Search

Multi-object tracking is advancing through two dominant paradigms: traditional tracking by detection and newly emerging tracking by query. In this work, we fuse them together and propose the tracking-by-detection-and-query paradigm, which is achieved by a Learnable Associator. Specifically, the basic information interaction module and the content-position alignment module are proposed for thorough information Interaction among object queries. Tracking results are directly Decoded from these queries. Hence, we name the method as LAID. Compared to tracking-by-query models, LAID achieves competitive tracking accuracy with notably higher training efficiency. With regard to tracking-by-detection methods, experimental results on DanceTrack show that LAID significantly surpasses the state-of-the-art heuristic method by 3.9% on HOTA metric and 6.1% on IDF1 metric. On SportsMOT, LAID also achieves the best score on HOTA metric. By holding low training cost, strong tracking capabilities, and an elegant end-to-end approach all at once, LAID presents a forward-looking direction for the field.

Recently, 3D Gaussian splatting has been getting a lot of attention as an innovative method for representing 3D space due to rapid rendering and image quality. However, copyright protection for the 3D Gaussian splatting has not yet been introduced. In this paper, we present a novel watermarking method for 3D Gaussian splatting. The proposed method embeds a binary message into 3D Gaussians by fine-tuning the pre-trained 3D Gaussian splatting model. To achieve this, we present Frequency-Guided Densification (FGD) that utilizes Discrete Fourier Transform to find patches with high-frequencies and split 3D Gaussians based on 3D Gaussian Contribution Vector. It is each 3D Gaussian contribution to rendered pixel colors, improving both rendering quality and bit accuracy. Furthermore, we modify an adaptive gradient mask to enhance rendering quality. Our experiments show that our method can embed a watermark in 3D Gaussians imperceptibly with increased capacity and robustness against attacks. Our method reduces optimization cost and achieves state-of-the-art performance compared to other methods.

Analyzing student actions is an important and challenging task in educational research. Existing efforts have been hampered by the lack of accessible datasets to capture the nuanced action dynamics in classrooms. In this paper, we present a new multi-label student action video (SAV) dataset for complex classroom scenes. The dataset consists of 4,324 carefully trimmed video clips from 758 different classrooms, each labeled with 15 different actions displayed by students in classrooms. Compared to existing behavioral datasets, our dataset stands out by providing a wide range of real classroom scenarios, high-quality video data, and unique challenges, including subtle movement differences, dense object engagement, significant scale differences, varied shooting angles, and visual occlusion. The increased complexity of the dataset brings new opportunities and challenges for benchmarking action detection. Innovatively, we also propose a new baseline method, a visual transformer for enhancing attention to key local details in small and dense object regions. Our method achieves excellent performance with mean Average Precision (mAP) of 67.9\% and 27.4\% on SAV and AVA, respectively. This paper not only provides the dataset but also calls for further research into AI-driven educational tools that may transform teaching methodologies and learning outcomes. The code and dataset will be released at https://github.com/Ritatanz/SAV.

The goal of image cropping is to identify visually appealing crops within an image. Conventional methods rely on specialized architectures trained on specific datasets, which struggle to be adapted to new requirements. Recent breakthroughs in large vision-language models (VLMs) have enabled visual in-context learning without explicit training. However, effective strategies for vision downstream tasks with VLMs remain largely unclear and underexplored. In this paper, we propose an effective approach to leverage VLMs for better image cropping. First, we propose an efficient prompt retrieval mechanism for image cropping to automate the selection of in-context examples. Second, we introduce an iterative refinement strategy to iteratively enhance the predicted crops. The proposed framework, named Cropper, is applicable to a wide range of cropping tasks, including free-form cropping, subject-aware cropping, and aspect ratio-aware cropping. Extensive experiments and a user study demonstrate that Cropper significantly outperforms state-of-the-art methods across several benchmarks.

Recognizing and disentangling visual attributes from objects is a foundation to many computer vision applications. While large vision language representations like CLIP had largely resolved the task of zero-shot object recognition, zero-shot visual attribute recognition remains a challenge because CLIP's contrastively-learned vision-language representation cannot effectively capture object-attribute dependencies. In this paper, we target this weakness and propose a sentence generation-based retrieval formulation for attribute recognition that is novel in 1) explicitly modeling a to-be-measured and retrieved object-attribute relation as a conditional probability graph, which converts the recognition problem into a dependency-sensitive language-modeling problem, and 2) applying a large pretrained Vision-Language Model (VLM) on this reformulation and naturally distilling its knowledge of image-object-attribute relations to use towards attribute recognition. Specifically, for each attribute to be recognized on an image, we measure the visual-conditioned probability of generating a short sentence encoding the attribute's relation to objects on the image. Unlike contrastive retrieval, which measures likelihood by globally aligning elements of the sentence to the image, generative retrieval is sensitive to the order and dependency of objects and attributes in the sentence. We demonstrate through experiments that generative retrieval consistently outperforms contrastive retrieval on two visual reasoning datasets, Visual Attribute in the Wild (VAW), and our newly-proposed Visual Genome Attribute Ranking (VGARank)., Comment: Accepted at ECCV 2024. Contact: zhuwilliam[at]google[dot]com. GitHub: https://github.com/google-research/google-research/tree/master/attribute_with_prefixlm

In iron-based superconductor Fe(Se,Te), a flat band-like feature near the Fermi level was observed around the Brillouin zone center in the superconducting state. It is under debate whether this is the evidence on the presence of the BCS-BEC crossover in the superconductor. High-resolution laser-based angle-resolved photoemission measurements are carried out on high quality single crystals of FeSe0.45Te0.55 superconductor to address the issue. By employing different polarization geometries, we have resolved and isolated the dyz band and the topological surface band, making it possible to study their superconducting behaviors separately. The dyz band alone does not form a flat band-like feature in the superconducting state and the measured dispersion can be well described by the BCS picture. We find that the flat band-like feature is formed from the combination of the dyz band and the topological surface state band in the superconducting state. These results reveal the origin of the flat band-like feature and rule out the presence of BCS-BEC crossover in Fe(Se,Te) superconductor.

Integrated sensing and communication (ISAC) emerges as an essential technique for overcoming spectrum congestion. However, the performance of traditional ISAC systems with fixed-position-antennas (FPA) is limited due to insufficient spatial degree of freedom (DoF) exploration. Recently, fluid antenna (FA) with reconfigurable antenna position is developed to enhance the sensing and communication performance by reshaping the channel. This paper investigates an FA-enhanced ISAC system where a base station is equipped with multiple FAs to communicate with multiple single-antenna users and with FPAs to sense a point target. In this paper, we consider both perfect and imperfect channel state information (CSI) of the communication channel and sensing channel. In two cases, we focus on the maximization of the sensing signal-to-noise (SNR) by optimizing the positions of FAs and the dual-functional beamforming under the constraints of the FA moving region, the minimum FA distance and the minimum signal-to-interference-plus-noise (SINR) per user. Specifically, for the ideal case of perfect CSI, an iterative alternating optimization (AO) algorithm is proposed to tackle the formulated problem where the dual-functional beamforming and the FA positions are obtained via semidefinite relaxation (SDR) and successive convex approximation (SCA) techniques. Then, for the imperfect CSI case, we propose an AO-based iterative algorithm where $\mathcal{S}-$Procedure and SCA are applied to obtain the dual-functional beamforming and the FA positions. Furthermore, we analytically and numerically prove the convergence of the proposed algorithms. Numerical results demonstrate the notable gains of the proposed algorithms in the respective cases., Comment: arXiv admin note: text overlap with arXiv:2407.05297

In high temperature cuprate superconductors, it was found that in the overdoped region the superfluid density decreases with the increase of hole doping. One natural question is whether there exists normal fluid in the superconducting state in the overdoped region. In this paper, we have carried out high-resolution ultra-low temperature laser-based angle-resolved photoemission measurements on a heavily overdoped Bi2212 sample with a $T_{\mathrm{c}}$ of 48 K. We find that this heavily overdoped Bi2212 remains in the strong coupling regime with $2 \mathit{\Delta}_0 / k_{\mathrm{B}} T_{\mathrm{c}}=5.8$. The single-particle scattering rate is very small along the nodal direction ($\sim$5 meV) and increases as the momentum moves from the nodal to the antinodal regions. A hard superconducting gap opening is observed near the antinodal region with the spectral weight at the Fermi level fully suppressed to zero. The normal fluid is found to be negligibly small in the superconducting state of this heavily overdoped Bi2212. These results provide key information to understand the high $T_\mathrm{c}$ mechanism in the cuprate superconductors., Comment: 13 pages, 4 figures

Diffusion models generate new samples by progressively decreasing the noise from the initially provided random distribution. This inference procedure generally utilizes a trained neural network numerous times to obtain the final output, creating significant latency and energy consumption on digital electronic hardware such as GPUs. In this study, we demonstrate that the propagation of a light beam through a semi-transparent medium can be programmed to implement a denoising diffusion model on image samples. This framework projects noisy image patterns through passive diffractive optical layers, which collectively only transmit the predicted noise term in the image. The optical transparent layers, which are trained with an online training approach, backpropagating the error to the analytical model of the system, are passive and kept the same across different steps of denoising. Hence this method enables high-speed image generation with minimal power consumption, benefiting from the bandwidth and energy efficiency of optical information processing., Comment: 17 pages, 10 figures

This paper investigates a fluid antenna (FA) enhanced integrated sensing and communication (ISAC) system consisting of a base station (BS), multiple single-antenna communication users, and one point target, where the BS is equipped with FAs to enhance both the communication and sensing performance. First, we formulate a problem that maximizes the radar signal-to-noise ratio (SNR) by jointly optimizing the FAs' positions and transmit beamforming matrix. Then, to tackle this highly non-convex problem, we present efficient algorithms by using alternating optimization (AO), successive convex approximation (SCA), and semi-definite relaxation (SDR). Numerical results demonstrate the convergence behavior and effectiveness of the proposed algorithm., Comment: This work has been accepted by 2024 IEEE/CIC International Conference on Communications in China (ICCC)

Unmanned Aerial Systems (UAS) are currently widely used in safety-critical fields such as industrial production, military operations, and disaster relief. Due to the diversity and complexity of application scenarios, UAS have become increasingly intricate. The challenge of designing and implementing highly reliable UAS while effectively controlling development costs and enhancing efficiency is a pressing issue faced by both academia and industry. Addressing this challenge, this paper aims to investigate an integrated approach to modeling, verification, and code generation for UAS. The paper begins by utilizing Architecture Analysis and Design Language (AADL) to model the UAS, proposing a set of generic UAS models. Based on these models, formal specifications are written to describe the system's safety properties and functions. Finally, the paper introduces a method for generating flight controller code for UAS based on the verified models. Experiments conducted with the proposed method demonstrate its effectiveness in identifying potential vulnerabilities in the UAS during the early design phase and in generating viable flight controller code from the verified models. This approach can enhance the efficiency of designing and verifying high-reliability UAS.

With the rapid advancement of autonomous driving technology, there is a growing need for enhanced safety and efficiency in the automatic environmental perception of vehicles during their operation. In modern vehicle setups, cameras and mmWave radar (radar), being the most extensively employed sensors, demonstrate complementary characteristics, inherently rendering them conducive to fusion and facilitating the achievement of both robust performance and cost-effectiveness. This paper focuses on a comprehensive survey of radar-vision (RV) fusion based on deep learning methods for 3D object detection in autonomous driving. We offer a comprehensive overview of each RV fusion category, specifically those employing region of interest (ROI) fusion and end-to-end fusion strategies. As the most promising fusion strategy at present, we provide a deeper classification of end-to-end fusion methods, including those 3D bounding box prediction based and BEV based approaches. Moreover, aligning with recent advancements, we delineate the latest information on 4D radar and its cutting-edge applications in autonomous vehicles (AVs). Finally, we present the possible future trends of RV fusion and summarize this paper.

In this study, we successfully developed two-dimensional paper-based analytical devices using a hybrid technique of injection molding and embossing. This innovative approach involves passive or active delivery of molten wax onto a glass substrate through a sealed chip, facilitating wax stamp creation.

Monocular vision-based 3D object detection is crucial in various sectors, yet existing methods face significant challenges in terms of accuracy and computational efficiency. Building on the successful strategies in 2D detection and depth estimation, we propose MonoDETRNext, which seeks to optimally balance precision and processing speed. Our methodology includes the development of an efficient hybrid visual encoder, enhancement of depth prediction mechanisms, and introduction of an innovative query generation strategy, augmented by an advanced depth predictor. Building on MonoDETR, MonoDETRNext introduces two variants: MonoDETRNext-F, which emphasizes speed, and MonoDETRNext-A, which focuses on precision. We posit that MonoDETRNext establishes a new benchmark in monocular 3D object detection and opens avenues for future research. We conducted an exhaustive evaluation demonstrating the model's superior performance against existing solutions. Notably, MonoDETRNext-A demonstrated a 4.60% improvement in the AP3D metric on the KITTI test benchmark over MonoDETR, while MonoDETRNext-F showed a 2.21% increase. Additionally, the computational efficiency of MonoDETRNext-F slightly exceeds that of its predecessor.

The advances in the Neural Radiance Fields (NeRF) research offer extensive applications in diverse domains, but protecting their copyrights has not yet been researched in depth. Recently, NeRF watermarking has been considered one of the pivotal solutions for safely deploying NeRF-based 3D representations. However, existing methods are designed to apply only to implicit or explicit NeRF representations. In this work, we introduce an innovative watermarking method that can be employed in both representations of NeRF. This is achieved by fine-tuning NeRF to embed binary messages in the rendering process. In detail, we propose utilizing the discrete wavelet transform in the NeRF space for watermarking. Furthermore, we adopt a deferred back-propagation technique and introduce a combination with the patch-wise loss to improve rendering quality and bit accuracy with minimum trade-offs. We evaluate our method in three different aspects: capacity, invisibility, and robustness of the embedded watermarks in the 2D-rendered images. Our method achieves state-of-the-art performance with faster training speed over the compared state-of-the-art methods.

Formal Methods (FMs) are currently essential for verifying the safety and reliability of software systems. However, the specification writing in formal methods tends to be complex and challenging to learn, requiring familiarity with various intricate formal specification languages and verification technologies. In response to the increasing complexity of software frameworks, existing specification writing methods fall short in meeting agility requirements. To address this, this paper introduces an Agile Formal Specification Language (ASL). The ASL is defined based on the K Framework and YAML Ain't Markup Language (YAML). The design of ASL incorporates agile design principles, making the writing of formal specifications simpler, more efficient, and scalable. Additionally, a specification translation algorithm is developed, capable of converting ASL into K formal specification language that can be executed for verification. Experimental evaluations demonstrate that the proposed method significantly reduces the code size needed for specification writing, enhancing agility in formal specification writing.

Ferroelectric domain walls hold great promise for innovative applications in ferroelectric devices. However, the underlying mechanisms behind the observed giant conductance of charged domain walls remain poorly understood. Using a first-principles approach that incorporates Boltzmann transport theory and the relaxation time approximation, we determine the carrier concentration, mobility, and conductivity of domain walls with head-to-head and tail-to-tail polarization orientations. Our systematic exploration reveals that the accumulation of carriers, particularly their concentration, plays a dominant role in the domain wall conductance mechanism. However, the observed conductance differences between head-to-head and tail-to-tail domain walls are primarily due to differences in carrier mobility. The width of the domain wall is a key factor determining the device scale. Our calculated domain wall width is significantly smaller than previously reported values. This method, not limited to a certain ferroelectric material, can be used for the optimization and application development of various domain wall materials and devices., Comment: 17 pages, 7 figures

The newly discovered Kagome superconductors AV$_3$Sb$_5$ (A=K, Rb and Cs) continue to bring surprises in generating unusual phenomena and physical properties, including anomalous Hall effect, unconventional charge density wave, electronic nematicity and time-reversal symmetry breaking. Here we report an unexpected emergence of multiple flat bands in the AV$_3$Sb$_5$ superconductors. By performing high-resolution angle-resolved photoemission (ARPES) measurements, we observed four branches of flat bands that span over the entire momentum space. The appearance of the flat bands is not anticipated from the band structure calculations and cannot be accounted for by the known mechanisms of flat band generation. It is intimately related to the evolution of van Hove singularities. It is for the first time to observe such emergence of multiple flat bands in solid materials. Our findings provide new insights in revealing the underlying mechanism that governs the unusual behaviors in the Kagome superconductors. They also provide a new pathway in producing flat bands and set a platform to study the flat bands related physics., Comment: 20 pages, 4 figures

The stabilization of optical frequency comb conventionally relies on active electronic feedback loops and stable frequency references. Here, we propose a new approach for autonomous frequency locking (AFL) to generate a zero-offset frequency comb based on cooperative nonlinear optical processes in a microcavity. In a simplified few-mode system, AFL enables the concept of fractional harmonic generation as a zero-offset multi-laser reference for measuring the carrier envelope offset frequency ($f_{\mathrm{ceo}}$) of frequency combs spanning less than one octave, such as 1/3 octave. Combining with Kerr comb generation in a microcaivity, AFL is further applied to directly generate zero-$f_{\mathrm{ceo}}$ soliton comb that is robust against fluctuations in pump laser and cavity resonances. Numerical simulations validate the AFL scheme, showing good agreement with analytical prediction of the locking condition. This work presents a new pathway for exploring novel frequency locking mechanisms and technologies using integrated photonic devices, and also appeals further investigations of cooperative nonlinear optics processes in microcavities.

The early stage evolution of local atomic structures in a multicomponent metallic glass during its crystallization process has been investigated via molecular dynamics simulation. It is found that the initial thermal stability and earliest stage evolution of the local atomic clusters show no strong correlation with their initial short-range orders, and this leads to an observation of a novel symmetry convergence phenomenon, which can be understood as an atomic structure manifestation of the ergodicity. Furthermore, in our system we have quantitatively proved that the crucial factor for the thermal stability against crystallization exhibited by the metallic glass, is not the total amount of icosahedral clusters, but the degree of global connectivity among them., Comment: 13 pages, 8 figures, accepted by CPB

Recent works have demonstrated that using reinforcement learning (RL) with multiple quality rewards can improve the quality of generated images in text-to-image (T2I) generation. However, manually adjusting reward weights poses challenges and may cause over-optimization in certain metrics. To solve this, we propose Parrot, which addresses the issue through multi-objective optimization and introduces an effective multi-reward optimization strategy to approximate Pareto optimal. Utilizing batch-wise Pareto optimal selection, Parrot automatically identifies the optimal trade-off among different rewards. We use the novel multi-reward optimization algorithm to jointly optimize the T2I model and a prompt expansion network, resulting in significant improvement of image quality and also allow to control the trade-off of different rewards using a reward related prompt during inference. Furthermore, we introduce original prompt-centered guidance at inference time, ensuring fidelity to user input after prompt expansion. Extensive experiments and a user study validate the superiority of Parrot over several baselines across various quality criteria, including aesthetics, human preference, text-image alignment, and image sentiment.

This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding. The Gemini family consists of Ultra, Pro, and Nano sizes, suitable for applications ranging from complex reasoning tasks to on-device memory-constrained use-cases. Evaluation on a broad range of benchmarks shows that our most-capable Gemini Ultra model advances the state of the art in 30 of 32 of these benchmarks - notably being the first model to achieve human-expert performance on the well-studied exam benchmark MMLU, and improving the state of the art in every one of the 20 multimodal benchmarks we examined. We believe that the new capabilities of the Gemini family in cross-modal reasoning and language understanding will enable a wide variety of use cases. We discuss our approach toward post-training and deploying Gemini models responsibly to users through services including Gemini, Gemini Advanced, Google AI Studio, and Cloud Vertex AI.

We present a study of electrical and thermal transport in Weyl semimetal WTe$_2$ down to 0.3 K. The Wiedemann-Franz law holds below 2 K and a downward deviation starts above. The deviation is more pronounced in cleaner samples, as expected in the hydrodynamic picture of electronic transport, where a fraction of electron-electron collisions conserve momentum. Phonons are the dominant heat carriers and their mean-free-path do not display a Knudsen minimum. This is presumably a consequence of weak anharmonicity, as indicated by the temperature dependence of the specific heat. Frequent momentum exchange between phonons and electrons leads to quantum oscillations of the phononic thermal conductivity. Bloch-Gr\"uneisen picture of electron-phonon scattering breaks down at low temperature when Umklapp ph-ph collisions cease to be a sink for electronic flow of momentum. Comparison with semi-metallic Sb shows that normal ph-ph collisions are amplified by anharmonicity. In both semimetals, at cryogenic temperature, e-ph collisions degrade the phononic flow of energy but not the electronic flow of momentum., Comment: 6 pages, 4 figures, Supplemental Materials included

Recent Text-to-Image (T2I) generation models such as Stable Diffusion and Imagen have made significant progress in generating high-resolution images based on text descriptions. However, many generated images still suffer from issues such as artifacts/implausibility, misalignment with text descriptions, and low aesthetic quality. Inspired by the success of Reinforcement Learning with Human Feedback (RLHF) for large language models, prior works collected human-provided scores as feedback on generated images and trained a reward model to improve the T2I generation. In this paper, we enrich the feedback signal by (i) marking image regions that are implausible or misaligned with the text, and (ii) annotating which words in the text prompt are misrepresented or missing on the image. We collect such rich human feedback on 18K generated images (RichHF-18K) and train a multimodal transformer to predict the rich feedback automatically. We show that the predicted rich human feedback can be leveraged to improve image generation, for example, by selecting high-quality training data to finetune and improve the generative models, or by creating masks with predicted heatmaps to inpaint the problematic regions. Notably, the improvements generalize to models (Muse) beyond those used to generate the images on which human feedback data were collected (Stable Diffusion variants). The RichHF-18K data set will be released in our GitHub repository: https://github.com/google-research/google-research/tree/master/richhf_18k., Comment: CVPR'24