Search

Primordial black holes (PBHs), originating from the gravitational collapse of large overdensities in the early Universe, emerge as a compelling dark matter (DM) candidate across a broad mass range. Of particular interest are ultra-light PBHs with masses around $10^{14}$ to $10^{17}$ g, which are typically probed by searching their evaporation products. Using the soft X-ray signal measured by the XMM telescopes, we derive constraints on the fraction of PBHs dark matter with masses in the range $10^{15}$-$10^{16}$ g. We find that observations exclude fraction $f>10^{-6}$ at 95\% C.L. for mass $M_{\rm PBH}=10^{15}$ g.

The CNN has achieved excellent results in the automatic classification of medical images. In this study, we propose a novel deep residual 3D attention non-local network (NL-RAN) to classify CT images included COVID-19, common pneumonia, and normal to perform rapid and explainable COVID-19 diagnosis. We built a deep residual 3D attention non-local network that could achieve end-to-end training. The network is embedded with a nonlocal module to capture global information, while a 3D attention module is embedded to focus on the details of the lesion so that it can directly analyze the 3D lung CT and output the classification results. The output of the attention module can be used as a heat map to increase the interpretability of the model. 4079 3D CT scans were included in this study. Each scan had a unique label (novel coronavirus pneumonia, common pneumonia, and normal). The CT scans cohort was randomly split into a training set of 3263 scans, a validation set of 408 scans, and a testing set of 408 scans. And compare with existing mainstream classification methods, such as CovNet, CBAM, ResNet, etc. Simultaneously compare the visualization results with visualization methods such as CAM. Model performance was evaluated using the Area Under the ROC Curve(AUC), precision, and F1-score. The NL-RAN achieved the AUC of 0.9903, the precision of 0.9473, and the F1-score of 0.9462, surpass all the classification methods compared. The heat map output by the attention module is also clearer than the heat map output by CAM. Our experimental results indicate that our proposed method performs significantly better than existing methods. In addition, the first attention module outputs a heat map containing detailed outline information to increase the interpretability of the model. Our experiments indicate that the inference of our model is fast. It can provide real-time assistance with diagnosis.

Recent image generation models excel at creating high-quality images from brief captions. However, they fail to maintain consistency of multiple instances across images when encountering lengthy contexts. This inconsistency is largely due to in existing training datasets the absence of granular instance feature labeling in existing training datasets. To tackle these issues, we introduce Openstory++, a large-scale dataset combining additional instance-level annotations with both images and text. Furthermore, we develop a training methodology that emphasizes entity-centric image-text generation, ensuring that the models learn to effectively interweave visual and textual information. Specifically, Openstory++ streamlines the process of keyframe extraction from open-domain videos, employing vision-language models to generate captions that are then polished by a large language model for narrative continuity. It surpasses previous datasets by offering a more expansive open-domain resource, which incorporates automated captioning, high-resolution imagery tailored for instance count, and extensive frame sequences for temporal consistency. Additionally, we present Cohere-Bench, a pioneering benchmark framework for evaluating the image generation tasks when long multimodal context is provided, including the ability to keep the background, style, instances in the given context coherent. Compared to existing benchmarks, our work fills critical gaps in multi-modal generation, propelling the development of models that can adeptly generate and interpret complex narratives in open-domain environments. Experiments conducted within Cohere-Bench confirm the superiority of Openstory++ in nurturing high-quality visual storytelling models, enhancing their ability to address open-domain generation tasks. More details can be found at https://openstorypp.github.io/

Face super-resolution aims to reconstruct a high-resolution face image from a low-resolution face image. Previous methods typically employ an encoder-decoder structure to extract facial structural features, where the direct downsampling inevitably introduces distortions, especially to high-frequency features such as edges. To address this issue, we propose a wavelet-based feature enhancement network, which mitigates feature distortion by losslessly decomposing the input feature into high and low-frequency components using the wavelet transform and processing them separately. To improve the efficiency of facial feature extraction, a full domain Transformer is further proposed to enhance local, regional, and global facial features. Such designs allow our method to perform better without stacking many modules as previous methods did. Experiments show that our method effectively balances performance, model size, and speed. Code link: https://github.com/PRIS-CV/WFEN.

Physics-informed neural networks (PINNs) integrate fundamental physical principles with advanced data-driven techniques, driving significant advancements in scientific computing. However, PINNs face persistent challenges with stiffness in gradient flow, which limits their predictive capabilities. This paper presents an improved PINN (I-PINN) to mitigate gradient-related failures. The core of I-PINN is to combine the respective strengths of neural networks with an improved architecture and adaptive weights containingupper bounds. The capability to enhance accuracy by at least one order of magnitude and accelerate convergence, without introducing extra computational complexity relative to the baseline model, is achieved by I-PINN. Numerical experiments with a variety of benchmarks illustrate the improved accuracy and generalization of I-PINN. The supporting data and code are accessible at https://github.com/PanChengN/I-PINN.git, enabling broader research engagement., Comment: Elsevier-LaTeX v1.2, 26 pages with 12 figures

This paper presents the design and optimization of a LYSO crystal-based electromagnetic calorimeter (ECAL) for the DarkSHINE experiment, which aims to search for dark photon as potential dark force mediator. The ECAL design has been meticulously evaluated through comprehensive simulations, focusing on optimizing dimensions, material choices, and placement within the detector array to enhance sensitivity in search for dark photon signatures while balancing cost and performance. The concluded ECAL design, comprising 2.5$\times$2.5$\times$4 cm$^3$ LYSO crystals arranged in a 52.5$\times$52.5$\times$44 cm$^3$ structure, ensures high energy resolution and effective energy containment. The study also explored the energy distribution across different ECAL regions and established a dynamic range for energy measurements, with a 4 GeV limit per crystal deemed sufficient. Additionally, the radiation tolerance of ECAL components was assessed, confirming the sustainability of LYSO crystals and radiation-resistant silicon sensors.

Vector spaces over finite fields and Anzahl formulas of subspaces were studied by Wan (Geometry of Classical Groups over Finite Fields, Science Press, 2002). As a generalization, we study vector spaces and singular linear spaces over commutative rings and obtain some Anzahl formulas of subspaces. Moreover, we discuss arcs and caps by using these formulas., Comment: 20 pages

Marine fog poses a significant hazard to global shipping, necessitating effective detection and forecasting to reduce economic losses. In recent years, several machine learning (ML) methods have demonstrated superior detection accuracy compared to traditional meteorological methods. However, most of these works are developed on proprietary datasets, and the few publicly accessible datasets are often limited to simplistic toy scenarios for research purposes. To advance the field, we have collected nearly a decade's worth of multi-modal data related to continuous marine fog stages from four series of geostationary meteorological satellites, along with meteorological observations and numerical analysis, covering 15 marine regions globally where maritime fog frequently occurs. Through pixel-level manual annotation by meteorological experts, we present the most comprehensive marine fog detection and forecasting dataset to date, named M4Fog, to bridge ocean and atmosphere. The dataset comprises 68,000 "super data cubes" along four dimensions: elements, latitude, longitude and time, with a temporal resolution of half an hour and a spatial resolution of 1 kilometer. Considering practical applications, we have defined and explored three meaningful tracks with multi-metric evaluation systems: static or dynamic marine fog detection, and spatio-temporal forecasting for cloud images. Extensive benchmarking and experiments demonstrate the rationality and effectiveness of the construction concept for proposed M4Fog. The data and codes are available to whole researchers through cloud platforms to develop ML-driven marine fog solutions and mitigate adverse impacts on human activities.

This work aims to generate natural and diverse group motions of multiple humans from textual descriptions. While single-person text-to-motion generation is extensively studied, it remains challenging to synthesize motions for more than one or two subjects from in-the-wild prompts, mainly due to the lack of available datasets. In this work, we curate human pose and motion datasets by estimating pose information from large-scale image and video datasets. Our models use a transformer-based diffusion framework that accommodates multiple datasets with any number of subjects or frames. Experiments explore both generation of multi-person static poses and generation of multi-person motion sequences. To our knowledge, our method is the first to generate multi-subject motion sequences with high diversity and fidelity from a large variety of textual prompts., Comment: ECCV 2024. Project page: https://shanmy.github.io/Multi-Motion/

Inferring 3D human motion is fundamental in many applications, including understanding human activity and analyzing one's intention. While many fruitful efforts have been made to human motion prediction, most approaches focus on pose-driven prediction and inferring human motion in isolation from the contextual environment, thus leaving the body location movement in the scene behind. However, real-world human movements are goal-directed and highly influenced by the spatial layout of their surrounding scenes. In this paper, instead of planning future human motion in a 'dark' room, we propose a Multi-Condition Latent Diffusion network (MCLD) that reformulates the human motion prediction task as a multi-condition joint inference problem based on the given historical 3D body motion and the current 3D scene contexts. Specifically, instead of directly modeling joint distribution over the raw motion sequences, MCLD performs a conditional diffusion process within the latent embedding space, characterizing the cross-modal mapping from the past body movement and current scene context condition embeddings to the future human motion embedding. Extensive experiments on large-scale human motion prediction datasets demonstrate that our MCLD achieves significant improvements over the state-of-the-art methods on both realistic and diverse predictions., Comment: Accepted by IEEE Transactions on Image Processing

In Ref.~\cite{Guo:2021rre}, we proposed to replace the final dark matter (DM) particle in the semi-annihilation mode $\rm DM+DM\to antiDM+Higgs~boson$ with its $Z_{N\geq 3}$ companion, thus reducing DM number density without DM-nucleon scattering. In this work, we study the indirect detection signals from DM annihilation, the Higgs boson pair with one of them from the companion decay being on- or off- shell, depending on the DM-companion mass splitting. We generate the photon spectrum by using PYTHIA8 and study the properties of the spectrum, to find that the hard part of the spectrum in our model is mainly shaped by the direct Higgs boson and thus does not differ much from that of the conventional semi-annihilation mode. Using the Fermi-LAT data of white dwarfs, we derive the current limit of the DM annihilation cross section for ${\rm DM+DM\to companion^*+Higgs~ boson}$, and for the relatively light DM, it reaches the typical thermal cross section. However, for the TeV scale DM, we have to rely on the Cherenkov Telescope Array, which is able to rule out the whole parameter space except for the coannihilation region., Comment: 14 pages, 3 figures

We study the energy issue in critical collapse of a spherically symmetric scalar field. It is found that in critical collapse, the contribution from the material energy is greater than that from the gravitational energy. The quantity $m/r$ plays an important role in identifying the formation of apparent horizon in gravitational collapse, where $m$ is the Misner-Sharp mass and $r$ the areal radius. We observe that in critical collapse, the maximum value of $m/r$ fluctuates between $2/15$ and $4/15$. This denotes a large gap between critical collapse and black hole formation for which the criterion is $m/r=1/2$., Comment: 8 pages, 7 figures

Image-to-video (I2V) generation aims to create a video sequence from a single image, which requires high temporal coherence and visual fidelity. However, existing approaches suffer from inconsistency of character appearances and poor preservation of fine details. Moreover, they require a large amount of video data for training, which can be computationally demanding. To address these limitations, we propose PoseAnimate, a novel zero-shot I2V framework for character animation. PoseAnimate contains three key components: 1) a Pose-Aware Control Module (PACM) that incorporates diverse pose signals into text embeddings, to preserve character-independent content and maintain precise alignment of actions. 2) a Dual Consistency Attention Module (DCAM) that enhances temporal consistency and retains character identity and intricate background details. 3) a Mask-Guided Decoupling Module (MGDM) that refines distinct feature perception abilities, improving animation fidelity by decoupling the character and background. We also propose a Pose Alignment Transition Algorithm (PATA) to ensure smooth action transition. Extensive experiment results demonstrate that our approach outperforms the state-of-the-art training-based methods in terms of character consistency and detail fidelity. Moreover, it maintains a high level of temporal coherence throughout the generated animations., Comment: 10 pages, 5 figures

Open-vocabulary 3D scene understanding presents a significant challenge in computer vision, with wide-ranging applications in embodied agents and augmented reality systems. Existing methods adopt neurel rendering methods as 3D representations and jointly optimize color and semantic features to achieve rendering and scene understanding simultaneously. In this paper, we introduce Semantic Gaussians, a novel open-vocabulary scene understanding approach based on 3D Gaussian Splatting. Our key idea is to distill knowledge from 2D pre-trained models to 3D Gaussians. Unlike existing methods, we design a versatile projection approach that maps various 2D semantic features from pre-trained image encoders into a novel semantic component of 3D Gaussians, which is based on spatial relationship and need no additional training. We further build a 3D semantic network that directly predicts the semantic component from raw 3D Gaussians for fast inference. The quantitative results on ScanNet segmentation and LERF object localization demonstates the superior performance of our method. Additionally, we explore several applications of Semantic Gaussians including object part segmentation, instance segmentation, scene editing, and spatiotemporal segmentation with better qualitative results over 2D and 3D baselines, highlighting its versatility and effectiveness on supporting diverse downstream tasks., Comment: Project page: see https://semantic-gaussians.github.io

When deploying segmentation models in practice, it is critical to evaluate their behaviors in varied and complex scenes. Different from the previous evaluation paradigms only in consideration of global attribute variations (e.g. adverse weather), we investigate both local and global attribute variations for robustness evaluation. To achieve this, we construct a mask-preserved attribute editing pipeline to edit visual attributes of real images with precise control of structural information. Therefore, the original segmentation labels can be reused for the edited images. Using our pipeline, we construct a benchmark covering both object and image attributes (e.g. color, material, pattern, style). We evaluate a broad variety of semantic segmentation models, spanning from conventional close-set models to recent open-vocabulary large models on their robustness to different types of variations. We find that both local and global attribute variations affect segmentation performances, and the sensitivity of models diverges across different variation types. We argue that local attributes have the same importance as global attributes, and should be considered in the robustness evaluation of segmentation models. Code: https://github.com/PRIS-CV/Pascal-EA., Comment: CVPR 2024

We propose a Bernoulli-barycentric rational matrix collocation method for two-dimensional evolutionary partial differential equations (PDEs) with variable coefficients that combines Bernoulli polynomials with barycentric rational interpolations in time and space, respectively. The theoretical accuracy $O\left((2\pi)^{-N}+h_x^{d_x-1}+h_y^{d_y-1}\right)$ of our numerical scheme is proven, where $N$ is the number of basis functions in time, $h_x$ and $h_y$ are the grid sizes in the $x$, $y$-directions, respectively, and $0\leq d_x\leq \frac{b-a}{h_x},~0\leq d_y\leq\frac{d-c}{h_y}$. For the efficient solution of the relevant linear system arising from the discretizations, we introduce a class of dimension expanded preconditioners that take the advantage of structural properties of the coefficient matrices, and we present a theoretical analysis of eigenvalue distributions of the preconditioned matrices. The effectiveness of our proposed method and preconditioners are studied for solving some real-world examples represented by the heat conduction equation, the advection-diffusion equation, the wave equation and telegraph equations., Comment: 23 pages, 6 figures, 9 tables (update some contexts)

We study the collisions of two scalar wave packets in the asymptotically flat spacetime and asymptotically anti-de Sitter spacetime in spherical symmetry. An energy transfer formula is obtained, $y=Cm_{i}m_{o}/r$, where $y$ is the transferred energy in the collisions of the two wave packets, $m_i$ and $m_o$ are the Misner-Sharp energies for the ingoing and outgoing wave packets, respectively, $r$ is the areal radius and collision place, and $C=1.873$ and $C=1.875$ for the asymptotically flat spacetime and asymptotically anti-de Sitter spacetime circumstances, respectively. The formula is universal, independent of the initial profiles of the scalar fields., Comment: 8 pages, 9 figures

Attribute labeling at large scale is typically incomplete and partial, posing significant challenges to model optimization. Existing attribute learning methods often treat the missing labels as negative or simply ignore them all during training, either of which could hamper the model performance to a great extent. To overcome these limitations, in this paper we leverage the available vision-language knowledge to explicitly disclose the missing labels for enhancing model learning. Given an image, we predict the likelihood of each missing attribute label assisted by an off-the-shelf vision-language model, and randomly select to ignore those with high scores in training. Our strategy strikes a good balance between fully ignoring and negatifying the missing labels, as these high scores are found to be informative on revealing label ambiguity. Extensive experiments show that our proposed vision-language assisted loss can achieve state-of-the-art performance on the newly cleaned VAW dataset. Qualitative evaluation demonstrates the ability of the proposed method in predicting more complete attributes., Comment: Accepted by IEEE IC-NIDC 2023

Image editing approaches with diffusion models have been rapidly developed, yet their applicability are subject to requirements such as specific editing types (e.g., foreground or background object editing, style transfer), multiple conditions (e.g., mask, sketch, caption), and time consuming fine-tuning of diffusion models. For alleviating these limitations and realizing efficient real image editing, we propose a novel editing technique that only requires an input image and target text for various editing types including non-rigid edits without fine-tuning diffusion model. Our method contains three novelties:(I) Target-text Inversion Schedule (TTIS) is designed to fine-tune the input target text embedding to achieve fast image reconstruction without image caption and acceleration of convergence.(II) Progressive Transition Scheme applies progressive linear interpolation between target text embedding and its fine-tuned version to generate transition embedding for maintaining non-rigid editing capability.(III) Balanced Attention Module (BAM) balances the tradeoff between textual description and image semantics.By the means of combining self-attention map from reconstruction process and cross-attention map from transition process, the guidance of target text embeddings in diffusion process is optimized.In order to demonstrate editing capability, effectiveness and efficiency of the proposed BARET, we have conducted extensive qualitative and quantitative experiments. Moreover, results derived from user study and ablation study further prove the superiority over other methods., Comment: Accepted by AAAI2024

We demonstrate laser frequency stabilization using a high-Q MgF2 crystalline whispering gallery mode resonator coupled with a tapered fiber. We discovered that the tapered fiber, acting as a microcantilever, exhibits mechanical resonance characteristics that is capable of transmitting acoustic perturbations to the frequency locking loop. Both experimental and theoretical investigations into the influence of external acoustic waves on the coupling system were conducted. After acoustic isolation, the locked laser exhibits a minimum frequency noise of 0.4Hz2/Hz at 7kHz and an integral linewidth of 68Hz (0.1s integration time). Benefiting from the ultralow frequency noise of the stabilized laser, it achieves a minimum noise equivalent acoustic signal level of 4.76*10-4 Pa/Hz1/2. Our results not only facilitate the realization of ultralow noise lasers but also serves as a novel and sensitive photoacoustic detector.

Axion-like particles (ALPs) may undergo mixing with photons in the presence of astrophysical magnetic fields, leading to alterations in the observed high energy $\gamma$-ray spectra. In this study, we investigate the ALP-photon oscillation effect using the spectra of the blazar Mrk 421 over 15 observation periods measured by Major Atmospheric Gamma Imaging Cherenkov Telescopes (MAGIC) and Fermi Large Area Telescope (Fermi-LAT). Compared with previous studies, we generate mock data under the ALP hypothesis and employ the ${\rm CL_s}$ method to set constraints on the ALP parameters. This method is widely utilized in high energy experiments and avoids the exclusion of specific parameter regions where distinguishing between the null and ALP hypotheses is challenging. We find that the ALP-photon coupling $g_{a\gamma}$ is constrained to be smaller than $\sim 2\times10^{-11}$ GeV$^{-1}$ for ALP masses ranging from $10^{-9}$ eV to $10^{-7}$ eV at the 95\% confidence level. We also present the constraints derived from the TS distribution under the null hypothesis, which is commonly utilized in previous astrophysical ALP studies. Our results reveal that the combined constraints of all the periods obtained from both methods are consistent. However, the ${\rm CL_s}$ method remains effective in cases where the latter method fails to provide constraints for specific observation periods., Comment: 10 pages, 27 figures

Human parsing aims to segment each pixel of the human image with fine-grained semantic categories. However, current human parsers trained with clean data are easily confused by numerous image corruptions such as blur and noise. To improve the robustness of human parsers, in this paper, we construct three corruption robustness benchmarks, termed LIP-C, ATR-C, and Pascal-Person-Part-C, to assist us in evaluating the risk tolerance of human parsing models. Inspired by the data augmentation strategy, we propose a novel heterogeneous augmentation-enhanced mechanism to bolster robustness under commonly corrupted conditions. Specifically, two types of data augmentations from different views, i.e., image-aware augmentation and model-aware image-to-image transformation, are integrated in a sequential manner for adapting to unforeseen image corruptions. The image-aware augmentation can enrich the high diversity of training images with the help of common image operations. The model-aware augmentation strategy that improves the diversity of input data by considering the model's randomness. The proposed method is model-agnostic, and it can plug and play into arbitrary state-of-the-art human parsing frameworks. The experimental results show that the proposed method demonstrates good universality which can improve the robustness of the human parsing models and even the semantic segmentation models when facing various image common corruptions. Meanwhile, it can still obtain approximate performance on clean data., Comment: Accepted by IEEE Transactions on Image Processing (TIP)

Cell proliferation and migration highly relate to normal tissue self-healing, therefore it is highly significant for artificial controlling. Recently, vibrational strong coupling between biomolecules and Mid-infrared (MIR) light photons has been successfully used to modify in vitro bioreactions, neuronal signaling and even animal behavior. However, the synergistic effects from molecules to cells remains unclear, and the regulation of MIR on cells needs to be explained from the molecular level. Herein, the proliferation rate and migration capacity of fibroblasts were increased by 156% and 162.5%, respectively, by vibratory coupling of 5.6 micrometers photons with carbonyl groups in biomolecules. Through transcriptome sequencing analysis, the regulatory mechanism of infrared light in 5.6 micrometers was explained from the level of signal pathway and cell components. 5.6 micrometers optical high power lasers can regulate cell function through vibrational strong coupling while minimizing photothermal damage. This work not only sheds light on the non-thermal effect on MIR light-based on wound healing, but also provides new evidence to future frequency medicine., Comment: 20 pages, 5 figures

Despite the broad application of Machine Learning models as a Service (MLaaS), they are vulnerable to model stealing attacks. These attacks can replicate the model functionality by using the black-box query process without any prior knowledge of the target victim model. Existing stealing defenses add deceptive perturbations to the victim's posterior probabilities to mislead the attackers. However, these defenses are now suffering problems of high inference computational overheads and unfavorable trade-offs between benign accuracy and stealing robustness, which challenges the feasibility of deployed models in practice. To address the problems, this paper proposes Isolation and Induction (InI), a novel and effective training framework for model stealing defenses. Instead of deploying auxiliary defense modules that introduce redundant inference time, InI directly trains a defensive model by isolating the adversary's training gradient from the expected gradient, which can effectively reduce the inference computational cost. In contrast to adding perturbations over model predictions that harm the benign accuracy, we train models to produce uninformative outputs against stealing queries, which can induce the adversary to extract little useful knowledge from victim models with minimal impact on the benign performance. Extensive experiments on several visual classification datasets (e.g., MNIST and CIFAR10) demonstrate the superior robustness (up to 48% reduction on stealing accuracy) and speed (up to 25.4x faster) of our InI over other state-of-the-art methods. Our codes can be found in https://github.com/DIG-Beihang/InI-Model-Stealing-Defense., Comment: Accepted by ACM Multimedia 2023

We study the dynamics of the critical collapse of a spherically symmetric scalar field. Approximate analytic expressions for the metric functions and matter field in the large-radius region are obtained. In the central region, owing to the boundary conditions, the equation of motion for the scalar field is reduced to the flat-spacetime form., Comment: 8 pages, 5 figures

Hydrophobic domains provide specific microenvironment for essential functional activities in life. Herein, we studied how the coassembling of peptides with catecholamines regulate the hydrophobic domain-containing nanostructures for fluorescence enhancement. By peptide encoding and coassembling with catecholamines of different hydrophilicities, a series of hierarchical assembling systems were constructed. In combination with molecular dynamics simulation, we experimentally discovered the hydrophobic domain of chromophore microenvironment regulates the fluorescence of coassembled nanostructures. Our results shed light on the rational design of fluorescent bio-coassembled nanoprobes for biomedical applications., Comment: 19 pages, 5 figures

In this study, we explore the robustness of cooperative multi-agent reinforcement learning (c-MARL) against Byzantine failures, where any agent can enact arbitrary, worst-case actions due to malfunction or adversarial attack. To address the uncertainty that any agent can be adversarial, we propose a Bayesian Adversarial Robust Dec-POMDP (BARDec-POMDP) framework, which views Byzantine adversaries as nature-dictated types, represented by a separate transition. This allows agents to learn policies grounded on their posterior beliefs about the type of other agents, fostering collaboration with identified allies and minimizing vulnerability to adversarial manipulation. We define the optimal solution to the BARDec-POMDP as an ex post robust Bayesian Markov perfect equilibrium, which we proof to exist and weakly dominates the equilibrium of previous robust MARL approaches. To realize this equilibrium, we put forward a two-timescale actor-critic algorithm with almost sure convergence under specific conditions. Experimentation on matrix games, level-based foraging and StarCraft II indicate that, even under worst-case perturbations, our method successfully acquires intricate micromanagement skills and adaptively aligns with allies, demonstrating resilience against non-oblivious adversaries, random allies, observation-based attacks, and transfer-based attacks.

In this paper, we address a highly challenging yet critical task: unsupervised long-term person re-identification with clothes change. Existing unsupervised person re-id methods are mainly designed for short-term scenarios and usually rely on RGB cues so that fail to perceive feature patterns that are independent of the clothes. To crack this bottleneck, we propose a silhouette-driven contrastive learning (SiCL) method, which is designed to learn cross-clothes invariance by integrating both the RGB cues and the silhouette information within a contrastive learning framework. To our knowledge, this is the first tailor-made framework for unsupervised long-term clothes change \reid{}, with superior performance on six benchmark datasets. We conduct extensive experiments to evaluate our proposed SiCL compared to the state-of-the-art unsupervised person reid methods across all the representative datasets. Experimental results demonstrate that our proposed SiCL significantly outperforms other unsupervised re-id methods.

Charge transfer in type-II heterostructures plays important roles in determining device performance for photovoltaic and photocatalytic applications. However, current theoretical studies of charge transfer process don't consider the effects of operating conditions such as illuminations and yield systemically larger interlayer transfer time of hot electrons in MoS2/WS2 compared to experimental results. Here in this work, we propose a general picture that, illumination can induce interfacial dipoles in type-II heterostructures, which can accelerate hot carrier transfer by reducing the energy difference between the electronic states in separate materials and enhancing the nonadiabatic couplings. Using the first-principles calculations and the ab-initio nonadiabatic molecular dynamics, we demonstrate this picture using MoS2/WS2 as a prototype. The calculated characteristic time for the interlayer transfer (60 fs) and the overall relaxation (700 fs) processes of hot electrons is in good agreement with the experiments. We further find that illumination mainly affects the ultrafast interlayer transfer process but has little effects on the relatively slow intralayer relaxation process. Therefore, the overall relaxation process of hot electrons has a saturated time with increased illumination strengths. The illumination-accelerated charge transfer is expected to universally exist in type-II heterostructures.

Illumination has been long known to affect semiconductor defect properties during either growth or operating process. Current theories of studying the illumination effects on defects usually have the assumption of unaffected formation energies of neutral defects as well as defect transition energy levels, and use the quasi-Fermi levels to describe behaviors of excess carriers with conclusions at variance. In this work, we first propose a method to simulate steady illumination conditions, based on which we demonstrate that formation energies of neutral defects and defect transition energy levels are insensitive to illumination. Then, we show that optical and thermal excitation of electrons can be seen equivalent with each other to reach a steady electron distribution in a homogeneous semiconductor. Consequently, the electron distribution can be characterized using just one effective temperature T' and one universal Fermi level E_F' for a homogeneous semiconductor under continuous and steady illuminations, which can be seen as a combination of quasi-equilibrium electron system with T' and a lattice system with T. Using the new concepts, we uncover the universal mechanisms of illumination effects on charged defects by treating the band edge states explicitly in the same footing as the defect states. We find that the formation energies of band edge 'defect' states shift with increased T' of electrons, thus affecting the E_F', changing defect ionic probabilities, and affecting concentrations of charged defects. We apply our theory to study the illumination effects on the doping behaviors in GaN:Mg and CdTe:Sb, obtaining results in accordance with experimental observations. More interesting experimental defect-related phenomena under steady illuminations are expected to be understood from our theory.

This paper presents a framework for efficient 3D clothed avatar reconstruction. By combining the advantages of the high accuracy of optimization-based methods and the efficiency of learning-based methods, we propose a coarse-to-fine way to realize a high-fidelity clothed avatar reconstruction (CAR) from a single image. At the first stage, we use an implicit model to learn the general shape in the canonical space of a person in a learning-based way, and at the second stage, we refine the surface detail by estimating the non-rigid deformation in the posed space in an optimization way. A hyper-network is utilized to generate a good initialization so that the convergence o f the optimization process is greatly accelerated. Extensive experiments on various datasets show that the proposed CAR successfully produces high-fidelity avatars for arbitrarily clothed humans in real scenes.

The main challenge of monocular 3D object detection is the accurate localization of 3D center. Motivated by a new and strong observation that this challenge can be remedied by a 3D-space local-grid search scheme in an ideal case, we propose a stage-wise approach, which combines the information flow from 2D-to-3D (3D bounding box proposal generation with a single 2D image) and 3D-to-2D (proposal verification by denoising with 3D-to-2D contexts) in a top-down manner. Specifically, we first obtain initial proposals from off-the-shelf backbone monocular 3D detectors. Then, we generate a 3D anchor space by local-grid sampling from the initial proposals. Finally, we perform 3D bounding box denoising at the 3D-to-2D proposal verification stage. To effectively learn discriminative features for denoising highly overlapped proposals, this paper presents a method of using the Perceiver I/O model to fuse the 3D-to-2D geometric information and the 2D appearance information. With the encoded latent representation of a proposal, the verification head is implemented with a self-attention module. Our method, named as MonoXiver, is generic and can be easily adapted to any backbone monocular 3D detectors. Experimental results on the well-established KITTI dataset and the challenging large-scale Waymo dataset show that MonoXiver consistently achieves improvement with limited computation overhead.