a joint optimization procedure to fuse instance and category representations. By virtual of unifying instance-level and category-level output, UniParser circumvents manually designed post-processing techniques and surpasses state-of-the-art methods, achieving 49.3% AP on MHPv2.0 and 60.4% AP on CIHP. We will release our source code, pretrained models, and online demos to facilitate future studies.

cs.CV↗

arXiv2024

DriveWorld: 4D Pre-trained Scene Understanding via World Models for Autonomous Driving

Vision-centric autonomous driving has recently raised wide attention due to its lower cost. Pre-training is essential for extracting a universal representation. However, current vision-centric pre-training typically relies on either 2D or 3D pre-text tasks, overlooking the temporal characteristics of autonomous driving as a 4D scene understanding task. In this paper, we address this challenge by introducing a world model-based autonomous driving 4D representation learning framework, dubbed \emph{DriveWorld}, which is capable of pre-training from multi-camera driving videos in a spatio-temporal fashion. Specifically, we propose a Memory State-Space Model for spatio-temporal modelling, which consists of a Dynamic Memory Bank module for learning temporal-aware latent dynamics to predict future changes and a Static Scene Propagation module for learning spatial-aware latent statics to offer comprehensive scene contexts. We additionally introduce a Task Prompt to decouple task-aware features for various downstream tasks. The experiments demonstrate that DriveWorld delivers promising results on various autonomous driving tasks. When pre-trained with the OpenScene dataset, DriveWorld achieves a 7.5% increase in mAP for 3D object detection, a 3.0% increase in IoU for online mapping, a 5.0% increase in AMOTA for multi-object tracking, a 0.1m decrease in minADE for motion forecasting, a 3.0% increase in IoU for occupancy prediction, and a 0.34m reduction in average L2 error for planning.

cs.CV↗

arXiv2024

Insights into the defect-driven heterogeneous structural evolution of Ni-rich layered cathode in lithium-ion batteries

Recently, considerable efforts have been made on research and improvement for Ni-rich lithium-ion batteries to meet the demand from vehicles and grid-level large-scale energy storage. Development of next-generation high-performance lithium-ion batteries requires a comprehensive understanding on the underlying electrochemical mechanisms associated with its structural evolution. In this work, advanced operando neutron diffraction and four-dimensional scanning transmission electron microscopy techniques are applied to clarify the structural evolution of electrodes in two distinct full cells with identical LiNi0.8Co0.1Mn0.1O2 cathode but different anode counterparts. It is found that both of cathodes in two cells exhibit non-intrinsic two-phase-like behavior at the early charge stage, indicating selective Li+ extraction from cathodes. But the heterogeneous evolution of cathode is less serious with graphite-silicon blended anode than that with graphite anode due to the different delithiation rate. Moreover, it is revealed that the formation of heterogeneous structure is led by the distribution of defects including Li/Ni disordering and microcracks, which should be inhibited by assembling appropriate anode to avoid potential threaten on cell performance. The present work unveils the origin of inhomogeneity in Ni-rich lithium-ion batteries and highlights the significance of kinetics control in electrodes for batteries with higher capacity and longer life.

cond-mat.mtrl-sci↗

arXiv2024

Prospects for measuring time variation of astrophysical neutrino sources at dark matter detectors

We study the prospects for measuring the time variation of solar and atmospheric neutrino fluxes at future large-scale Xenon and Argon dark matter detectors. For solar neutrinos, a yearly time variation arises from the eccentricity of the Earth's orbit, and, for charged current interactions, from a smaller energy-dependent day-night variation to due flavor regeneration as neutrinos travel through the Earth. For a 100-ton Xenon detector running for 10 years with a Xenon-136 fraction of $\lesssim 0.1\%$, in the electron recoil channel a time-variation amplitude of about 0.8\% is detectable with a power of 90\% and the level of significance of 10\%. This is sufficient to detect time variation due to eccentricity, which has amplitude of $\sim 3\%$. In the nuclear recoil channel, the detectable amplitude is about 10\% under current detector resolution and efficiency conditions, and this generally reduces to about 1\% for improved detector resolution and efficiency, the latter of which is sufficient to detect time variation due to eccentricity. Our analysis assumes both known and unknown periods. We provide scalings to determine the sensitivity to an arbitrary time-varying amplitude as a function of detector parameters. Identifying the time variation of the neutrino fluxes will be important for distinguishing neutrinos from dark matter signals and other detector-related backgrounds, and extracting properties of neutrinos that can be uniquely studied in dark matter experiments.

hep-ph↗

arXiv2024

Detection of astrophysical neutrinos at prospective locations of dark matter detectors

We study the prospects for detection of solar and atmospheric neutrino fluxes at future large-scale dark matter detectors through both electron and nuclear recoils. We specifically examine how the detection prospects change for several prospective detector locations (SURF, SNOlab, Gran Sasso, CJPL, and Kamioka), and improve upon the statistical methodologies used in previous studies. Due to its ability to measure lower neutrino energies than other locations, we find that the best prospects for the atmospheric neutrino flux are at the SURF location, while the prospects are weakest at CJPL because it is restricted to higher neutrino energies. On the contrary, the prospects for the diffuse supernova neutrino background (DSNB) are best at CJPL, due largely to the reduced atmospheric neutrino background at this location. Including full detector resolution and efficiency models, the CNO component of the solar flux is detectable via the electron recoil channel with exposures of $\sim 10^3$ ton-yr for all locations. These results highlight the benefits for employing two detector locations, one at high and one at low latitude.

hep-ph↗

arXiv2023

The Hilbert cube contains a minimal subshift of full mean dimension

We construct a minimal dynamical system of mean dimension equal to $1$, which can be embedded in the shift action on the Hilbert cube $[0,1]^\mathbb{Z}$. This clarifies a seemingly plausible impression about embedding possibility in relation to mean dimension. Our result finally leads to a full understanding of a pair of exact ranges of all the possible values of mean dimension, within which there will always be a minimal dynamical system that can/cannot be embedded in the shift action on the Hilbert cube.

math.DS↗

arXiv2023

Unified Single-Stage Transformer Network for Efficient RGB-T Tracking

Most existing RGB-T tracking networks extract modality features in a separate manner, which lacks interaction and mutual guidance between modalities. This limits the network's ability to adapt to the diverse dual-modality appearances of targets and the dynamic relationships between the modalities. Additionally, the three-stage fusion tracking paradigm followed by these networks significantly restricts the tracking speed. To overcome these problems, we propose a unified single-stage Transformer RGB-T tracking network, namely USTrack, which unifies the above three stages into a single ViT (Vision Transformer) backbone with a dual embedding layer through self-attention mechanism. With this structure, the network can extract fusion features of the template and search region under the mutual interaction of modalities. Simultaneously, relation modeling is performed between these features, efficiently obtaining the search region fusion features with better target-background discriminability for prediction. Furthermore, we introduce a novel feature selection mechanism based on modality reliability to mitigate the influence of invalid modalities for prediction, further improving the tracking performance. Extensive experiments on three popular RGB-T tracking benchmarks demonstrate that our method achieves new state-of-the-art performance while maintaining the fastest inference speed 84.2FPS. In particular, MPR/MSR on the short-term and long-term subsets of VTUAV dataset increased by 11.1$\%$/11.7$\%$ and 11.3$\%$/9.7$\%$.

cs.CV↗

arXiv2023

DiffCR: A Fast Conditional Diffusion Framework for Cloud Removal from Optical Satellite Images

Optical satellite images are a critical data source; however, cloud cover often compromises their quality, hindering image applications and analysis. Consequently, effectively removing clouds from optical satellite images has emerged as a prominent research direction. While recent advancements in cloud removal primarily rely on generative adversarial networks, which may yield suboptimal image quality, diffusion models have demonstrated remarkable success in diverse image-generation tasks, showcasing their potential in addressing this challenge. This paper presents a novel framework called DiffCR, which leverages conditional guided diffusion with deep convolutional networks for high-performance cloud removal for optical satellite imagery. Specifically, we introduce a decoupled encoder for conditional image feature extraction, providing a robust color representation to ensure the close similarity of appearance information between the conditional input and the synthesized output. Moreover, we propose a novel and efficient time and condition fusion block within the cloud removal model to accurately simulate the correspondence between the appearance in the conditional image and the target image at a low computational cost. Extensive experimental evaluations on two commonly used benchmark datasets demonstrate that DiffCR consistently achieves state-of-the-art performance on all metrics, with parameter and computational complexities amounting to only 5.1% and 5.4%, respectively, of those previous best methods. The source code, pre-trained models, and all the experimental results will be publicly available at https://github.com/XavierJiezou/DiffCR upon the paper's acceptance of this work.

cs.CV↗

arXiv2023

The 3rd Anti-UAV Workshop & Challenge: Methods and Results

The 3rd Anti-UAV Workshop & Challenge aims to encourage research in developing novel and accurate methods for multi-scale object tracking. The Anti-UAV dataset used for the Anti-UAV Challenge has been publicly released. There are two main differences between this year's competition and the previous two. First, we have expanded the existing dataset, and for the first time, released a training set so that participants can focus on improving their models. Second, we set up two tracks for the first time, i.e., Anti-UAV Tracking and Anti-UAV Detection & Tracking. Around 76 participating teams from the globe competed in the 3rd Anti-UAV Challenge. In this paper, we provide a brief summary of the 3rd Anti-UAV Workshop & Challenge including brief introductions to the top three methods in each track. The submission leaderboard will be reopened for researchers that are interested in the Anti-UAV challenge. The benchmark dataset and other information can be found at: https://anti-uav.github.io/.

cs.CV↗

arXiv2023

Evidential Detection and Tracking Collaboration: New Problem, Benchmark and Algorithm for Robust Anti-UAV System

Unmanned Aerial Vehicles (UAVs) have been widely used in many areas, including transportation, surveillance, and military. However, their potential for safety and privacy violations is an increasing issue and highly limits their broader applications, underscoring the critical importance of UAV perception and defense (anti-UAV). Still, previous works have simplified such an anti-UAV task as a tracking problem, where the prior information of UAVs is always provided; such a scheme fails in real-world anti-UAV tasks (i.e. complex scenes, indeterminate-appear and -reappear UAVs, and real-time UAV surveillance). In this paper, we first formulate a new and practical anti-UAV problem featuring the UAVs perception in complex scenes without prior UAVs information. To benchmark such a challenging task, we propose the largest UAV dataset dubbed AntiUAV600 and a new evaluation metric. The AntiUAV600 comprises 600 video sequences of challenging scenes with random, fast, and small-scale UAVs, with over 723K thermal infrared frames densely annotated with bounding boxes. Finally, we develop a novel anti-UAV approach via an evidential collaboration of global UAVs detection and local UAVs tracking, which effectively tackles the proposed problem and can serve as a strong baseline for future research. Extensive experiments show our method outperforms SOTA approaches and validate the ability of AntiUAV600 to enhance UAV perception performance due to its large scale and complexity. Our dataset, pretrained models, and source codes will be released publically.

cs.CV↗

arXiv2023

Single-stage Multi-human Parsing via Point Sets and Center-based Offsets

This work studies the multi-human parsing problem. Existing methods, either following top-down or bottom-up two-stage paradigms, usually involve expensive computational costs. We instead present a high-performance Single-stage Multi-human Parsing (SMP) deep architecture that decouples the multi-human parsing problem into two fine-grained sub-problems, i.e., locating the human body and parts. SMP leverages the point features in the barycenter positions to obtain their segmentation and then generates a series of offsets from the barycenter of the human body to the barycenters of parts, thus performing human body and parts matching without the grouping process. Within the SMP architecture, we propose a Refined Feature Retain module to extract the global feature of instances through generated mask attention and a Mask of Interest Reclassify module as a trainable plug-in module to refine the classification results with the predicted segmentation. Extensive experiments on the MHPv2.0 dataset demonstrate the best effectiveness and efficiency of the proposed method, surpassing the state-of-the-art method by 2.1% in AP50p, 1.0% in APvolp, and 1.2% in PCP50. In particular, the proposed method requires fewer training epochs and a less complex model architecture. We will release our source codes, pretrained models, and online demos to facilitate further studies.

cs.CV↗

arXiv2023

On A Saturated Poromechanical Framework and Its Relation to Abaqus Soil Mechanics and Biot Poroelasticity Frameworks

We introduce a conservational and constitutive framework for a closed and isothermal two-phase material system consisting of a deformable porous solid matrix and a fully saturating, single-phase, and compressible pore fluid without inter-phase mass exchange. We re-derive a generalized fluid mass balance law using fundamental transport rules. We also summarize from the literature a fundamental force balance law for the fluid-solid mixture that does not require any effective stress law a priori. We show that the two conservation laws are coupled naturally to second-order without any constitutive prerequisites. This differs from Biot poroelasticity, which first postulates first-order fluid-solid coupling as two linearized constitutive relationships and then enforces them into simple Eulerian form of conservation laws. Next, we examine a limiting-case unsaturated soil mechanics framework implemented in Abaqus, by assuming isothermal conditions, full saturation, and no adsorption, and then relate it to our framework. We prove that (1) the two mass balance laws are always equivalent regardless of fluid constitutive behaviors, and (2) the two force balance laws are equivalent in their specific forms with a linearly elastic solid skeleton. Finally, taking advantage of a fundamental pore constitutive law, we show how our framework, and by extension the limiting-case Abaqus framework, naturally gives rise to the distinction between drained and undrained settings, and reduces to Biot poroelasticity under simplifying conditions. Notably, our framework indicates the presence of an additional solid-to-fluid coupling term when the solid particle velocity is non-orthogonal to the Darcy velocity.

physics.flu-dyn↗

arXiv2023

Spectroscopic Evidence for Dirac Nodal Surfaces and Nodal Rings in Superconductor NaAlSi

The discovery of the topological states has become a key topic in condensed matter physics with the focus evolving from the Dirac or Weyl points to high-dimension topological states of the nodal lines and nodal surfaces. For a topological material to manifest its quantum properties and become useful in applications, the topological states need to be genuine and clean so that they lie close to the Fermi level without other trivial bands existing at the Fermi level. While a number of high-dimension topological materials are predicted, only a few of them have been synthesized and confirmed and the genuine and clean ones are especially scarce. Here we report the realization of the genuine clean multiple high-dimension topological states in NaAlSi. By performing high-resolution angle-resolved photoemission measurements and band structure calculations, we have observed two sets of nodal surfaces and the formation of two homocentric nodal ring states in NaAlSi. The observed nodal rings are distinct in that the inner one is a type-{\uppercase\expandafter{\romannumeral1}} nodal ring while the outer one is a type-{\uppercase\expandafter{\romannumeral1}} nodal ring embedded with four type-{\uppercase\expandafter{\romannumeral3}} nodal points. All the bands involved in the nodal rings lie very close to the Fermi level with no other trivial bands coexisting at the Fermi level. These observations make NaAlSi a desirable topological material to explore for novel quantum states and exotic properties.

cond-mat.mtrl-sci↗

arXiv2023

Observation of spin-polarized surface states in a nodal line semimetal SnTaS$_{2}$

The superconductor SnTaS$_{2}$ is theoretically predicted to be an intriguing topological nodal line semimetal without consideration of spin-orbit coupling. By carrying out angle-resolved photoemission (ARPES) and spin-resolved ARPES measurements combined with band structure calculations, we have provided a complete picture of the electronic structure and spin polarization property for the prominent surface states of SnTaS$_{2}$. The low-energy electronic states are dominated by surface states; two of them are from the S-terminated surface, while four of them are from the Sn-terminated surface. These give rise to interesting Fermi surface topology of SnTaS$_{2}$: three pockets located at $\barΓ$, $\bar{M}$ and $\bar{K}$ for the S-terminated surface and two pockets surrounding $\barΓ$ and $\bar{K}$ for the Sn-terminated surface. We further reveal that two surface states that cross the Fermi level are spin-polarized. Since SnTaS$_{2}$ is also a superconductor, our observations indicate that it may provide a new platform to explore topological superconductivity and other exotic properties.

cond-mat.supr-con↗

arXiv2023

The Solar Upper Transition Region Imager (SUTRI) onboard the SATech-01 satellite

The Solar Upper Transition Region Imager (SUTRI) onboard the Space Advanced Technology demonstration satellite (SATech-01), which was launched to a sun-synchronous orbit at a height of 500 km in July 2022, aims to test the on-orbit performance of our newly developed Sc-Si multi-layer reflecting mirror and the 2kx2k EUV CMOS imaging camera and to take full-disk solar images at the Ne VII 46.5 nm spectral line with a filter width of 3 nm. SUTRI employs a Ritchey-Chretien optical system with an aperture of 18 cm. The on-orbit observations show that SUTRI images have a field of view of 41.6'x41.6' and a moderate spatial resolution of 8" without an image stabilization system. The normal cadence of SUTRI images is 30 s and the solar observation time is about 16 hours each day because the earth eclipse time accounts for about 1/3 of SATech-01's orbit period. Approximately 15 GB data is acquired each day and made available online after processing. SUTRI images are valuable as the Ne VII 46.5 nm line is formed at a temperature regime of 0.5 MK in the solar atmosphere, which has rarely been sampled by existing solar imagers. SUTRI observations will establish connections between structures in the lower solar atmosphere and corona, and advance our understanding of various types of solar activity such as flares, filament eruptions, coronal jets and coronal mass ejections.

astro-ph.SR↗

arXiv2023

Towards End-to-end Semi-supervised Learning for One-stage Object Detection

Semi-supervised object detection (SSOD) is a research hot spot in computer vision, which can greatly reduce the requirement for expensive bounding-box annotations. Despite great success, existing progress mainly focuses on two-stage detection networks like FasterRCNN, while the research on one-stage detectors is often ignored. In this paper, we focus on the semi-supervised learning for the advanced and popular one-stage detection network YOLOv5. Compared with Faster-RCNN, the implementation of YOLOv5 is much more complex, and the various training techniques used in YOLOv5 can also reduce the benefit of SSOD. In addition to this challenge, we also reveal two key issues in one-stage SSOD, which are low-quality pseudo-labeling and multi-task optimization conflict, respectively. To address these issues, we propose a novel teacher-student learning recipe called OneTeacher with two innovative designs, namely Multi-view Pseudo-label Refinement (MPR) and Decoupled Semi-supervised Optimization (DSO). In particular, MPR improves the quality of pseudo-labels via augmented-view refinement and global-view filtering, and DSO handles the joint optimization conflicts via structure tweaks and task-specific pseudo-labeling. In addition, we also carefully revise the implementation of YOLOv5 to maximize the benefits of SSOD, which is also shared with the existing SSOD methods for fair comparison. To validate OneTeacher, we conduct extensive experiments on COCO and Pascal VOC. The extensive experiments show that OneTeacher can not only achieve superior performance than the compared methods, e.g., 15.0% relative AP gains over Unbiased Teacher, but also well handle the key issues in one-stage SSOD. Our source code is available at: https://github.com/luogen1996/OneTeacher.

cs.CV↗