Search

Multi-object tracking (MOT) in computer vision remains a significant challenge, requiring precise localization and continuous tracking of multiple objects in video sequences. The emergence of data sets that emphasize robust reidentification, such as DanceTrack, has highlighted the need for effective solutions. While memory-based approaches have shown promise, they often suffer from high computational complexity and memory usage due to storing feature at every single frame. In this paper, we propose a novel memory-based approach that selectively stores critical features based on object motion and overlapping awareness, aiming to enhance efficiency while minimizing redundancy. As a result, our method not only store longer temporal information with limited number of stored features in the memory, but also diversify states of a particular object to enhance the association performance. Our approach significantly improves over MOTRv2 in the DanceTrack test set, demonstrating a gain of 2.0% AssA score and 2.1% in IDF1 score.

In [6], we have designed impulsive and feed-back controls for harmonic chains with a point thermostat. In this work, a new type of control is proposed: internal control. We study the internal control for for stochastic lattice dynamics, with the goal of controlling the transition kernel of the kinetic equation in the limit., Comment: 38 pages, 1 figure

User experience on mobile devices is constrained by limited battery capacity and processing power, but 6G technology advancements are diving rapidly into mobile technical evolution. Mobile edge computing (MEC) offers a solution, offloading computationally intensive tasks to edge cloud servers, reducing battery drain compared to local processing. The upcoming integrated sensing and communication in mobile communication may improve the trajectory prediction and processing delays. This study proposes a greedy resource allocation optimization strategy for multi-user networks to minimize aggregate energy usage. Numerical results show potential improvement at 33\% for every 1000 iteration. Addressing prediction model division and velocity accuracy issues is crucial for better results. A plan for further improvement and achieving objectives is outlined for the upcoming work phase.

Polyp segmentation, a critical concern in medical imaging, has prompted numerous proposed methods aimed at enhancing the quality of segmented masks. While current state-of-the-art techniques produce impressive results, the size and computational cost of these models pose challenges for practical industry applications. Recently, the Segment Anything Model (SAM) has been proposed as a robust foundation model, showing promise for adaptation to medical image segmentation. Inspired by this concept, we propose SAM-EG, a framework that guides small segmentation models for polyp segmentation to address the computation cost challenge. Additionally, in this study, we introduce the Edge Guiding module, which integrates edge information into image features to assist the segmentation model in addressing boundary issues from current segmentation model in this task. Through extensive experiments, our small models showcase their efficacy by achieving competitive results with state-of-the-art methods, offering a promising approach to developing compact models with high accuracy for polyp segmentation and in the broader field of medical imaging.

Current video-language models (VLMs) rely extensively on instance-level alignment between video and language modalities, which presents two major limitations: (1) visual reasoning disobeys the natural perception that humans do in first-person perspective, leading to a lack of reasoning interpretation; and (2) learning is limited in capturing inherent fine-grained relationships between two modalities. In this paper, we take an inspiration from human perception and explore a compositional approach for egocentric video representation. We introduce HENASY (Hierarchical ENtities ASsemblY), which includes a spatiotemporal token grouping mechanism to explicitly assemble dynamically evolving scene entities through time and model their relationship for video representation. By leveraging compositional structure understanding, HENASY possesses strong interpretability via visual grounding with free-form text queries. We further explore a suite of multi-grained contrastive losses to facilitate entity-centric understandings. This comprises three alignment types: video-narration, noun-entity, verb-entities alignments. Our method demonstrates strong interpretability in both quantitative and qualitative experiments; while maintaining competitive performances on five downstream tasks via zero-shot transfer or as video/text representation, including video/text retrieval, action recognition, multi-choice query, natural language query, and moments query., Comment: under submission

Multivariate time series classification (MTSC) has attracted significant research attention due to its diverse real-world applications. Recently, exploiting transformers for MTSC has achieved state-of-the-art performance. However, existing methods focus on generic features, providing a comprehensive understanding of data, but they ignore class-specific features crucial for learning the representative characteristics of each class. This leads to poor performance in the case of imbalanced datasets or datasets with similar overall patterns but differing in minor class-specific details. In this paper, we propose a novel Shapelet Transformer (ShapeFormer), which comprises class-specific and generic transformer modules to capture both of these features. In the class-specific module, we introduce the discovery method to extract the discriminative subsequences of each class (i.e. shapelets) from the training set. We then propose a Shapelet Filter to learn the difference features between these shapelets and the input time series. We found that the difference feature for each shapelet contains important class-specific features, as it shows a significant distinction between its class and others. In the generic module, convolution filters are used to extract generic features that contain information to distinguish among all classes. For each module, we employ the transformer encoder to capture the correlation between their features. As a result, the combination of two transformer modules allows our model to exploit the power of both types of features, thereby enhancing the classification performance. Our experiments on 30 UEA MTSC datasets demonstrate that ShapeFormer has achieved the highest accuracy ranking compared to state-of-the-art methods. The code is available at https://github.com/xuanmay2701/shapeformer., Comment: Accepted at KDD 2024

A universal quantum computer can be used as a simulator capable of predicting properties of diverse quantum systems. Electronic structure problems in chemistry offer practical use cases around the hundred-qubit mark. This appears promising since current quantum processors have reached these sizes. However, mapping these use cases onto quantum computers yields deep circuits, and for for pre-fault-tolerant quantum processors, the large number of measurements to estimate molecular energies leads to prohibitive runtimes. As a result, realistic chemistry is out of reach of current quantum computers in isolation. A natural question is whether classical distributed computation can relieve quantum processors from parsing all but a core, intrinsically quantum component of a chemistry workflow. Here, we incorporate quantum computations of chemistry in a quantum-centric supercomputing architecture, using up to 6400 nodes of the supercomputer Fugaku to assist a Heron superconducting quantum processor. We simulate the N$_2$ triple bond breaking in a correlation-consistent cc-pVDZ basis set, and the active-space electronic structure of [2Fe-2S] and [4Fe-4S] clusters, using 58, 45 and 77 qubits respectively, with quantum circuits of up to 10570 (3590 2-qubit) quantum gates. We obtain our results using a class of quantum circuits that approximates molecular eigenstates, and a hybrid estimator. The estimator processes quantum samples, produces upper bounds to the ground-state energy and wavefunctions supported on a polynomial number of states. This guarantees an unconditional quality metric for quantum advantage, certifiable by classical computers at polynomial cost. For current error rates, our results show that classical distributed computing coupled to quantum processors can produce good approximate solutions for practical problems beyond sizes amenable to exact diagonalization.

As the impact of climate change escalates, the global necessity to transition to sustainable energy sources becomes increasingly evident. Renewable energies have emerged as a viable solution for users, with Photovoltaic energy being a favored choice for small installations due to its reliability and efficiency. Accurate mapping of PV installations is crucial for understanding the extension of its adoption and informing energy policy. To meet this need, we introduce S3Former, designed to segment solar panels from aerial imagery and provide size and location information critical for analyzing the impact of such installations on the grid. Solar panel identification is challenging due to factors such as varying weather conditions, roof characteristics, Ground Sampling Distance variations and lack of appropriate initialization weights for optimized training. To tackle these complexities, S3Former features a Masked Attention Mask Transformer incorporating a self-supervised learning pretrained backbone. Specifically, our model leverages low-level and high-level features extracted from the backbone and incorporates an instance query mechanism incorporated on the Transformer architecture to enhance the localization of solar PV installations. We introduce a self-supervised learning phase (pretext task) to improve the initialization weights on the backbone of S3Former. We evaluated S3Former using diverse datasets, demonstrate improvement state-of-the-art models., Comment: Preprint

In the food industry, assessing the quality of poultry carcasses during processing is a crucial step. This study proposes an effective approach for automating the assessment of carcass quality without requiring skilled labor or inspector involvement. The proposed system is based on machine learning (ML) and computer vision (CV) techniques, enabling automated defect detection and carcass quality assessment. To this end, an end-to-end framework called CarcassFormer is introduced. It is built upon a Transformer-based architecture designed to effectively extract visual representations while simultaneously detecting, segmenting, and classifying poultry carcass defects. Our proposed framework is capable of analyzing imperfections resulting from production and transport welfare issues, as well as processing plant stunner, scalder, picker, and other equipment malfunctions. To benchmark the framework, a dataset of 7,321 images was initially acquired, which contained both single and multiple carcasses per image. In this study, the performance of the CarcassFormer system is compared with other state-of-the-art (SOTA) approaches for both classification, detection, and segmentation tasks. Through extensive quantitative experiments, our framework consistently outperforms existing methods, demonstrating remarkable improvements across various evaluation metrics such as AP, AP@50, and AP@75. Furthermore, the qualitative results highlight the strengths of CarcassFormer in capturing fine details, including feathers, and accurately localizing and segmenting carcasses with high precision. To facilitate further research and collaboration, the pre-trained model and source code of CarcassFormer is available for research purposes at: \url{https://github.com/UARK-AICV/CarcassFormer}., Comment: Accepted to Poultry Science Journal

Referring image segmentation is a challenging task that involves generating pixel-wise segmentation masks based on natural language descriptions. Existing methods have relied mostly on visual features to generate the segmentation masks while treating text features as supporting components. This over-reliance on visual features can lead to suboptimal results, especially in complex scenarios where text prompts are ambiguous or context-dependent. To overcome these challenges, we present a novel framework VATEX to improve referring image segmentation by enhancing object and context understanding with Vision-Aware Text Feature. Our method involves using CLIP to derive a CLIP Prior that integrates an object-centric visual heatmap with text description, which can be used as the initial query in DETR-based architecture for the segmentation task. Furthermore, by observing that there are multiple ways to describe an instance in an image, we enforce feature similarity between text variations referring to the same visual input by two components: a novel Contextual Multimodal Decoder that turns text embeddings into vision-aware text features, and a Meaning Consistency Constraint to ensure further the coherent and consistent interpretation of language expressions with the context understanding obtained from the image. Our method achieves a significant performance improvement on three benchmark datasets RefCOCO, RefCOCO+ and G-Ref. Code is available at: https://nero1342.github.io/VATEX\_RIS., Comment: 30 pages including supplementary

Video summarization is a crucial research area that aims to efficiently browse and retrieve relevant information from the vast amount of video content available today. With the exponential growth of multimedia data, the ability to extract meaningful representations from videos has become essential. Video summarization techniques automatically generate concise summaries by selecting keyframes, shots, or segments that capture the video's essence. This process improves the efficiency and accuracy of various applications, including video surveillance, education, entertainment, and social media. Despite the importance of video summarization, there is a lack of diverse and representative datasets, hindering comprehensive evaluation and benchmarking of algorithms. Existing evaluation metrics also fail to fully capture the complexities of video summarization, limiting accurate algorithm assessment and hindering the field's progress. To overcome data scarcity challenges and improve evaluation, we propose an unsupervised approach that leverages video data structure and information for generating informative summaries. By moving away from fixed annotations, our framework can produce representative summaries effectively. Moreover, we introduce an innovative evaluation pipeline tailored specifically for video summarization. Human participants are involved in the evaluation, comparing our generated summaries to ground truth summaries and assessing their informativeness. This human-centric approach provides valuable insights into the effectiveness of our proposed techniques. Experimental results demonstrate that our training-free framework outperforms existing unsupervised approaches and achieves competitive results compared to state-of-the-art supervised methods., Comment: 115 pages, 1 supplementary paper, undergraduate thesis report at US-VNUHCM

In this paper, we present TAC-SUM, a novel and efficient training-free approach for video summarization that addresses the limitations of existing cluster-based models by incorporating temporal context. Our method partitions the input video into temporally consecutive segments with clustering information, enabling the injection of temporal awareness into the clustering process, setting it apart from prior cluster-based summarization methods. The resulting temporal-aware clusters are then utilized to compute the final summary, using simple rules for keyframe selection and frame importance scoring. Experimental results on the SumMe dataset demonstrate the effectiveness of our proposed approach, outperforming existing unsupervised methods and achieving comparable performance to state-of-the-art supervised summarization techniques. Our source code is available for reference at \url{https://github.com/hcmus-thesis-gulu/TAC-SUM}., Comment: 14 pages, 6 figures, accepted in PSIVT 2023

We propose an algorithm for simulating the dynamics of a geometrically local Hamiltonian $A$ under a small geometrically local perturbation $\alpha B$. In certain regimes, the algorithm achieves the optimal scaling and outperforms the state-of-the-art algorithms. By moving into the interaction frame of $A$ and classically computing the Magnus expansion of the interaction-picture Hamiltonian, our algorithm bypasses the need for ancillary qubits. In analyzing its performance, we develop a framework to capture the quasi-locality of the Magnus operators, leading to a tightened bound for the error of the Magnus truncation. The Lieb-Robinson bound also guarantees the efficiency of computing the Magnus operators and of their subsequent decomposition into elementary quantum gates. These features make our algorithm appealing for near-term and early-fault-tolerant simulations., Comment: 17 pages, 1 figure, 1 table

This paper presents a simple yet efficient ensemble learning framework for Vietnamese scene text spotting. Leveraging the power of ensemble learning, which combines multiple models to yield more accurate predictions, our approach aims to significantly enhance the performance of scene text spotting in challenging urban settings. Through experimental evaluations on the VinText dataset, our proposed method achieves a significant improvement in accuracy compared to existing methods with an impressive accuracy of 5%. These results unequivocally demonstrate the efficacy of ensemble learning in the context of Vietnamese scene text spotting in urban environments, highlighting its potential for real world applications, such as text detection and recognition in urban signage, advertisements, and various text-rich urban scenes., Comment: RIVF 2023

Federated Class-Incremental Learning (FCIL) is an underexplored yet pivotal issue, involving the dynamic addition of new classes in the context of federated learning. In this field, Data-Free Knowledge Transfer (DFKT) plays a crucial role in addressing catastrophic forgetting and data privacy problems. However, prior approaches lack the crucial synergy between DFKT and the model training phases, causing DFKT to encounter difficulties in generating high-quality data from a non-anchored latent space of the old task model. In this paper, we introduce LANDER (Label Text Centered Data-Free Knowledge Transfer) to address this issue by utilizing label text embeddings (LTE) produced by pretrained language models. Specifically, during the model training phase, our approach treats LTE as anchor points and constrains the feature embeddings of corresponding training samples around them, enriching the surrounding area with more meaningful information. In the DFKT phase, by using these LTE anchors, LANDER can synthesize more meaningful samples, thereby effectively addressing the forgetting problem. Additionally, instead of tightly constraining embeddings toward the anchor, the Bounding Loss is introduced to encourage sample embeddings to remain flexible within a defined radius. This approach preserves the natural differences in sample embeddings and mitigates the embedding overlap caused by heterogeneous federated settings. Extensive experiments conducted on CIFAR100, Tiny-ImageNet, and ImageNet demonstrate that LANDER significantly outperforms previous methods and achieves state-of-the-art performance in FCIL. The code is available at https://github.com/tmtuan1307/lander., Comment: Accepted at CVPR 2024

Amodal Instance Segmentation (AIS) presents a challenging task as it involves predicting both visible and occluded parts of objects within images. Existing AIS methods rely on a bidirectional approach, encompassing both the transition from amodal features to visible features (amodal-to-visible) and from visible features to amodal features (visible-to-amodal). Our observation shows that the utilization of amodal features through the amodal-to-visible can confuse the visible features due to the extra information of occluded/hidden segments not presented in visible display. Consequently, this compromised quality of visible features during the subsequent visible-to-amodal transition. To tackle this issue, we introduce ShapeFormer, a decoupled Transformer-based model with a visible-to-amodal transition. It facilitates the explicit relationship between output segmentations and avoids the need for amodal-to-visible transitions. ShapeFormer comprises three key modules: (i) Visible-Occluding Mask Head for predicting visible segmentation with occlusion awareness, (ii) Shape-Prior Amodal Mask Head for predicting amodal and occluded masks, and (iii) Category-Specific Shape Prior Retriever aims to provide shape prior knowledge. Comprehensive experiments and extensive ablation studies across various AIS benchmarks demonstrate the effectiveness of our ShapeFormer. The code is available at: \url{https://github.com/UARK-AICV/ShapeFormer}, Comment: Accepted to IJCNN2024

Human-human communication is like a delicate dance where listeners and speakers concurrently interact to maintain conversational dynamics. Hence, an effective model for generating listener nonverbal behaviors requires understanding the dyadic context and interaction. In this paper, we present an effective framework for creating 3D facial motions in dyadic interactions. Existing work consider a listener as a reactive agent with reflexive behaviors to the speaker's voice and facial motions. The heart of our framework is Dyadic Interaction Modeling (DIM), a pre-training approach that jointly models speakers' and listeners' motions through masking and contrastive learning to learn representations that capture the dyadic context. To enable the generation of non-deterministic behaviors, we encode both listener and speaker motions into discrete latent representations, through VQ-VAE. The pre-trained model is further fine-tuned for motion generation. Extensive experiments demonstrate the superiority of our framework in generating listener motions, establishing a new state-of-the-art according to the quantitative measures capturing the diversity and realism of generated motions. Qualitative results demonstrate the superior capabilities of the proposed approach in generating diverse and realistic expressions, eye blinks and head gestures. The code is available at https://github.com/Boese0601/Dyadic-Interaction-Modeling, Comment: The first two authors contribute equally. The paper is accepted by ECCV 2024. Project Page: https://boese0601.github.io/dim/ Code: https://github.com/Boese0601/Dyadic-Interaction-Modeling

Drawing is an art that enables people to express their imagination and emotions. However, individuals usually face challenges in drawing, especially when translating conceptual ideas into visually coherent representations and bridging the gap between mental visualization and practical execution. In response, we propose ARtVista - a novel system integrating AR and generative AI technologies. ARtVista not only recommends reference images aligned with users' abstract ideas and generates sketches for users to draw but also goes beyond, crafting vibrant paintings in various painting styles. ARtVista also offers users an alternative approach to create striking paintings by simulating the paint-by-number concept on reference images, empowering users to create visually stunning artwork devoid of the necessity for advanced drawing skills. We perform a pilot study and reveal positive feedback on its usability, emphasizing its effectiveness in visualizing user ideas and aiding the painting process to achieve stunning pictures without requiring advanced drawing skills. The source code will be available at https://github.com/htrvu/ARtVista., Comment: CHI 2024

Creating thematic collections in industries demands innovative designs and cohesive concepts. Designers may face challenges in maintaining thematic consistency when drawing inspiration from existing objects, landscapes, or artifacts. While AI-powered graphic design tools offer help, they often fail to generate cohesive sets based on specific thematic concepts. In response, we introduce iCONTRA, an interactive CONcept TRAnsfer system. With a user-friendly interface, iCONTRA enables both experienced designers and novices to effortlessly explore creative design concepts and efficiently generate thematic collections. We also propose a zero-shot image editing algorithm, eliminating the need for fine-tuning models, which gradually integrates information from initial objects, ensuring consistency in the generation process without influencing the background. A pilot study suggests iCONTRA's potential to reduce designers' efforts. Experimental results demonstrate its effectiveness in producing consistent and high-quality object concept transfers. iCONTRA stands as a promising tool for innovation and creative exploration in thematic collection design. The source code will be available at: https://github.com/vdkhoi20/iCONTRA., Comment: CHI 2024

In our previous work, numerical schemes for a simplified version of 3-wave kinetic equations, in which only the simple forward-cascade terms of the collision operators are kept, have been successfully designed, especially to capture the long time dynamics of the equation given the multiple blow-up time phenomenon. In this second work in the series, we propose numerical treatments for the complete 3-wave kinetic equations, in which the complete, much more complicated collision operators are fully considered based on a novel conservative form of the equation. We then derive an implicit finite volume scheme to solve the equation. The new discretization uses an adaptive time-stepping method which allows for the simulations to be carried to very long times. Our computed solutions are compared with previously derived long-time asymptotic estimates for the decay rate of total energy of time-dependent solutions of 3-wave kinetic equations and found to be in excellent agreement.

A semi-parametric joint Value-at-Risk (VaR) and Expected Shortfall (ES) forecasting framework employing multiple realized measures is developed. The proposed framework extends the realized exponential GARCH model to be semi-parametrically estimated, via a joint loss function, whilst extending existing quantile time series models to incorporate multiple realized measures. A quasi-likelihood is built, employing the asymmetric Laplace distribution that is directly linked to a joint loss function, which enables Bayesian inference for the proposed model. An adaptive Markov Chain Monte Carlo method is used for the model estimation. The empirical section evaluates the performance of the proposed framework with six stock markets from January 2000 to June 2022, covering the period of COVID-19. Three realized measures, including 5- minute realized variance, bi-power variation, and realized kernel, are incorporated and evaluated in the proposed framework. One-step-ahead VaR and ES forecasting results of the proposed model are compared to a range of parametric and semi-parametric models, lending support to the effectiveness of the proposed framework.

Pneumatic systems are common in manufacturing, healthcare, transportation, robotics, and many other fields. Failures in these systems can have very serious consequences, particularly if they go undetected. In this work, we present an air-powered error detector device that can detect and respond to failures in pneumatically actuated systems. The device contains 21 monolithic membrane valves that act like transistors in a pneumatic logic "circuit" that uses vacuum to represent TRUE and atmospheric pressure as FALSE. Three pneumatic exclusive-OR (XOR) gates are used to calculate the parity bit corresponding to the values of several control bits. If the calculated value of the parity bit differs from the expected value, then an error (like a leak or a blocked air line) has been detected and the device outputs a pneumatic error signal which can in turn be used to alert a user, shut down the system, or take some other action. As a proof-of-concept, we used our pneumatic error detector to monitor the operation of a medical device, an intermittent pneumatic compression (IPC) device commonly used to prevent the formation of life-threatening blood clots in the wearer's legs. Experiments confirm that when the IPC device was damaged, the pneumatic error detector immediately recognized the error (a leak) and alerted the wearer using sound. By providing a simple and low-cost way to add fault detection to pneumatic actuation systems without using sensors, our pneumatic error detector can promote safety and reliability across the wide range of pneumatic systems., Comment: 23 pages, 5 figures

Checking whether two quantum circuits are approximately equivalent is a common task in quantum computing. We consider a closely related identity check problem: given a quantum circuit $U$, one has to estimate the diamond-norm distance between $U$ and the identity channel. We present a classical algorithm approximating the distance to the identity within a factor $\alpha=D+1$ for shallow geometrically local $D$-dimensional circuits provided that the circuit is sufficiently close to the identity. The runtime of the algorithm scales linearly with the number of qubits for any constant circuit depth and spatial dimension. We also show that the operator-norm distance to the identity $\|U-I\|$ can be efficiently approximated within a factor $\alpha=5$ for shallow 1D circuits and, under a certain technical condition, within a factor $\alpha=2D+3$ for shallow $D$-dimensional circuits. A numerical implementation of the identity check algorithm is reported for 1D Trotter circuits with up to 100 qubits., Comment: 10 pages, 3 figures

We consider the control problem for an infinite chain of coupled harmonic oscillators with a Langevin thermostat at the origin. We study the effect of two types of open-loop boundary controls, impulsive control and linear memory-feedback control, in the high frequency limit. We investigate their action on the reflection-transmission coefficients for the wave energy for the scattering of the thermostat. Our study shows that impulsive boundary controls have no impact on the rates and are thus not appropriate to act on the system, despite their physical meaning and relevance. In contrast, the second kind of control that we propose, which is less standard and uses the past of the state solution of the system, is adequate and relevant. We prove that any triple of rates satisfying appropriate assumptions is asymptotically reachable thanks to linear memory-feedback controls that we design explicitly.

In this paper, we study a new approach related to the convergence analysis of Ishikawa-type iterative models to a common fixed point of two non-expansive mappings in Banach spaces. The main novelty of our contribution lies in the so-called \emph{optimal error bounds}, which established some necessary and sufficient conditions for convergence and derived both the error estimates and bounds on the convergence rates for iterative schemes. Although a special interest here is devoted to the Ishikawa and modified Ishikawa iterative sequences, the theory of \emph{optimal error bounds} proposed in this paper can also be favorably applied to various types of iterative models to approximate common fixed points of non-expansive mappings., Comment: 29 pages, 9 figures

The electrocardiogram (ECG) is a valuable signal used to assess various aspects of heart health, such as heart rate and rhythm. It plays a crucial role in identifying cardiac conditions and detecting anomalies in ECG data. However, distinguishing between normal and abnormal ECG signals can be a challenging task. In this paper, we propose an approach that leverages anomaly detection to identify unhealthy conditions using solely normal ECG data for training. Furthermore, to enhance the information available and build a robust system, we suggest considering both the time series and time-frequency domain aspects of the ECG signal. As a result, we introduce a specialized network called the Multimodal Time and Spectrogram Restoration Network (TSRNet) designed specifically for detecting anomalies in ECG signals. TSRNet falls into the category of restoration-based anomaly detection and draws inspiration from both the time series and spectrogram domains. By extracting representations from both domains, TSRNet effectively captures the comprehensive characteristics of the ECG signal. This approach enables the network to learn robust representations with superior discrimination abilities, allowing it to distinguish between normal and abnormal ECG patterns more effectively. Furthermore, we introduce a novel inference method, termed Peak-based Error, that specifically focuses on ECG peaks, a critical component in detecting abnormalities. The experimental result on the large-scale dataset PTB-XL has demonstrated the effectiveness of our approach in ECG anomaly detection, while also prioritizing efficiency by minimizing the number of trainable parameters. Our code is available at https://github.com/UARK-AICV/TSRNet., Comment: Accepted at ISBI 2024

We present a novel approach in the domain of federated learning (FL), particularly focusing on addressing the challenges posed by modality heterogeneity, variability in modality availability across clients, and the prevalent issue of missing data. We introduce a meta-learning framework specifically designed for multimodal federated tasks. Our approach is motivated by the need to enable federated models to robustly adapt when exposed to new modalities, a common scenario in FL where clients often differ in the number of available modalities. The effectiveness of our proposed framework is demonstrated through extensive experimentation on an augmented MNIST dataset, enriched with audio and sign language data. We demonstrate that the proposed algorithm achieves better performance than the baseline on a subset of missing modality scenarios with careful tuning of the meta-learning rates. This is a shortened report, and our work will be extended and updated soon.

Computational models are an essential tool for the design, characterization, and discovery of novel materials. Hard computational tasks in materials science stretch the limits of existing high-performance supercomputing centers, consuming much of their simulation, analysis, and data resources. Quantum computing, on the other hand, is an emerging technology with the potential to accelerate many of the computational tasks needed for materials science. In order to do that, the quantum technology must interact with conventional high-performance computing in several ways: approximate results validation, identification of hard problems, and synergies in quantum-centric supercomputing. In this paper, we provide a perspective on how quantum-centric supercomputing can help address critical computational problems in materials science, the challenges to face in order to solve representative use cases, and new suggested directions., Comment: 60 pages, 14 figures; comments welcome

Whole-slide image (WSI) analysis plays a crucial role in cancer diagnosis and treatment. In addressing the demands of this critical task, self-supervised learning (SSL) methods have emerged as a valuable resource, leveraging their efficiency in circumventing the need for a large number of annotations, which can be both costly and time-consuming to deploy supervised methods. Nevertheless, patch-wise representation may exhibit instability in performance, primarily due to class imbalances stemming from patch selection within WSIs. In this paper, we introduce Nearby Patch Contrastive Learning (NearbyPatchCL), a novel self-supervised learning method that leverages nearby patches as positive samples and a decoupled contrastive loss for robust representation learning. Our method demonstrates a tangible enhancement in performance for downstream tasks involving patch-level multi-class classification. Additionally, we curate a new dataset derived from WSIs sourced from the Canine Cutaneous Cancer Histology, thus establishing a benchmark for the rigorous evaluation of patch-level multi-class classification methodologies. Intensive experiments show that our method significantly outperforms the supervised baseline and state-of-the-art SSL methods with top-1 classification accuracy of 87.56%. Our method also achieves comparable results while utilizing a mere 1% of labeled data, a stark contrast to the 100% labeled data requirement of other approaches. Source code: https://github.com/nvtien457/NearbyPatchCL, Comment: MMM 2024

Person Re-Identification (Re-ID) task seeks to enhance the tracking of multiple individuals by surveillance cameras. It supports multimodal tasks, including text-based person retrieval and human matching. One of the most significant challenges faced in Re-ID is clothes-changing, where the same person may appear in different outfits. While previous methods have made notable progress in maintaining clothing data consistency and handling clothing change data, they still rely excessively on clothing information, which can limit performance due to the dynamic nature of human appearances. To mitigate this challenge, we propose the Pose-Guidance Deep Supervision (PGDS), an effective framework for learning pose guidance within the Re-ID task. It consists of three modules: a human encoder, a pose encoder, and a Pose-to-Human Projection module (PHP). Our framework guides the human encoder, i.e., the main re-identification model, with pose information from the pose encoder through multiple layers via the knowledge transfer mechanism from the PHP module, helping the human encoder learn body parts information without increasing computation resources in the inference stage. Through extensive experiments, our method surpasses the performance of current state-of-the-art methods, demonstrating its robustness and effectiveness for real-world applications. Our code is available at https://github.com/huyquoctrinh/PGDS., Comment: Accepted at AVSS 2024

Randomized controlled trials (RCTs) are the accepted standard for treatment effect estimation but they can be infeasible due to ethical reasons and prohibitive costs. Single-arm trials, where all patients belong to the treatment group, can be a viable alternative but require access to an external control group. We propose an identifiable deep latent-variable model for this scenario that can also account for missing covariate observations by modeling their structured missingness patterns. Our method uses amortized variational inference to learn both group-specific and identifiable shared latent representations, which can subsequently be used for {\em (i)} patient matching if treatment outcomes are not available for the treatment group, or for {\em (ii)} direct treatment effect estimation assuming outcomes are available for both groups. We evaluate the model on a public benchmark as well as on a data set consisting of a published RCT study and real-world electronic health records. Compared to previous methods, our results show improved performance both for direct treatment effect estimation as well as for effect estimation via patient matching., Comment: Published at the 27th International Conference on Artificial Intelligence and Statistics (AISTATS) 2024

As climate change intensifies, the global imperative to shift towards sustainable energy sources becomes more pronounced. Photovoltaic (PV) energy is a favored choice due to its reliability and ease of installation. Accurate mapping of PV installations is crucial for understanding their adoption and informing energy policy. To meet this need, we introduce the SolarFormer, designed to segment solar panels from aerial imagery, offering insights into their location and size. However, solar panel identification in Computer Vision is intricate due to various factors like weather conditions, roof conditions, and Ground Sampling Distance (GSD) variations. To tackle these complexities, we present the SolarFormer, featuring a multi-scale Transformer encoder and a masked-attention Transformer decoder. Our model leverages low-level features and incorporates an instance query mechanism to enhance the localization of solar PV installations. We rigorously evaluated our SolarFormer using diverse datasets, including GGE (France), IGN (France), and USGS (California, USA), across different GSDs. Our extensive experiments consistently demonstrate that our model either matches or surpasses state-of-the-art models, promising enhanced solar panel segmentation for global sustainable energy initiatives., Comment: Pre-print

Existing privacy-preserving speech representation learning methods target a single application domain. In this paper, we present a novel framework to anonymize utterance-level speech embeddings generated by pre-trained encoders and show its effectiveness for a range of speech classification tasks. Specifically, given the representations from a pre-trained encoder, we train a Transformer to estimate the representations for the same utterances spoken by other speakers. During inference, the extracted representations can be converted into different identities to preserve privacy. We compare the results with the voice anonymization baselines from the VoicePrivacy 2022 challenge. We evaluate our framework on speaker identification for privacy and emotion recognition, depression classification, and intent classification for utility. Our method outperforms the baselines on privacy and utility in paralinguistic tasks and achieves comparable performance for intent classification., Comment: INTERSPEECH 2023

Many real-world image recognition problems, such as diagnostic medical imaging exams, are "long-tailed" $\unicode{x2013}$ there are a few common findings followed by many more relatively rare conditions. In chest radiography, diagnosis is both a long-tailed and multi-label problem, as patients often present with multiple findings simultaneously. While researchers have begun to study the problem of long-tailed learning in medical image recognition, few have studied the interaction of label imbalance and label co-occurrence posed by long-tailed, multi-label disease classification. To engage with the research community on this emerging topic, we conducted an open challenge, CXR-LT, on long-tailed, multi-label thorax disease classification from chest X-rays (CXRs). We publicly release a large-scale benchmark dataset of over 350,000 CXRs, each labeled with at least one of 26 clinical findings following a long-tailed distribution. We synthesize common themes of top-performing solutions, providing practical recommendations for long-tailed, multi-label medical image classification. Finally, we use these insights to propose a path forward involving vision-language foundation models for few- and zero-shot disease classification., Comment: Update after major revision

Reconstructing and processing the 3D objects are popular activities in the research field of computer graphics, image processing and computer vision. The 3D objects are processed based on the methods like geometric modeling, a branch of applied mathematics and computational geometry, or the machine learning algorithms based on image processing. The computation of geometrical objects includes processing the curves and surfaces, subdivision, simplification, meshing, holes filling, reconstructing, and refining the 3D surface objects on both point cloud data and triangular mesh. While the machine learning methods are developed using deep learning models. With the support of 3D laser scan devices and Lidar techniques, the obtained dataset is close to original shape of the real objects. Besides, the photography and its application based on the modern techniques in recent years help us collect data and process the 3D models more precise. This article proposes an improved method for filling holes on the 3D object surface based on an automatic segmentation. Instead of filling the hole directly as the existing methods, we now subdivide the hole before filling it. The hole is first determined and segmented automatically based on computation of its local curvature. It is then filled on each part of the hole to match its local curvature shape. The method can work on both 3D point cloud surfaces and triangular mesh surface. Comparing to the state of the art methods, our proposed method obtained higher accuracy of the reconstructed 3D objects., Comment: 20 pages, 11 figures, 37 references

Precise 3D environmental mapping is pivotal in robotics. Existing methods often rely on predefined concepts during training or are time-intensive when generating semantic maps. This paper presents Open-Fusion, a groundbreaking approach for real-time open-vocabulary 3D mapping and queryable scene representation using RGB-D data. Open-Fusion harnesses the power of a pre-trained vision-language foundation model (VLFM) for open-set semantic comprehension and employs the Truncated Signed Distance Function (TSDF) for swift 3D scene reconstruction. By leveraging the VLFM, we extract region-based embeddings and their associated confidence maps. These are then integrated with 3D knowledge from TSDF using an enhanced Hungarian-based feature-matching mechanism. Notably, Open-Fusion delivers outstanding annotation-free 3D segmentation for open-vocabulary without necessitating additional 3D training. Benchmark tests on the ScanNet dataset against leading zero-shot methods highlight Open-Fusion's superiority. Furthermore, it seamlessly combines the strengths of region-based VLFM and TSDF, facilitating real-time 3D scene comprehension that includes object concepts and open-world semantics. We encourage the readers to view the demos on our project page: https://uark-aicv.github.io/OpenFusion

Data-Free Knowledge Distillation (DFKD) has made significant recent strides by transferring knowledge from a teacher neural network to a student neural network without accessing the original data. Nonetheless, existing approaches encounter a significant challenge when attempting to generate samples from random noise inputs, which inherently lack meaningful information. Consequently, these models struggle to effectively map this noise to the ground-truth sample distribution, resulting in prolonging training times and low-quality outputs. In this paper, we propose a novel Noisy Layer Generation method (NAYER) which relocates the random source from the input to a noisy layer and utilizes the meaningful constant label-text embedding (LTE) as the input. LTE is generated by using the language model once, and then it is stored in memory for all subsequent training processes. The significance of LTE lies in its ability to contain substantial meaningful inter-class information, enabling the generation of high-quality samples with only a few training steps. Simultaneously, the noisy layer plays a key role in addressing the issue of diversity in sample generation by preventing the model from overemphasizing the constrained label information. By reinitializing the noisy layer in each iteration, we aim to facilitate the generation of diverse samples while still retaining the method's efficiency, thanks to the ease of learning provided by LTE. Experiments carried out on multiple datasets demonstrate that our NAYER not only outperforms the state-of-the-art methods but also achieves speeds 5 to 15 times faster than previous approaches. The code is available at https://github.com/tmtuan1307/nayer., Comment: Accepted at CVPR 2024