Search

Video quality assessment (VQA) is a crucial task in the development of video compression standards, as it directly impacts the viewer experience. This paper presents the results of the Compressed Video Quality Assessment challenge, held in conjunction with the Advances in Image Manipulation (AIM) workshop at ECCV 2024. The challenge aimed to evaluate the performance of VQA methods on a diverse dataset of 459 videos, encoded with 14 codecs of various compression standards (AVC/H.264, HEVC/H.265, AV1, and VVC/H.266) and containing a comprehensive collection of compression artifacts. To measure the methods performance, we employed traditional correlation coefficients between their predictions and subjective scores, which were collected via large-scale crowdsourced pairwise human comparisons. For training purposes, participants were provided with the Compressed Video Quality Assessment Dataset (CVQAD), a previously developed dataset of 1022 videos. Up to 30 participating teams registered for the challenge, while we report the results of 6 teams, which submitted valid final solutions and code for reproducing the results. Moreover, we calculated and present the performance of state-of-the-art VQA methods on the developed dataset, providing a comprehensive benchmark for future research. The dataset, results, and online leaderboard are publicly available at https://challenges.videoprocessing.ai/challenges/compressedvideo-quality-assessment.html.

Ventilated acoustic resonator(VAR), a type of acoustic metamaterial, emerge as an alternative for sound attenuation in environments that require ventilation, owing to its excellent low-frequency attenuation performance and flexible shape adaptability. However, due to the non-linear acoustic responses of VARs, the VAR designs are generally obtained within a limited parametrized design space, and the design relies on the iteration of the numerical simulation which consumes a considerable amount of computational time and resources. This paper proposes an acoustic response-encoded variational autoencoder (AR-VAE), a novel variational autoencoder-based generative design model for the efficient and accurate inverse design of VAR even with non-parametrized designs. The AR-VAE matches the high-dimensional acoustic response with the VAR cross-section image in the dimension-reduced latent space, which enables the AR-VAE to generate various non-parametrized VAR cross-section images with the target acoustic response. AR-VAE generates non-parameterized VARs from target acoustic responses, which show a 25-fold reduction in mean squared error compared to conventional deep learning-based parameter searching methods while exhibiting lower average mean squared error and peak frequency variance. By combining the inverse-designed VARs by AR-VAE, multi-cavity VAR was devised for broadband and multitarget peak frequency attenuation. The proposed design method presents a new approach for structural inverse-design with a high-dimensional non-linear physical response.

Relativistic polarized electron beams can find applications in broad areas of fundamental physics. Here, we propose for the first time that electron spin polarization can be realized efficiently via collective beam-target interactions. When a relativistic unpolarized electron beam is incident onto the surface of a solid target with a grazing angle, strong magnetic fields are induced at the target surface due to the formation of a high reflux of target electrons. This results in violent beam self-focusing and corresponding beam density increase via magnetic pinching. The pinched dense beam in turn further enhances the magnetic fields to the level of a few Giga-Gauss, which is high enough to trigger strong synchrotron radiation of ultrarelativistic electrons. During the interaction, electron spin polarization develops along the magnetic field direction, which is achieved via radiative spin flips in the quantum radiation-dominated regime. As a consequence, the incident electron beam can be effectively polarized via the spin-dependent radiation reaction, for example, the mean polarization of electrons with energy less than 2 GeV can reach above 50% for an initial 5GeV beam. This provides a robust way for the development of polarized electron sources.

We present an inverse image-formation module that can enhance the robustness of existing visual SLAM pipelines for casually captured scenarios. Casual video captures often suffer from motion blur and varying appearances, which degrade the final quality of coherent 3D visual representation. We propose integrating the physical imaging into the SLAM system, which employs linear HDR radiance maps to collect measurements. Specifically, individual frames aggregate images of multiple poses along the camera trajectory to explain prevalent motion blur in hand-held videos. Additionally, we accommodate per-frame appearance variation by dedicating explicit variables for image formation steps, namely white balance, exposure time, and camera response function. Through joint optimization of additional variables, the SLAM pipeline produces high-quality images with more accurate trajectories. Extensive experiments demonstrate that our approach can be incorporated into recent visual SLAM pipelines using various scene representations, such as neural radiance fields or Gaussian splatting., Comment: ECCV 2024

Coffee is one of the most valuable primary commodities. Despite this, the common selection technique of green coffee beans relies on personnel visual inspection, which is labor-intensive and subjective. Therefore, an efficient way to evaluate the quality of beans is needed. In this paper, we demonstrate a site-independent approach to find site-specific color features of the seed coat in qualified green coffee beans. We then propose two evaluation schemes for green coffee beans based on this site-specific color feature of qualified beans. Due to the site-specific properties of these color features, machine learning classifiers indicate that compared with the existing evaluation schemes of beans, our evaluation schemes have the advantages of being simple, having less computational costs, and having universal applicability. Finally, this site-specific color feature can distinguish qualified beans from different growing sites. Moreover, this function can prevent cheating in the coffee business and is unique to our evaluation scheme of beans., Comment: 21 pages, 7 figures

We present a study of the semileptonic decay $D^0\rightarrow \pi^-\pi^0e^{+}\nu_{e}$ using an $e^+e^-$ annihilation data sample of $7.93~\mathrm{fb}^{-1}$ collected at the center-of-mass energy of 3.773 GeV with the BESIII detector. The branching fraction of $D^0\to \rho(770)^-e^+\nu_e$ is measured to be $(1.439 \pm 0.033(\rm stat.) \pm 0.027(\rm syst.)) \times10^{-3}$, which is a factor 1.6 more precise than previous measurements. By performing an amplitude analysis, we measure the hadronic form-factor ratios of $D^0\to \rho(770)^-e^+\nu_e$ at $q^2=0$ assuming the single-pole-dominance parametrization: $r_{V}=V(0)/A_1(0)=1.548\pm0.079(\rm stat.)\pm0.041(\rm syst.)$ and $r_{2}=A_2(0)/A_1(0)=0.823\pm0.056(\rm stat.)\pm0.026(\rm syst.)$., Comment: 12 pages, 3 figures

Deep learning-based person re-identification (re-id) models are widely employed in surveillance systems and inevitably inherit the vulnerability of deep networks to adversarial attacks. Existing attacks merely consider cross-dataset and cross-model transferability, ignoring the cross-test capability to perturb models trained in different domains. To powerfully examine the robustness of real-world re-id models, the Meta Transferable Generative Attack (MTGA) method is proposed, which adopts meta-learning optimization to promote the generative attacker producing highly transferable adversarial examples by learning comprehensively simulated transfer-based cross-model\&dataset\&test black-box meta attack tasks. Specifically, cross-model\&dataset black-box attack tasks are first mimicked by selecting different re-id models and datasets for meta-train and meta-test attack processes. As different models may focus on different feature regions, the Perturbation Random Erasing module is further devised to prevent the attacker from learning to only corrupt model-specific features. To boost the attacker learning to possess cross-test transferability, the Normalization Mix strategy is introduced to imitate diverse feature embedding spaces by mixing multi-domain statistics of target models. Extensive experiments show the superiority of MTGA, especially in cross-model\&dataset and cross-model\&dataset\&test attacks, our MTGA outperforms the SOTA methods by 21.5\% and 11.3\% on mean mAP drop rate, respectively. The code of MTGA will be released after the paper is accepted.

We study the CP asymmetries of the rare top-quark decays $t \to c \gamma$ and $t \to cg$ in the aligned two-Higgs-doublet model (A2HDM), which is generically characterized by new sources of CP violation beyond the Standard Model (SM). Specifically, the branching ratios and CP asymmetries of these rare top-quark decays are explicitly formulated, with an emphasis on the origins of weak and strong phases in the A2HDM. Taking into account the most relevant constraints on this model, we evaluate the variations of these observables with respect to the model parameters. It is found that the branching ratios of $t \to c \gamma$ and $t \to cg$ decays can maximally reach up to $1.47\times10^{-10}$ and $4.86\times10^{-9}$ respectively, which are about four and three orders of magnitude higher than the corresponding SM predictions. While the branching ratios are almost independent of the relative phase $\varphi$ between the two alignment parameters $\varsigma_u$ and $\varsigma_d$ within the allowed parameter space, the CP asymmetries are found to be very sensitive to $\varphi$. When the two alignment parameters are complex with a non-zero $\varphi$ varied within the range $[50^\circ,150^\circ]$, the magnitudes of the CP asymmetries can be significantly enhanced relative to both the SM and the real case. In particular, the maximum absolute values of the CP asymmetries can even reach up to $\mathcal{O}(1)$ for these two decay modes, in the range $\varphi \in [70^\circ,100^\circ]$. These interesting observations could be utilized to discriminate the SM and the different scenarios of the A2HDM., Comment: 46 pages, 12 figures, and 3 tables

Scene coordinate regression (SCR) methods have emerged as a promising area of research due to their potential for accurate visual localization. However, many existing SCR approaches train on samples from all image regions, including dynamic objects and texture-less areas. Utilizing these areas for optimization during training can potentially hamper the overall performance and efficiency of the model. In this study, we first perform an in-depth analysis to validate the adverse impacts of these areas. Drawing inspiration from our analysis, we then introduce an error-guided feature selection (EGFS) mechanism, in tandem with the use of the Segment Anything Model (SAM). This mechanism seeds low reprojection areas as prompts and expands them into error-guided masks, and then utilizes these masks to sample points and filter out problematic areas in an iterative manner. The experiments demonstrate that our method outperforms existing SCR approaches that do not rely on 3D information on the Cambridge Landmarks and Indoor6 datasets., Comment: ECCV2024

Recent advances in diffusion models have significantly enhanced the cotrollable generation of streetscapes for and facilitated downstream perception and planning tasks. However, challenges such as maintaining temporal coherence, generating long videos, and accurately modeling driving scenes persist. Accordingly, we propose DreamForge, an advanced diffusion-based autoregressive video generation model designed for the long-term generation of 3D-controllable and extensible video. In terms of controllability, our DreamForge supports flexible conditions such as text descriptions, camera poses, 3D bounding boxes, and road layouts, while also providing perspective guidance to produce driving scenes that are both geometrically and contextually accurate. For consistency, we ensure inter-view consistency through cross-view attention and temporal coherence via an autoregressive architecture enhanced with motion cues. Codes will be available at https://github.com/PJLab-ADG/DriveArena., Comment: Second place solution for W-CODA-Track2

Rare-earth tetraborides ($R$B$_{4}$) have attracted a lot of recent attention due to their intriguing electronic, magnetic, and topological properties. We have theoretically investigated topological properties of PrB$_{4}$, which is unique among $R$B$_{4}$ family due to its ferromagnetic ground state. We have discovered that PrB$_{4}$ is an intrinsic magnetic Weyl system possessing multiple topological band crossings with various chiral charges. Density-functional-theory band calculations combined with tight-binding band analysis reveal large Fermi-arc surface states, which are characteristic fingerprints of Weyl fermions. Anomalous Hall conductivity is estimated to be very large, ranging from 500 to 1000 ($\Omega \cdot$cm)$^{-1}$ near the Fermi level, which also demonstrates the topological Weyl character of ferromagnetic PrB$_{4}$. These findings suggest that PrB$_{4}$, being a potential candidate of magnetic Weyl system, would be a promising rare-earth topological system for applications to next-generation spintronic and photonic devices., Comment: 7 pages, 6 figures

Recently, low-frequency mechanical energy harvesters based on solid-liquid contact electrification have garnered widespread attention for their unique advantages in wear resistance, high charge transfer efficiency, and novel insights into electron-ion interactions at the solid-liquid interface, particularly in material identification. Hence, we designed an robust and efficient water cup triboelectric nanogenerator (WC-TENG) that only uses ordinary drinking water and plastic water cups as primary materials, achieving high-efficiency power output while eliminating the need for metal electrodes and effectively addressing the issue of corrosion in generator components. Experimental results indicate that, at an operating frequency of 2 Hz, the WC-TENG generates an open-circuit voltage (Voc) of 249.71 V, a short-circuit current (Isc) of 4.21 uA, and a transferred charge (Qsc) of 188.85 nC. The WC-TENG demonstrates long-term stability and reliability, maintaining stable voltage output over 1500 s. Moreover, the WC-TENG maintains stable performance under high humidity conditions, and its output enhances with increasing temperature, underscoring its robustness and adaptability for diverse environmental applications. Furthermore, the introduction of ethanol disrupts the potential balance at the solid-liquid interface by impeding electron transfer and reducing the WC-TENG's electrical output, but as the ethanol volatilizes, the device gradually returns to its original potential state, demonstrating its potential as a selective ethanol sensor. This design not only advances the development of corrosion-resistant, high-performance energy harvesters but also opens up new possibilities for low-cost, sustainable, and environmentally adaptable sensing technologies., Comment: 13,5798

Wave energy harvesting is critical for advancing the development and utilization of marine resources. In this study, we present a novel multi-roller structure triboelectric nanogenerator (MR-TENG) designed specifically for efficient water wave energy harvesting. The MR-TENG leverages a coupled multi-roller design to significantly enhance its energy harvesting capabilities. The triboelectric layers are composed of polytetrafluoroethylene (PTFE) film and paper, with a grid copper electrode serving as the conductive element. Through an optimized energy output strategy, a single MR-TENG is capable of generating 602.045 {\mu}J of electrical energy within 100 s. The device achieves a short-circuit current (Isc) of approximately 2.06 {\mu}A and an open-circuit voltage (Voc) of around 166 V. We further investigate the impact of different connection modes, including parallel and series configurations, on the performance of MR-TENG arrays. Notably, the electrical energy produced by the MR-TENG array is sufficient to power 40 blue commercial light-emitting diodes (LEDs). This research not only introduces a versatile optimization approach and energy management strategy for roller-structured TENGs but also contributes significantly to the advancement of ocean-based TENG technology., Comment: 14.5371

Cross-domain recommendation (CDR) aims to improve recommendation accuracy in sparse domains by transferring knowledge from data-rich domains. However, existing CDR methods often assume the availability of user-item interaction data across domains, overlooking user privacy concerns. Furthermore, these methods suffer from performance degradation in scenarios with sparse overlapping users, as they typically depend on a large number of fully shared users for effective knowledge transfer. To address these challenges, we propose a Federated Prototype-based Contrastive Learning (CL) method for Privacy-Preserving CDR, named FedPCL-CDR. This approach utilizes non-overlapping user information and prototypes to improve multi-domain performance while protecting user privacy. FedPCL-CDR comprises two modules: local domain (client) learning and global server aggregation. In the local domain, FedPCL-CDR clusters all user data to learn representative prototypes, effectively utilizing non-overlapping user information and addressing the sparse overlapping user issue. It then facilitates knowledge transfer by employing both local and global prototypes returned from the server in a CL manner. Simultaneously, the global server aggregates representative prototypes from local domains to learn both local and global prototypes. The combination of prototypes and federated learning (FL) ensures that sensitive user data remains decentralized, with only prototypes being shared across domains, thereby protecting user privacy. Extensive experiments on four CDR tasks using two real-world datasets demonstrate that FedPCL-CDR outperforms the state-of-the-art baselines.

Building on VeriX (Verified eXplainability, arXiv:2212.01051), a system for producing optimal verified explanations for machine learning model outputs, we present VeriX+, which significantly improves both the size and the generation time of verified explanations. We introduce a bound propagation-based sensitivity technique to improve the size, and a binary search-based traversal with confidence ranking for improving time -- the two techniques are orthogonal and can be used independently or together. We also show how to adapt the QuickXplain (Junker 2004) algorithm to our setting to provide a trade-off between size and time. Experimental evaluations on standard benchmarks demonstrate significant improvements on both metrics, e.g., a size reduction of 38% on the GTSRB dataset and a time reduction of 90% on MNIST. We also explore applications of our verified explanations and show that explanation size is a useful proxy for both incorrectness detection and out-of-distribution detection.

The IW And phenomenon in cataclysmic variables presents a significant challenge to the accretion disk instability model. Using photometric data from the All-Sky Automated Survey for Supernovae, the Zwicky Transient Facility, and the Transiting Exoplanet Survey Satellite, we identify Karachurin 12 as a new IW And-type object with a cycle period of 35.69(3) days. We also report for the first time that Karachurin 12 is a negative superhump (NSH) system featuring a precessing tilted disk, with precession, orbital, and NSH periods of 4.9588(2) days, 0.3168895(13) days, and 0.2979861(8) days, respectively. Our analysis, using dips as indexes and NSHs as probes, reveals diverse cycle patterns in Karachurin 12, with NSH amplitude varying throughout the cycle. Analyses of NSH behaviour using multiple methods shows that the amplitude decreases with increasing outbursts and increases with weakening outbursts, which we suggest is related to changes in the radius of the accretion disk. The mass transfer outburst model fails to explain the observed NSH amplitude variations, whereas the tilted thermally unstable disk model accounts for most of the observed cycles and dip patterns, particularly the disappearance of the IW And phenomenon when NSHs become undetectable. However, no significant changes in the NSH period were observed. These findings suggest a potential link between the IW And phenomenon and a tilted disk. Further improvements in simulations are needed to better understand the detailed dynamics of these cycles., Comment: 22 pages, 9 figures and 3 tables

The potential for higher-resolution image generation using pretrained diffusion models is immense, yet these models often struggle with issues of object repetition and structural artifacts especially when scaling to 4K resolution and higher. We figure out that the problem is caused by that, a single prompt for the generation of multiple scales provides insufficient efficacy. In response, we propose HiPrompt, a new tuning-free solution that tackles the above problems by introducing hierarchical prompts. The hierarchical prompts offer both global and local guidance. Specifically, the global guidance comes from the user input that describes the overall content, while the local guidance utilizes patch-wise descriptions from MLLMs to elaborately guide the regional structure and texture generation. Furthermore, during the inverse denoising process, the generated noise is decomposed into low- and high-frequency spatial components. These components are conditioned on multiple prompt levels, including detailed patch-wise descriptions and broader image-level prompts, facilitating prompt-guided denoising under hierarchical semantic guidance. It further allows the generation to focus more on local spatial regions and ensures the generated images maintain coherent local and global semantics, structures, and textures with high definition. Extensive experiments demonstrate that HiPrompt outperforms state-of-the-art works in higher-resolution image generation, significantly reducing object repetition and enhancing structural quality., Comment: https://liuxinyv.github.io/HiPrompt/

In stereo matching, CNNs have traditionally served as the predominant architectures. Although Transformer-based stereo models have been studied recently, their performance still lags behind CNN-based stereo models due to the inherent data scarcity issue in the stereo matching task. In this paper, we propose Masked Image Modeling Distilled Stereo matching model, termed MaDis-Stereo, that enhances locality inductive bias by leveraging Masked Image Modeling (MIM) in training Transformer-based stereo model. Given randomly masked stereo images as inputs, our method attempts to conduct both image reconstruction and depth prediction tasks. While this strategy is beneficial to resolving the data scarcity issue, the dual challenge of reconstructing masked tokens and subsequently performing stereo matching poses significant challenges, particularly in terms of training stability. To address this, we propose to use an auxiliary network (teacher), updated via Exponential Moving Average (EMA), along with the original stereo model (student), where teacher predictions serve as pseudo supervisory signals to effectively distill knowledge into the student model. State-of-the-arts performance is achieved with the proposed method on several stereo matching such as ETH3D and KITTI 2015. Additionally, to demonstrate that our model effectively leverages locality inductive bias, we provide the attention distance measurement.

Transfer learning based on full fine-tuning (FFT) of the pre-trained encoder and task-specific decoder becomes increasingly complex as deep models grow exponentially. Parameter efficient fine-tuning (PEFT) approaches using adapters consisting of small learnable layers have emerged as an alternative to FFT, achieving comparable performance while maintaining high training efficiency. However, the inflexibility of the adapter with respect to input instances limits its capability of learning task-specific information in diverse downstream tasks. In this paper, we propose a novel PEFT approach, input-Conditioned transFormer, termed iConFormer, that leverages a dynamic adapter conditioned on the input instances. To secure flexible learning ability on input instances in various downstream tasks, we introduce an input-Conditioned Network (iCoN) in the dynamic adapter that enables instance-level feature transformation. To be specific, iCoN generates channel-wise convolutional kernels for each feature and transform it using adaptive convolution process to effectively capture task-specific and fine-grained details tailor to downstream tasks. Experimental results demonstrate that by tuning just 1.6% to 2.8% of the Transformer backbone parameters, iConFormer achieves performance comparable to FFT in monocular depth estimation and semantic segmentation, while outperforming it in image classification and instance segmentation. Also, the proposed method consistently outperforms recent PEFT methods for all the tasks mentioned above.

Unsupervised Domain Adaptation (UDA) endeavors to bridge the gap between a model trained on a labeled source domain and its deployment in an unlabeled target domain. However, current high-performance models demand significant resources, resulting in prohibitive deployment costs and highlighting the need for small yet effective models. For UDA of lightweight models, Knowledge Distillation (KD) in a Teacher-Student framework can be a common approach, but we find that domain shift in UDA leads to a significant increase in non-salient parameters in the teacher model, degrading model's generalization ability and transferring misleading information to the student model. Interestingly, we observed that this phenomenon occurs considerably less in the student model. Driven by this insight, we introduce Collaborative Learning, a method that updates the teacher's non-salient parameters using the student model and at the same time enhance the student's performance using the updated teacher model. Experiments across various tasks and datasets show consistent performance improvements for both student and teacher models. For example, in semantic segmentation, CLDA achieves an improvement of +0.7% mIoU for teacher and +1.4% mIoU for student compared to the baseline model in the GTA to Cityscapes. In the Synthia to Cityscapes, it achieves an improvement of +0.8% mIoU for teacher and +2.0% mIoU for student.

In the effective field theory, the massless dark photon $\gamma'$ can only couple with the Standard Model particle through operators of dimension higher than four, thereby offering a high sensitivity to the new physics energy scale. Using $7.9~\rm{fb^{-1}}$ of $e^+e^-$ collision data collected at $\sqrt{s}=3.773$ GeV with the BESIII detector at the BEPCII collider, we measure the effective flavor-changing neutral current coupling of $cu\gamma'$ in $D^0\to\omega\gamma'$ and $D^0\to\gamma\gamma'$ processes to search for the massless dark photon. No significant signals are observed, and the upper limits at the 90% confidence level on the massless dark photon branching fraction are set to be $1.1\times10^{-5}$ and $2.0\times10^{-6}$ for $D^0\to\omega\gamma'$ and $D^0\to\gamma\gamma'$, respectively. These results provide the most stringent constraint on the new physics energy scale associated with $cu\gamma'$ coupling in the world, with the new physics energy scale related parameter $|\mathbb{C}|^2+|\mathbb{C}_5|^2<8.2\times10^{-17}~\rm{GeV}^{-2}$ at the 90% confidence level, playing a unique role in the dark sector search with the charm sector., Comment: 9 pages, 4 figures

Unlike other vision tasks where Transformer-based approaches are becoming increasingly common, stereo depth estimation is still dominated by convolution-based approaches. This is mainly due to the limited availability of real-world ground truth for stereo matching, which is a limiting factor in improving the performance of Transformer-based stereo approaches. In this paper, we propose UniTT-Stereo, a method to maximize the potential of Transformer-based stereo architectures by unifying self-supervised learning used for pre-training with stereo matching framework based on supervised learning. To be specific, we explore the effectiveness of reconstructing features of masked portions in an input image and at the same time predicting corresponding points in another image from the perspective of locality inductive bias, which is crucial in training models with limited training data. Moreover, to address these challenging tasks of reconstruction-and-prediction, we present a new strategy to vary a masking ratio when training the stereo model with stereo-tailored losses. State-of-the-art performance of UniTT-Stereo is validated on various benchmarks such as ETH3D, KITTI 2012, and KITTI 2015 datasets. Lastly, to investigate the advantages of the proposed approach, we provide a frequency analysis of feature maps and the analysis of locality inductive bias based on attention maps.

Masked Image Modeling (MIM) techniques have redefined the landscape of computer vision, enabling pre-trained models to achieve exceptional performance across a broad spectrum of tasks. Despite their success, the full potential of MIM-based methods in dense prediction tasks, particularly in depth estimation, remains untapped. Existing MIM approaches primarily rely on single-image inputs, which makes it challenging to capture the crucial structured information, leading to suboptimal performance in tasks requiring fine-grained feature representation. To address these limitations, we propose SG-MIM, a novel Structured knowledge Guided Masked Image Modeling framework designed to enhance dense prediction tasks by utilizing structured knowledge alongside images. SG-MIM employs a lightweight relational guidance framework, allowing it to guide structured knowledge individually at the feature level rather than naively combining at the pixel level within the same architecture, as is common in traditional multi-modal pre-training methods. This approach enables the model to efficiently capture essential information while minimizing discrepancies between pre-training and downstream tasks. Furthermore, SG-MIM employs a selective masking strategy to incorporate structured knowledge, maximizing the synergy between general representation learning and structured knowledge-specific learning. Our method requires no additional annotations, making it a versatile and efficient solution for a wide range of applications. Our evaluations on the KITTI, NYU-v2, and ADE20k datasets demonstrate SG-MIM's superiority in monocular depth estimation and semantic segmentation.

Neural network solvers for partial differential equations (PDEs) have made significant progress, yet they continue to face challenges related to data scarcity and model robustness. Traditional data augmentation methods, which leverage symmetry or invariance, impose strong assumptions on physical systems that often do not hold in dynamic and complex real-world applications. To address this research gap, this study introduces a universal learning strategy for neural network PDEs, named Systematic Model Augmentation for Robust Training (SMART). By focusing on challenging and improving the model's weaknesses, SMART reduces generalization error during training under data-scarce conditions, leading to significant improvements in prediction accuracy across various PDE scenarios. The effectiveness of the proposed method is demonstrated through both theoretical analysis and extensive experimentation. The code will be available.

The manipulation and transformation of quantum resources are key parts of quantum mechanics. Among them, asymmetry is one of the most useful operational resources, which is widely used in quantum clocks, quantum metrology, and other tasks. Recent studies have shown that the asymmetry of quantum states can be significantly amplified with the assistance of correlating catalysts which are finite-dimensional auxiliaries. In the experiment, we perform translationally invariant operations, ensuring that the asymmetric resources of the entire system remain non-increasing, on a composite system composed of a catalytic system and a quantum system. The experimental results demonstrate an asymmetry amplification of 0.0172\pm0.0022 in the system following the catalytic process. Our work showcases the potential of quantum catalytic processes and is expected to inspire further research in the field of quantum resource theories., Comment: 17pages,7figures

We introduce OLMoE, a fully open, state-of-the-art language model leveraging sparse Mixture-of-Experts (MoE). OLMoE-1B-7B has 7 billion (B) parameters but uses only 1B per input token. We pretrain it on 5 trillion tokens and further adapt it to create OLMoE-1B-7B-Instruct. Our models outperform all available models with similar active parameters, even surpassing larger ones like Llama2-13B-Chat and DeepSeekMoE-16B. We present various experiments on MoE training, analyze routing in our model showing high specialization, and open-source all aspects of our work: model weights, training data, code, and logs., Comment: 61 pages (24 main), 36 figures, 14 tables

This paper develops a novel multi-relaxation-time (MRT) lattice Boltzmann method (LBM) for solving the volume averaged Navier-Stokes equations (VANSE). Different from the approach given in [1], this method is rooted in the widely-adopted density equilibrium distribution, which provides possibility for simulating scenarios where fluid compressibility cannot be ignored, e.g., thermal and multiphase flows. The Chapman-Enskog analysis is presented to confirm the consistency of this scheme at macroscopic level. Some numerical experiments further demonstrate that it achieves second-order convergence and exhibits better numerical performance over previous schemes as reported [2-4]., Comment: 9 pages

Panoptic 3D reconstruction from a monocular video is a fundamental perceptual task in robotic scene understanding. However, existing efforts suffer from inefficiency in terms of inference speed and accuracy, limiting their practical applicability. We present EPRecon, an efficient real-time panoptic 3D reconstruction framework. Current volumetric-based reconstruction methods usually utilize multi-view depth map fusion to obtain scene depth priors, which is time-consuming and poses challenges to real-time scene reconstruction. To end this, we propose a lightweight module to directly estimate scene depth priors in a 3D volume for reconstruction quality improvement by generating occupancy probabilities of all voxels. In addition, to infer richer panoptic features from occupied voxels, EPRecon extracts panoptic features from both voxel features and corresponding image features, obtaining more detailed and comprehensive instance-level semantic information and achieving more accurate segmentation results. Experimental results on the ScanNetV2 dataset demonstrate the superiority of EPRecon over current state-of-the-art methods in terms of both panoptic 3D reconstruction quality and real-time inference. Code is available at https://github.com/zhen6618/EPRecon.

The success of Large Language Models (LLMs) relies heavily on the huge amount of pre-training data learned in the pre-training phase. The opacity of the pre-training process and the training data causes the results of many benchmark tests to become unreliable. If any model has been trained on a benchmark test set, it can seriously hinder the health of the field. In order to automate and efficiently test the capabilities of large language models, numerous mainstream benchmarks adopt a multiple-choice format. As the swapping of the contents of multiple-choice options does not affect the meaning of the question itself, we propose a simple and effective data leakage detection method based on this property. Specifically, we shuffle the contents of the options in the data to generate the corresponding derived data sets, and then detect data leakage based on the model's log probability distribution over the derived data sets. If there is a maximum and outlier in the set of log probabilities, it indicates that the data is leaked. Our method is able to work under black-box conditions without access to model training data or weights, effectively identifying data leakage from benchmark test sets in model pre-training data, including both normal scenarios and complex scenarios where options may have been shuffled intentionally or unintentionally. Through experiments based on two LLMs and benchmark designs, we demonstrate the effectiveness of our method. In addition, we evaluate the degree of data leakage of 31 mainstream open-source LLMs on four benchmark datasets and give a ranking of the leaked LLMs for each benchmark, and we find that the Qwen family of LLMs has the highest degree of data leakage.

In the realm of Adversarial Distillation (AD), strategic and precise knowledge transfer from an adversarially robust teacher model to a less robust student model is paramount. Our Dynamic Guidance Adversarial Distillation (DGAD) framework directly tackles the challenge of differential sample importance, with a keen focus on rectifying the teacher model's misclassifications. DGAD employs Misclassification-Aware Partitioning (MAP) to dynamically tailor the distillation focus, optimizing the learning process by steering towards the most reliable teacher predictions. Additionally, our Error-corrective Label Swapping (ELS) corrects misclassifications of the teacher on both clean and adversarially perturbed inputs, refining the quality of knowledge transfer. Further, Predictive Consistency Regularization (PCR) guarantees consistent performance of the student model across both clean and adversarial inputs, significantly enhancing its overall robustness. By integrating these methodologies, DGAD significantly improves upon the accuracy of clean data and fortifies the model's defenses against sophisticated adversarial threats. Our experimental validation on CIFAR10, CIFAR100, and Tiny ImageNet datasets, employing various model architectures, demonstrates the efficacy of DGAD, establishing it as a promising approach for enhancing both the robustness and accuracy of student models in adversarial settings.

The recent advances in large language models (LLMs) have significantly expanded their applications across various fields such as language generation, summarization, and complex question answering. However, their application to privacy compliance and technical privacy reviews remains under-explored, raising critical concerns about their ability to adhere to global privacy standards and protect sensitive user data. This paper seeks to address this gap by providing a comprehensive case study evaluating LLMs' performance in privacy-related tasks such as privacy information extraction (PIE), legal and regulatory key point detection (KPD), and question answering (QA) with respect to privacy policies and data protection regulations. We introduce a Privacy Technical Review (PTR) framework, highlighting its role in mitigating privacy risks during the software development life-cycle. Through an empirical assessment, we investigate the capacity of several prominent LLMs, including BERT, GPT-3.5, GPT-4, and custom models, in executing privacy compliance checks and technical privacy reviews. Our experiments benchmark the models across multiple dimensions, focusing on their precision, recall, and F1-scores in extracting privacy-sensitive information and detecting key regulatory compliance points. While LLMs show promise in automating privacy reviews and identifying regulatory discrepancies, significant gaps persist in their ability to fully comply with evolving legal standards. We provide actionable recommendations for enhancing LLMs' capabilities in privacy compliance, emphasizing the need for robust model improvements and better integration with legal and regulatory requirements. This study underscores the growing importance of developing privacy-aware LLMs that can both support businesses in compliance efforts and safeguard user privacy rights., Comment: 8 pages, 4 figures

Large Language Models (LLMs) have recently displayed their extraordinary capabilities in language understanding. However, how to comprehensively assess the sentiment capabilities of LLMs continues to be a challenge. This paper investigates the ability of LLMs to detect and react to sentiment in text modal. As the integration of LLMs into diverse applications is on the rise, it becomes highly critical to comprehend their sensitivity to emotional tone, as it can influence the user experience and the efficacy of sentiment-driven tasks. We conduct a series of experiments to evaluate the performance of several prominent LLMs in identifying and responding appropriately to sentiments like positive, negative, and neutral emotions. The models' outputs are analyzed across various sentiment benchmarks, and their responses are compared with human evaluations. Our discoveries indicate that although LLMs show a basic sensitivity to sentiment, there are substantial variations in their accuracy and consistency, emphasizing the requirement for further enhancements in their training processes to better capture subtle emotional cues. Take an example in our findings, in some cases, the models might wrongly classify a strongly positive sentiment as neutral, or fail to recognize sarcasm or irony in the text. Such misclassifications highlight the complexity of sentiment analysis and the areas where the models need to be refined. Another aspect is that different LLMs might perform differently on the same set of data, depending on their architecture and training datasets. This variance calls for a more in-depth study of the factors that contribute to the performance differences and how they can be optimized., Comment: 10 pages, 2 figures

The possibility of observing spectral features in exoplanet atmospheres with space missions like JWST and ARIEL necessitates the accurate modelling of cloud particle opacities. In exoplanet atmospheres, cloud particles can be made from multiple materials and be considerably chemically heterogeneous. Therefore, assumptions on the morphology of cloud particles are required to calculate their opacities. The aim of this work is to analyse how different approaches to calculate the opacities of heterogeneous cloud particles affect cloud particle optical properties. We calculate cloud particle optical properties using seven different mixing treatments: four effective medium theories (EMTs: Bruggeman, Landau-Lifshitz-Looyenga (LLL), Maxwell-Garnett, and Linear), core-shell, and two homogeneous cloud particle approximations. We study the mixing behaviour of 21 commonly considered cloud particle materials for exoplanets. To analyse the impact on observations, we study the transmission spectra of HATS-6b, WASP-39b, WASP-76b, and WASP-107b.Materials with large refractive indices, like iron-bearing species or carbon, can change the optical properties of cloud particles when they comprise less than 1\% of the total particle volume. The mixing treatment of heterogeneous cloud particles also has an observable effect on transmission spectroscopy. Assuming core-shell or homogeneous cloud particles results in less muting of molecular features and retains the cloud spectral features of the individual cloud particle materials. The predicted transit depth for core-shell and homogeneous cloud particle materials are similar for all planets used in this work. If EMTs are used, cloud spectral features are broader and cloud spectral features of the individual cloud particle materials are not retained. Using LLL leads to less molecular features in transmission spectra compared to Bruggeman., Comment: 21 pages, 15 figures, Accepted by A&A

This paper explores higher-resolution video outpainting with extensive content generation. We point out common issues faced by existing methods when attempting to largely outpaint videos: the generation of low-quality content and limitations imposed by GPU memory. To address these challenges, we propose a diffusion-based method called \textit{Follow-Your-Canvas}. It builds upon two core designs. First, instead of employing the common practice of "single-shot" outpainting, we distribute the task across spatial windows and seamlessly merge them. It allows us to outpaint videos of any size and resolution without being constrained by GPU memory. Second, the source video and its relative positional relation are injected into the generation process of each window. It makes the generated spatial layout within each window harmonize with the source video. Coupling with these two designs enables us to generate higher-resolution outpainting videos with rich content while keeping spatial and temporal consistency. Follow-Your-Canvas excels in large-scale video outpainting, e.g., from 512X512 to 1152X2048 (9X), while producing high-quality and aesthetically pleasing results. It achieves the best quantitative results across various resolution and scale setups. The code is released on https://github.com/mayuelala/FollowYourCanvas, Comment: Github: https://github.com/mayuelala/FollowYourCanvas Page: https://follow-your-canvas.github.io/

We propose an uplink over-the-air aggregation (OAA) method for wireless federated learning (FL) that simultaneously trains multiple models. To maximize the multi-model training convergence rate, we derive an upper bound on the optimality gap of the global model update, and then, formulate an uplink joint transmit-receive beamforming optimization problem to minimize this upper bound. We solve this problem using the block coordinate descent approach, which admits low-complexity closed-form updates. Simulation results show that our proposed multi-model FL with fast OAA substantially outperforms sequentially training multiple models under the conventional single-model approach., Comment: 5 pages, 5 figures. Accepted by IEEE SPAWC 2024. arXiv admin note: text overlap with arXiv:2312.13424

Thermal transport is a fundamental mechanism of energy transfer process quite distinct from wave propagation phenomena. It can be manipulated well beyond the possibilities offered by natural materials with a new generation of artificial metamaterials: thermal metamaterials. Topological physics, a focal point in contemporary condensed matter physics, is closely intertwined with thermal metamaterials in recent years. Inspired by topological photonics and topological acoustics in wave metamaterials, a new research field emerged recently, which we dub `topological thermotics', which encompasses three primary branches: topological thermal conduction, convection, and radiation. For topological thermal conduction, we discuss recent advances in both 1D and higher-dimensional thermal topological phases. For topological thermal convection, we discuss the implementation of thermal exceptional points with their unique properties and non-Hermitian thermal topological states. Finally, we review the most recent demonstration of topological effects in the near-field and far-field radiation. Anticipating future developments, we conclude by discussing potential directions of topological thermotics, including the expansion into other diffusion processes such as particle dynamics and plasma physics, and the integration with machine learning techniques., Comment: This perpective summarizes the topological physics in thermal metamaterials and proposes a new research field, "topological thermotics"

The intrinsic morphology of stellar components within HI-bearing dwarf galaxies remains a topic of uncertainty. Leveraging the galaxy dataset derived from the cross-matched catalog of the Arecibo Legacy Fast Arecibo L-band Feed Array HI 21cm line survey and the Sloan Digital Sky Survey, we employ a Markov Chain Monte Carlo methodology and assume a triaxial model to scrutinize the inherent stellar distributions of these HI-bearing dwarf galaxies. Our analysis indicates a preference for oblate-triaxial models with $C

Cross-domain speech enhancement (SE) is often faced with severe challenges due to the scarcity of noise and background information in an unseen target domain, leading to a mismatch between training and test conditions. This study puts forward a novel data simulation method to address this issue, leveraging noise-extractive techniques and generative adversarial networks (GANs) with only limited target noisy speech data. Notably, our method employs a noise encoder to extract noise embeddings from target-domain data. These embeddings aptly guide the generator to synthesize utterances acoustically fitted to the target domain while authentically preserving the phonetic content of the input clean speech. Furthermore, we introduce the notion of dynamic stochastic perturbation, which can inject controlled perturbations into the noise embeddings during inference, thereby enabling the model to generalize well to unseen noise conditions. Experiments on the VoiceBank-DEMAND benchmark dataset demonstrate that our domain-adaptive SE method outperforms an existing strong baseline based on data simulation., Comment: Accepted to IEEE SLT 2024

Using a data sample of $e^+e^-$ collisions corresponding to an integrated luminosity of 7.93 $\rm fb^{-1}$ collected with the BESIII detector at the center-of-mass energy 3.773~GeV, we perform the first amplitude analysis of the decay $D^{+} \to K_{S}^{0} K_{S}^{0} \pi^{+}$. The absolute branching fraction of $D^{+} \to K_{S}^{0}K_{S}^{0} \pi^{+}$ is measured to be $(2.97 \pm 0.09_{\rm stat.} \pm 0.05_{\rm syst.})\times10^{-3}$. The dominant intermediate process is $D^{+} \to K_{S}^{0}K^{*}(892)^{+}$, whose branching fraction is determined to be $(8.72 \pm 0.28_{\rm stat.} \pm 0.15_{\rm syst.}) \times 10^{-3}$, including all the $K^*(892)^+$ decays.

In this paper, we summarize the methods and experimental results we proposed for Task 2 in the learn2reg 2024 Challenge. This task focuses on unsupervised registration of anatomical structures in brain MRI images between different patients. The difficulty lies in: (1) without segmentation labels, and (2) a large amount of data. To address these challenges, we built an efficient backbone network and explored several schemes to further enhance registration accuracy. Under the guidance of the NCC loss function and smoothness regularization loss function, we obtained a smooth and reasonable deformation field. According to the leaderboard, our method achieved a Dice coefficient of 77.34%, which is 1.4% higher than the TransMorph. Overall, we won second place on the leaderboard for Task 2., Comment: MICCAI Learn2Reg 2024 Challenge & WBIR 2024 Workshop on Biomedical Imaging Registration

We prove the existence of murmurations in the family of Maass forms of weight 0 and level 1 with their Laplace eigenvalue parameter going to infinity (i.e., correlations between the parity and Hecke eigenvalues at primes growing in proportion to the analytic conductor).

UHD images, typically with resolutions equal to or higher than 4K, pose a significant challenge for efficient image quality assessment (IQA) algorithms, as adopting full-resolution images as inputs leads to overwhelming computational complexity and commonly used pre-processing methods like resizing or cropping may cause substantial loss of detail. To address this problem, we design a multi-branch deep neural network (DNN) to assess the quality of UHD images from three perspectives: global aesthetic characteristics, local technical distortions, and salient content perception. Specifically, aesthetic features are extracted from low-resolution images downsampled from the UHD ones, which lose high-frequency texture information but still preserve the global aesthetics characteristics. Technical distortions are measured using a fragment image composed of mini-patches cropped from UHD images based on the grid mini-patch sampling strategy. The salient content of UHD images is detected and cropped to extract quality-aware features from the salient regions. We adopt the Swin Transformer Tiny as the backbone networks to extract features from these three perspectives. The extracted features are concatenated and regressed into quality scores by a two-layer multi-layer perceptron (MLP) network. We employ the mean square error (MSE) loss to optimize prediction accuracy and the fidelity loss to optimize prediction monotonicity. Experimental results show that the proposed model achieves the best performance on the UHD-IQA dataset while maintaining the lowest computational complexity, demonstrating its effectiveness and efficiency. Moreover, the proposed model won first prize in ECCV AIM 2024 UHD-IQA Challenge. The code is available at https://github.com/sunwei925/UIQA., Comment: The proposed model won first prize in ECCV AIM 2024 Pushing the Boundaries of Blind Photo Quality Assessment Challenge

Platform-based laborers face unprecedented challenges and working conditions that result from algorithmic opacity, insufficient data transparency, and unclear policies and regulations. The CSCW and HCI communities increasingly turn to worker data collectives as a means to advance related policy and regulation, hold platforms accountable for data transparency and disclosure, and empower the collective worker voice. However, fundamental questions remain for designing, governing and sustaining such data infrastructures. In this workshop, we leverage frameworks such as data feminism to design sustainable and power-aware data collectives that tackle challenges present in various types of online labor platforms (e.g., ridesharing, freelancing, crowdwork, carework). While data collectives aim to support worker collectives and complement relevant policy initiatives, the goal of this workshop is to encourage their designers to consider topics of governance, privacy, trust, and transparency. In this one-day session, we convene research and advocacy community members to reflect on critical platform work issues (e.g., worker surveillance, discrimination, wage theft, insufficient platform accountability) as well as to collaborate on codesigning data collectives that ethically and equitably address these concerns by supporting working collectivism and informing policy development.

Large language models (LLMs) and retrieval-augmented generation (RAG) techniques have revolutionized traditional information access, enabling AI agent to search and summarize information on behalf of users during dynamic dialogues. Despite their potential, current AI search engines exhibit considerable room for improvement in several critical areas. These areas include the support for multimodal information, the delivery of personalized responses, the capability to logically answer complex questions, and the facilitation of more flexible interactions. This paper proposes a novel AI Search Engine framework called the Agent Collaboration Network (ACN). The ACN framework consists of multiple specialized agents working collaboratively, each with distinct roles such as Account Manager, Solution Strategist, Information Manager, and Content Creator. This framework integrates mechanisms for picture content understanding, user profile tracking, and online evolution, enhancing the AI search engine's response quality, personalization, and interactivity. A highlight of the ACN is the introduction of a Reflective Forward Optimization method (RFO), which supports the online synergistic adjustment among agents. This feature endows the ACN with online learning capabilities, ensuring that the system has strong interactive flexibility and can promptly adapt to user feedback. This learning method may also serve as an optimization approach for agent-based systems, potentially influencing other domains of agent applications., Comment: ACMMM 2024 MMGR WORKSHOP

With the proliferation of location-aware devices, large amount of trajectories have been generated when agents such as people, vehicles and goods flow around the urban environment. These raw trajectories, typically collected from various sources such as GPS in cars, personal mobile devices, and public transport, are often sparse and fragmented due to limited sampling rates, infrastructure coverage and data loss. In this context, trajectory recovery aims to reconstruct such sparse raw trajectories into their dense and continuous counterparts, so that fine-grained movement of agents across space and time can be captured faithfully. Existing trajectory recovery approaches typically rely on the prior knowledge of travel mode or motion patterns, and often fail in densely populated urban areas where accurate maps are absent. In this paper, we present a new recovery framework called TrajWeaver based on probabilistic diffusion models, which is able to recover dense and refined trajectories from the sparse raw ones, conditioned on various auxiliary features such as Areas of Interest along the way, user identity and waybill information. The core of TrajWeaver is a novel State Propagation Diffusion Model (SPDM), which introduces a new state propagation mechanism on top of the standard diffusion models, so that knowledge computed in earlier diffusion steps can be reused later, improving the recovery performance while reducing the number of steps needed. Extensive experiments show that the proposed TrajWeaver can recover from raw trajectories of various lengths, sparsity levels and heterogeneous travel modes, and outperform the state-of-the-art baselines significantly in recovery accuracy. Our code is available at: https://anonymous.4open.science/r/TrajWeaver/, Comment: First submission, extended to 10 pages include ref

Using $e^+e^-$ collision data collected by the BESIII detector at BEPCII corresponding to an integrated luminosity of 30 $\rm fb^{-1}$, we measure Born cross sections and effective form factors for the process $e^+e^-\to\Xi^0\bar{\Xi}^0$ at forty-five center-of-mass energies between 3.51 and 4.95 GeV. The dressed cross section is fitted, assuming a power-law function plus a charmonium(-like) state, i.e., $\psi(3770)$, $\psi(4040)$, $\psi(4160)$, $\psi(4230)$, $\psi(4360)$, $\psi(4415)$ or $\psi(4660)$. No significant charmonium(-like) state decaying into $\Xi^0\bar\Xi^0$ is observed. Upper limits at the 90% confidence level on the product of the branching fraction and the electronic partial width are provided for each decay. In addition, ratios of the Born cross sections and the effective form factors for $e^+e^-\to\Xi^0\bar{\Xi}^0$ and $e^+e^-\to\Xi^-\bar{\Xi}^+$ are also presented to test isospin symmetry and the vector meson dominance model., Comment: 22 pages, 2 tables, 4 figures

Data assimilation techniques are often confronted with challenges handling complex high dimensional physical systems, because high precision simulation in complex high dimensional physical systems is computationally expensive and the exact observation functions that can be applied in these systems are difficult to obtain. It prompts growing interest in integrating deep learning models within data assimilation workflows, but current software packages for data assimilation cannot handle deep learning models inside. This study presents a novel Python package seamlessly combining data assimilation with deep neural networks to serve as models for state transition and observation functions. The package, named TorchDA, implements Kalman Filter, Ensemble Kalman Filter (EnKF), 3D Variational (3DVar), and 4D Variational (4DVar) algorithms, allowing flexible algorithm selection based on application requirements. Comprehensive experiments conducted on the Lorenz 63 and a two-dimensional shallow water system demonstrate significantly enhanced performance over standalone model predictions without assimilation. The shallow water analysis validates data assimilation capabilities mapping between different physical quantity spaces in either full space or reduced order space. Overall, this innovative software package enables flexible integration of deep learning representations within data assimilation, conferring a versatile tool to tackle complex high dimensional dynamical systems across scientific domains.