arXiv subjects

Lei Wang

Publications and source records attributed to Lei Wang.

At least 559 records · Page 31Linked to original sources

arXiv2024

Motion meets Attention: Video Motion Prompts

Videos contain rich spatio-temporal information. Traditional methods for extracting motion, used in tasks such as action recognition, often rely on visual contents rather than precise motion features. This phenomenon is referred to as 'blind motion extraction' behavior, which proves inefficient in capturing motions of interest due to a lack of motion-guided cues. Recently, attention mechanisms have enhanced many computer vision tasks by effectively highlighting salient visual areas. Inspired by this, we propose a modified Sigmoid function with learnable slope and shift parameters as an attention mechanism to modulate motion signals from frame differencing maps. This approach generates a sequence of attention maps that enhance the processing of motion-related video content. To ensure temporal continuity and smoothness of the attention maps, we apply pair-wise temporal attention variation regularization to remove unwanted motions (e.g., noise) while preserving important ones. We then perform Hadamard product between each pair of attention maps and the original video frames to highlight the evolving motions of interest over time. These highlighted motions, termed video motion prompts, are subsequently used as inputs to the model instead of the original video frames. We formalize this process as a motion prompt layer and incorporate the regularization term into the loss function to learn better motion prompts. This layer serves as an adapter between the model and the video data, bridging the gap between traditional 'blind motion extraction' and the extraction of relevant motions of interest. We show that our lightweight, plug-and-play motion prompt layer seamlessly integrates into models like SlowFast, X3D, and TimeSformer, enhancing performance on benchmarks such as FineGym and MPII Cooking 2.

cs.CV↗

arXiv2024

A novel brain registration model combining structural and functional MRI information

Although developed functional magnetic resonance imaging (fMRI) registration algorithms based on deep learning have achieved a certain degree of alignment of functional area, they underutilized fine structural information. In this paper, we propose a semi-supervised convolutional neural network (CNN) registration model that integrates both structural and functional MRI information. The model first learns to generate deformation fields by inputting structural MRI (T1w-MRI) into the CNN to capture fine structural information. Then, we construct a local functional connectivity pattern to describe the local fMRI information, and use the Bhattacharyya coefficient to measure the similarity between two fMRI images, which is used as a loss function to facilitate the alignment of functional areas. In the inter-subject registration experiment, our model achieved an average number of voxels exceeding the threshold of 4.24 is 2248 in the group-level t-test maps for the four functional brain networks (default mode network, visual network, central executive network, and sensorimotor network). Additionally, the atlas-based registration experiment results show that the average number of voxels exceeding this threshold is 3620. The results are the largest among all methods. Our model achieves an excellent registration performance in fMRI and improves the consistency of functional regions. The proposed model has the potential to optimize fMRI image processing and analysis, facilitating the development of fMRI applications.

eess.IV↗

arXiv2024

Fast Extrinsic Calibration for Multiple Inertial Measurement Units in Visual-Inertial System

In this paper, we propose a fast extrinsic calibration method for fusing multiple inertial measurement units (MIMU) to improve visual-inertial odometry (VIO) localization accuracy. Currently, data fusion algorithms for MIMU highly depend on the number of inertial sensors. Based on the assumption that extrinsic parameters between inertial sensors are perfectly calibrated, the fusion algorithm provides better localization accuracy with more IMUs, while neglecting the effect of extrinsic calibration error. Our method builds two non-linear least-squares problems to estimate the MIMU relative position and orientation separately, independent of external sensors and inertial noises online estimation. Then we give the general form of the virtual IMU (VIMU) method and propose its propagation on manifold. We perform our method on datasets, our self-made sensor board, and board with different IMUs, validating the superiority of our method over competing methods concerning speed, accuracy, and robustness. In the simulation experiment, we show that only fusing two IMUs with our calibration method to predict motion can rival nine IMUs. Real-world experiments demonstrate better localization accuracy of the VIO integrated with our calibration method and VIMU propagation on manifold.

cs.RO↗

arXiv2024

Adaptive Multi-head Contrastive Learning

In contrastive learning, two views of an original image, generated by different augmentations, are considered a positive pair, and their similarity is required to be high. Similarly, two views of distinct images form a negative pair, with encouraged low similarity. Typically, a single similarity measure, provided by a lone projection head, evaluates positive and negative sample pairs. However, due to diverse augmentation strategies and varying intra-sample similarity, views from the same image may not always be similar. Additionally, owing to inter-sample similarity, views from different images may be more akin than those from the same image. Consequently, enforcing high similarity for positive pairs and low similarity for negative pairs may be unattainable, and in some cases, such enforcement could detrimentally impact performance. To address this challenge, we propose using multiple projection heads, each producing a distinct set of features. Our pre-training loss function emerges from a solution to the maximum likelihood estimation over head-wise posterior distributions of positive samples given observations. This loss incorporates the similarity measure over positive and negative pairs, each re-weighted by an individual adaptive temperature, regulated to prevent ill solutions. Our approach, Adaptive Multi-Head Contrastive Learning (AMCL), can be applied to and experimentally enhances several popular contrastive learning methods such as SimCLR, MoCo, and Barlow Twins. The improvement remains consistent across various backbones and linear probing epochs, and becomes more significant when employing multiple augmentation methods.

cs.CV↗

arXiv2024

TrackNetV4: Enhancing Fast Sports Object Tracking with Motion Attention Maps

Accurately detecting and tracking high-speed, small objects, such as balls in sports videos, is challenging due to factors like motion blur and occlusion. Although recent deep learning frameworks like TrackNetV1, V2, and V3 have advanced tennis ball and shuttlecock tracking, they often struggle in scenarios with partial occlusion or low visibility. This is primarily because these models rely heavily on visual features without explicitly incorporating motion information, which is crucial for precise tracking and trajectory prediction. In this paper, we introduce an enhancement to the TrackNet family by fusing high-level visual features with learnable motion attention maps through a motion-aware fusion mechanism, effectively emphasizing the moving ball's location and improving tracking performance. Our approach leverages frame differencing maps, modulated by a motion prompt layer, to highlight key motion regions over time. Experimental results on the tennis ball and shuttlecock datasets show that our method enhances the tracking performance of both TrackNetV2 and V3. We refer to our lightweight, plug-and-play solution, built on top of the existing TrackNet, as TrackNetV4.

cs.CV↗

arXiv2024

Hypersphere Secure Sketch Revisited: Probabilistic Linear Regression Attack on IronMask in Multiple Usage

Protection of biometric templates is a critical and urgent area of focus. IronMask demonstrates outstanding recognition performance while protecting facial templates against existing known attacks. In high-level, IronMask can be conceptualized as a fuzzy commitment scheme building on the hypersphere directly. We devise an attack on IronMask targeting on the security notion of renewability. Our attack, termed as Probabilistic Linear Regression Attack, utilizes the linearity of underlying used error correcting code. This attack is the first algorithm to successfully recover the original template when getting multiple protected templates in acceptable time and requirement of storage. We implement experiments on IronMask applied to protect ArcFace that well verify the validity of our attacks. Furthermore, we carry out experiments in noisy environments and confirm that our attacks are still applicable. Finally, we put forward two strategies to mitigate this type of attacks.

cs.CR↗

arXiv2024

SpMis: An Investigation of Synthetic Spoken Misinformation Detection

In recent years, speech generation technology has advanced rapidly, fueled by generative models and large-scale training techniques. While these developments have enabled the production of high-quality synthetic speech, they have also raised concerns about the misuse of this technology, particularly for generating synthetic misinformation. Current research primarily focuses on distinguishing machine-generated speech from human-produced speech, but the more urgent challenge is detecting misinformation within spoken content. This task requires a thorough analysis of factors such as speaker identity, topic, and synthesis. To address this need, we conduct an initial investigation into synthetic spoken misinformation detection by introducing an open-source dataset, SpMis. SpMis includes speech synthesized from over 1,000 speakers across five common topics, utilizing state-of-the-art text-to-speech systems. Although our results show promising detection capabilities, they also reveal substantial challenges for practical implementation, underscoring the importance of ongoing research in this critical area.

cs.CL↗

arXiv2024

First Indication of Solar $^8$B Neutrino Flux through Coherent Elastic Neutrino-Nucleus Scattering in PandaX-4T

The PandaX-4T liquid xenon detector at the China Jinping Underground Laboratory is used to measure the solar $^8$B neutrino flux by detecting neutrinos through coherent scattering with xenon nuclei. Data samples requiring the coincidence of scintillation and ionization signals (paired), as well as unpaired ionization-only signals (US2), are selected with energy threshold of approximately 1.1 keV (0.33 keV) nuclear recoil energy. Combining the commissioning run and the first science run of PandaX-4T, a total exposure of 1.20 and 1.04 tonne$\cdot$year are collected for the paired and US2, respectively. After unblinding, 3 and 332 events are observed with an expectation of 2.8$\pm$0.5 and 251$\pm$32 background events, for the paired and US2 data, respectively. A combined analysis yields a best-fit $^8$B neutrino signal of 3.5 (75) events from the paired (US2) data sample, with $\sim$37\% uncertainty, and the background-only hypothesis is disfavored at 2.64$σ$ significance. This gives a solar $^8$B neutrino flux of ($8.4\pm3.1$)$\times$10$^6$ cm$^{-2}$s$^{-1}$, consistent with the standard solar model prediction. It is also the first indication of solar $^8$B neutrino ``fog'' in a dark matter direct detection experiment.

hep-ex↗

arXiv2024

KARGEN: Knowledge-enhanced Automated Radiology Report Generation Using Large Language Models

Harnessing the robust capabilities of Large Language Models (LLMs) for narrative generation, logical reasoning, and common-sense knowledge integration, this study delves into utilizing LLMs to enhance automated radiology report generation (R2Gen). Despite the wealth of knowledge within LLMs, efficiently triggering relevant knowledge within these large models for specific tasks like R2Gen poses a critical research challenge. This paper presents KARGEN, a Knowledge-enhanced Automated radiology Report GENeration framework based on LLMs. Utilizing a frozen LLM to generate reports, the framework integrates a knowledge graph to unlock chest disease-related knowledge within the LLM to enhance the clinical utility of generated reports. This is achieved by leveraging the knowledge graph to distill disease-related features in a designed way. Since a radiology report encompasses both normal and disease-related findings, the extracted graph-enhanced disease-related features are integrated with regional image features, attending to both aspects. We explore two fusion methods to automatically prioritize and select the most relevant features. The fused features are employed by LLM to generate reports that are more sensitive to diseases and of improved quality. Our approach demonstrates promising results on the MIMIC-CXR and IU-Xray datasets.

cs.CV↗

arXiv2024

A Double Tracking Method for Optimization with Decentralized Generalized Orthogonality Constraints

In this paper, we consider the decentralized optimization problems with generalized orthogonality constraints, where both the objective function and the constraint exhibit a distributed structure. Such optimization problems, albeit ubiquitous in practical applications, remain unsolvable by existing algorithms in the presence of distributed constraints. To address this issue, we convert the original problem into an unconstrained penalty model by resorting to the recently proposed constraint-dissolving operator. However, this transformation compromises the essential property of separability in the resulting penalty function, rendering it impossible to employ existing algorithms to solve. We overcome this difficulty by introducing a novel algorithm that tracks the gradient of the objective function and the Jacobian of the constraint mapping simultaneously. The global convergence guarantee is rigorously established with an iteration complexity. To substantiate the effectiveness and efficiency of our proposed algorithm, we present numerical results on both synthetic and real-world datasets.

math.OC↗

arXiv2024

Rapid Automatic Multiple Moving Objects Detection Method Based on Feature Extraction from Images with Non-sidereal Tracking

Optically observing and monitoring moving objects, both natural and artificial, is important to human space security. Non-sidereal tracking can improve the system's limiting magnitude for moving objects, which benefits the surveillance. However, images with non-sidereal tracking include complex background, as well as objects with different brightness and moving mode, posing a significant challenge for accurate multi-object detection in such images, especially in wide field of view (WFOV) telescope images. To achieve a higher detection precision in a higher speed, we proposed a novel object detection method, which combines the source feature extraction and the neural network. First, our method extracts object features from optical images such as centroid, shape, and flux. Then it conducts a naive labeling based on those features to distinguish moving objects from stars. After balancing the labeled data, we employ it to train a neural network aimed at creating a classification model for point-like and streak-like objects. Ultimately, based on the neural network model's classification outcomes, moving objects whose motion modes consistent with the tracked objects are detected via track association, while objects with different motion modes are detected using morphological statistics. The validation, based on the space objects images captured in target tracking mode with the 1-meter telescope at Nanshan, Xinjiang Astronomical Observatory, demonstrates that our method achieves 94.72% detection accuracy with merely 5.02% false alarm rate, and a processing time of 0.66s per frame. Consequently, our method can rapidly and accurately detect objects with different motion modes from wide-field images with non-sidereal tracking.

astro-ph.IM↗

arXiv2024

MoManifold: Learning to Measure 3D Human Motion via Decoupled Joint Acceleration Manifolds

Incorporating temporal information effectively is important for accurate 3D human motion estimation and generation which have wide applications from human-computer interaction to AR/VR. In this paper, we present MoManifold, a novel human motion prior, which models plausible human motion in continuous high-dimensional motion space. Different from existing mathematical or VAE-based methods, our representation is designed based on the neural distance field, which makes human dynamics explicitly quantified to a score and thus can measure human motion plausibility. Specifically, we propose novel decoupled joint acceleration manifolds to model human dynamics from existing limited motion data. Moreover, we introduce a novel optimization method using the manifold distance as guidance, which facilitates a variety of motion-related tasks. Extensive experiments demonstrate that MoManifold outperforms existing SOTAs as a prior in several downstream tasks such as denoising real-world human mocap data, recovering human motion from partial 3D observations, mitigating jitters for SMPL-based pose estimators, and refining the results of motion in-betweening.

cs.CV↗

arXiv2024

Text-Region Matching for Multi-Label Image Recognition with Missing Labels

Recently, large-scale visual language pre-trained (VLP) models have demonstrated impressive performance across various downstream tasks. Motivated by these advancements, pioneering efforts have emerged in multi-label image recognition with missing labels, leveraging VLP prompt-tuning technology. However, they usually cannot match text and vision features well, due to complicated semantics gaps and missing labels in a multi-label image. To tackle this challenge, we propose $\textbf{T}$ext-$\textbf{R}$egion $\textbf{M}$atching for optimizing $\textbf{M}$ulti-$\textbf{L}$abel prompt tuning, namely TRM-ML, a novel method for enhancing meaningful cross-modal matching. Compared to existing methods, we advocate exploring the information of category-aware regions rather than the entire image or pixels, which contributes to bridging the semantic gap between textual and visual representations in a one-to-one matching manner. Concurrently, we further introduce multimodal contrastive learning to narrow the semantic gap between textual and visual modalities and establish intra-class and inter-class relationships. Additionally, to deal with missing labels, we propose a multimodal category prototype that leverages intra- and inter-category semantic relationships to estimate unknown labels, facilitating pseudo-label generation. Extensive experiments on the MS-COCO, PASCAL VOC, Visual Genome, NUS-WIDE, and CUB-200-211 benchmark datasets demonstrate that our proposed framework outperforms the state-of-the-art methods by a significant margin. Our code is available here: https://github.com/yu-gi-oh-leilei/TRM-ML.

cs.CV↗

arXiv2024

Could Bibliometrics Reveal Top Science and Technology Achievements and Researchers? The Case for Evaluatology-based Science and Technology Evaluation

By utilizing statistical methods to analyze bibliographic data, bibliometrics faces inherent limitations in identifying the most significant science and technology achievements and researchers. To overcome this challenge, we present an evaluatology-based science and technology evaluation methodology. At the heart of this approach lies the concept of an extended evaluation condition, encompassing eight crucial components derived from a field. We define four relationships that illustrate the connections among various achievements based on their mapped extended EC components, as well as their temporal and citation links. Within a relationship under an extended evaluation condition, evaluators can effectively compare these achievements by carefully addressing the influence of confounding variables. We establish a real-world evaluation system encompassing an entire collection of achievements, each of which is mapped to several components of an extended EC. Within a specific field like chip technology or open source, we construct a perfect evaluation model that can accurately trace the evolution and development of all achievements in terms of four relationships based on the real-world evaluation system. Building upon the foundation of the perfect evaluation model, we put forth four-round rules to eliminate non-significant achievements by utilizing four relationships. This process allows us to establish a pragmatic evaluation model that effectively captures the essential achievements, serving as a curated collection of the top N achievements within a specific field during a specific timeframe. We present a case study on the top 100 Chip achievements which highlights its practical application and efficacy in identifying significant achievements and researchers that otherwise can not be identified by using bibliometrics.

cs.CE↗

arXiv2024

SATO: Stable Text-to-Motion Framework

Is the Text to Motion model robust? Recent advancements in Text to Motion models primarily stem from more accurate predictions of specific actions. However, the text modality typically relies solely on pre-trained Contrastive Language-Image Pretraining (CLIP) models. Our research has uncovered a significant issue with the text-to-motion model: its predictions often exhibit inconsistent outputs, resulting in vastly different or even incorrect poses when presented with semantically similar or identical text inputs. In this paper, we undertake an analysis to elucidate the underlying causes of this instability, establishing a clear link between the unpredictability of model outputs and the erratic attention patterns of the text encoder module. Consequently, we introduce a formal framework aimed at addressing this issue, which we term the Stable Text-to-Motion Framework (SATO). SATO consists of three modules, each dedicated to stable attention, stable prediction, and maintaining a balance between accuracy and robustness trade-off. We present a methodology for constructing an SATO that satisfies the stability of attention and prediction. To verify the stability of the model, we introduced a new textual synonym perturbation dataset based on HumanML3D and KIT-ML. Results show that SATO is significantly more stable against synonyms and other slight perturbations while keeping its high accuracy performance.

cs.CV↗

arXiv2024

MatterGPT: A Generative Transformer for Multi-Property Inverse Design of Solid-State Materials

Inverse design of solid-state materials with desired properties represents a formidable challenge in materials science. Although recent generative models have demonstrated potential, their adoption has been hindered by limitations such as inefficiency, architectural constraints and restricted open-source availability. The representation of crystal structures using the SLICES (Simplified Line-Input Crystal-Encoding System) notation as a string of characters enables the use of state-of-the-art natural language processing models, such as Transformers, for crystal design. Drawing inspiration from the success of GPT models in generating coherent text, we trained a generative Transformer on the next-token prediction task to generate solid-state materials with targeted properties. We demonstrate MatterGPT's capability to generate de novo crystal structures with targeted single properties, including both lattice-insensitive (formation energy) and lattice-sensitive (band gap) properties. Furthermore, we extend MatterGPT to simultaneously target multiple properties, addressing the complex challenge of multi-objective inverse design of crystals. Our approach showcases high validity, uniqueness, and novelty in generated structures, as well as the ability to generate materials with properties beyond the training data distribution. This work represents a significant step forward in computational materials discovery, offering a powerful and open tool for designing materials with tailored properties for various applications in energy, electronics, and beyond.

cond-mat.mtrl-sci↗

arXiv2024

Prioritizing Modalities: Flexible Importance Scheduling in Federated Multimodal Learning

Federated Learning (FL) is a distributed machine learning approach that enables devices to collaboratively train models without sharing their local data, ensuring user privacy and scalability. However, applying FL to real-world data presents challenges, particularly as most existing FL research focuses on unimodal data. Multimodal Federated Learning (MFL) has emerged to address these challenges, leveraging modality-specific encoder models to process diverse datasets. Current MFL methods often uniformly allocate computational frequencies across all modalities, which is inefficient for IoT devices with limited resources. In this paper, we propose FlexMod, a novel approach to enhance computational efficiency in MFL by adaptively allocating training resources for each modality encoder based on their importance and training requirements. We employ prototype learning to assess the quality of modality encoders, use Shapley values to quantify the importance of each modality, and adopt the Deep Deterministic Policy Gradient (DDPG) method from deep reinforcement learning to optimize the allocation of training resources. Our method prioritizes critical modalities, optimizing model performance and resource utilization. Experimental results on three real-world datasets demonstrate that our proposed method significantly improves the performance of MFL models.

cs.LG↗

arXiv2024

You Only Acquire Sparse-channel (YOAS): A Unified Framework for Dense-channel EEG Generation

High-precision acquisition of dense-channel electroencephalogram (EEG) signals is often impeded by the costliness and lack of portability of equipment. In contrast, generating dense-channel EEG signals effectively from sparse channels shows promise and economic viability. However, sparse-channel EEG poses challenges such as reduced spatial resolution, information loss, signal mixing, and heightened susceptibility to noise and interference. To address these challenges, we first theoretically formulate the dense-channel EEG generation problem as by optimizing a set of cross-channel EEG signal generation problems. Then, we propose the YOAS framework for generating dense-channel data from sparse-channel EEG signals. The YOAS totally consists of four sequential stages: Data Preparation, Data Preprocessing, Biased-EEG Generation, and Synthetic EEG Generation. Data Preparation and Preprocessing carefully consider the distribution of EEG electrodes and low signal-to-noise ratio problem of EEG signals. Biased-EEG Generation includes sub-modules of BiasEEGGanFormer and BiasEEGDiffFormer, which facilitate long-term feature extraction with attention and generate signals by combining electrode position alignment with diffusion model, respectively. Synthetic EEG Generation synthesizes the final signals, employing a deduction paradigm for multi-channel EEG generation. Extensive experiments confirmed YOAS's feasibility, efficiency, and theoretical validity, even remarkably enhancing data discernibility. This breakthrough in dense-channel EEG signal generation from sparse-channel data opens new avenues for exploration in EEG signal processing and application.

cs.CV↗