arXiv subjects

Xiao Wang

Publications and source records attributed to Xiao Wang.

At least 379 records · Page 21Linked to original sources

arXiv2024

Video DataFlywheel: Resolving the Impossible Data Trinity in Video-Language Understanding

Recently, video-language understanding has achieved great success through large-scale pre-training. However, data scarcity remains a prevailing challenge. This study quantitatively reveals an "impossible trinity" among data quantity, diversity, and quality in pre-training datasets. Recent efforts seek to refine large-scale, diverse ASR datasets compromised by low quality through synthetic annotations. These methods successfully leverage useful information in multimodal video content (frames, tags, ASR transcripts, etc.) to refine the original annotations. Nevertheless, they struggle to mitigate noise within synthetic annotations and lack scalability as the dataset size expands. To address these issues, we introduce the Video DataFlywheel framework, which iteratively refines video annotations with improved noise control methods. For iterative refinement, we first leverage a video-language model to generate synthetic annotations, resulting in a refined dataset. Then, we pre-train on it and fine-tune on human refinement examples for a stronger model. These processes are repeated for continuous improvement. For noise control, we present AdaTaiLr, a novel noise control method that requires weaker assumptions on noise distribution, thereby proving more effective in large datasets with theoretical guarantees. The combination of iterative refinement and AdaTaiLr can achieve better scalability in video-language understanding. Extensive experiments show that our framework outperforms existing data refinement baselines, delivering a 3% performance boost and improving dataset quality with minimal diversity loss. Furthermore, our refined dataset facilitates significant improvements in various video-language understanding tasks, including video question answering and text-video retrieval.

cs.CV↗

arXiv2024

Adaptive Learning of the Latent Space of Wasserstein Generative Adversarial Networks

Generative models based on latent variables, such as generative adversarial networks (GANs) and variational auto-encoders (VAEs), have gained lots of interests due to their impressive performance in many fields. However, many data such as natural images usually do not populate the ambient Euclidean space but instead reside in a lower-dimensional manifold. Thus an inappropriate choice of the latent dimension fails to uncover the structure of the data, possibly resulting in mismatch of latent representations and poor generative qualities. Towards addressing these problems, we propose a novel framework called the latent Wasserstein GAN (LWGAN) that fuses the Wasserstein auto-encoder and the Wasserstein GAN so that the intrinsic dimension of the data manifold can be adaptively learned by a modified informative latent distribution. We prove that there exist an encoder network and a generator network in such a way that the intrinsic dimension of the learned encoding distribution is equal to the dimension of the data manifold. We theoretically establish that our estimated intrinsic dimension is a consistent estimate of the true dimension of the data manifold. Meanwhile, we provide an upper bound on the generalization error of LWGAN, implying that we force the synthetic data distribution to be similar to the real data distribution from a population perspective. Comprehensive empirical experiments verify our framework and show that LWGAN is able to identify the correct intrinsic dimension under several scenarios, and simultaneously generate high-quality synthetic data by sampling from the learned latent distribution.

stat.ML↗

arXiv2024

Gravitational waves from cosmological first-order phase transitions with precise hydrodynamics

We calculate the gravitational wave spectrum generated by sound waves during a cosmological phase transition, incorporating several advancements beyond the current state-of-the-art. Rather than relying on the bag model or similar approximations, we derive the equation of state directly from the effective potential. This approach enables us to accurately determine the hydrodynamic quantities, which serve as initial conditions in a generalised hybrid simulation. This simulation tracks the fluid evolution after bubble collisions, leading to the generation of gravitational waves. Our work is the first self-consistent numerical calculation of gravitational waves for the real singlet extension of the standard model. Our computational method is adaptable to any particle physics model, offering a fast and reliable way to calculate gravitational waves generated by sound waves. With fewer approximations, our approach provides a robust foundation for precise gravitational wave calculations and allows for the exploration of model-independent features of gravitational waves from phase transitions.

hep-ph↗

arXiv2024

Hierarchical Graph Interaction Transformer with Dynamic Token Clustering for Camouflaged Object Detection

Camouflaged object detection (COD) aims to identify the objects that seamlessly blend into the surrounding backgrounds. Due to the intrinsic similarity between the camouflaged objects and the background region, it is extremely challenging to precisely distinguish the camouflaged objects by existing approaches. In this paper, we propose a hierarchical graph interaction network termed HGINet for camouflaged object detection, which is capable of discovering imperceptible objects via effective graph interaction among the hierarchical tokenized features. Specifically, we first design a region-aware token focusing attention (RTFA) with dynamic token clustering to excavate the potentially distinguishable tokens in the local region. Afterwards, a hierarchical graph interaction transformer (HGIT) is proposed to construct bi-directional aligned communication between hierarchical features in the latent interaction space for visual semantics enhancement. Furthermore, we propose a decoder network with confidence aggregated feature fusion (CAFF) modules, which progressively fuses the hierarchical interacted features to refine the local detail in ambiguous regions. Extensive experiments conducted on the prevalent datasets, i.e. COD10K, CAMO, NC4K and CHAMELEON demonstrate the superior performance of HGINet compared to existing state-of-the-art methods. Our code is available at https://github.com/Garyson1204/HGINet.

cs.CV↗

arXiv2024

Direct evidence for anisotropic magnetic interaction in $α$-RuCl$_3$ from polarized inelastic neutron scattering

Polarized neutron scattering experiments reveal the anisotropy of magnetic correlations in the candidate Kitaev material $α$-RuCl$_3$. The anisotropy of the inelastic response at the magnetic Bragg positions is just opposite to the expectation for a simple Heisenberg model. Near the antiferromagnetic $q$ vector, there are no low-energy transversal magnon modes directly documenting the fully anisotropic and bond-directional character of the magnetic interaction in $α$-RuCl$_3$. However, other findings disagree with a simple or strongly dominant Kitaev component.

cond-mat.str-el↗

arXiv2024

Uncertainty-aware Bridge based Mobile-Former Network for Event-based Pattern Recognition

The mainstream human activity recognition (HAR) algorithms are developed based on RGB cameras, which are easily influenced by low-quality images (e.g., low illumination, motion blur). Meanwhile, the privacy protection issue caused by ultra-high definition (HD) RGB cameras aroused more and more people's attention. Inspired by the success of event cameras which perform better on high dynamic range, no motion blur, and low energy consumption, we propose to recognize human actions based on the event stream. We propose a lightweight uncertainty-aware information propagation based Mobile-Former network for efficient pattern recognition, which aggregates the MobileNet and Transformer network effectively. Specifically, we first embed the event images using a stem network into feature representations, then, feed them into uncertainty-aware Mobile-Former blocks for local and global feature learning and fusion. Finally, the features from MobileNet and Transformer branches are concatenated for pattern recognition. Extensive experiments on multiple event-based recognition datasets fully validated the effectiveness of our model. The source code of this work will be released at https://github.com/Event-AHU/Uncertainty_aware_MobileFormer.

cs.CV↗

arXiv2024

Self-consistent prediction of gravitational waves from cosmological phase transitions

Gravitational waves from cosmological phase transitions are novel probes of fundamental physics, making their precise calculation essential for revealing various mysteries of the early Universe. In this work we propose a framework that enables the consistent calculation of such gravitational waves sourced by sound waves. Starting from the Lagrangian, this framework integrates the calculation of the dynamics of first-order phase transitions in a self-consistent manner, eliminating various approximations typically introduced by conventional methods. At the heart of our approach is the congruous evaluation of the phase transition hydrodynamics that, at every step, is consistently informed by the Lagrangian. We demonstrate the application of our framework using the SM+$|H|^6$ model, deriving the corresponding gravitational wave spectrum. Our framework establishes a robust foundation for the precise prediction of gravitational waves from phase transitions.

hep-ph↗

arXiv2024

MCBA: A Matroid Constraint-Based Approach for Composite Service Recommendation Considering Compatibility and Diversity

With the growing popularity of microservices, many companies are encapsulating their business processes as Web APIs for remote invocation. These lightweight Web APIs offer mashup developers an efficient way to achieve complex functionalities without starting from scratch. However, this also presents challenges, such as the concentration of developers'search results on popular APIs limiting diversity, and difficulties in verifying API compatibility. A method is needed to recommend diverse compositions of compatible APIs that fulfill mashup functional requirements from a large pool of candidate APIs. To tackle this issue, this paper introduces a Matroid Constraint-Based Approach (MCBA) for composite service recommendation, consisting of two stages: API composition discovery focusing on compatibility and top-k composition recommendation focusing on diversity. In the first stage, the API composition issue is formulated as a minimal group Steiner tree (MGST) problem, subsequently addressed by a "compression-solution" algorithm. In the second stage, a Maximum Marginal Relevance method under partition matroid constraints (MMR-PMC) is employed to ensure recommendation diversity. Comprehensive experiments on the real-world dataset show that MCBA surpasses several state-of-the-art methods in terms of accuracy, compatibility, diversity, and efficiency.

cs.SE↗

arXiv2024

Pedestrian Attribute Recognition via CLIP based Prompt Vision-Language Fusion

Existing pedestrian attribute recognition (PAR) algorithms adopt pre-trained CNN (e.g., ResNet) as their backbone network for visual feature learning, which might obtain sub-optimal results due to the insufficient employment of the relations between pedestrian images and attribute labels. In this paper, we formulate PAR as a vision-language fusion problem and fully exploit the relations between pedestrian images and attribute labels. Specifically, the attribute phrases are first expanded into sentences, and then the pre-trained vision-language model CLIP is adopted as our backbone for feature embedding of visual images and attribute descriptions. The contrastive learning objective connects the vision and language modalities well in the CLIP-based feature space, and the Transformer layers used in CLIP can capture the long-range relations between pixels. Then, a multi-modal Transformer is adopted to fuse the dual features effectively and feed-forward network is used to predict attributes. To optimize our network efficiently, we propose the region-aware prompt tuning technique to adjust very few parameters (i.e., only the prompt vectors and classification heads) and fix both the pre-trained VL model and multi-modal Transformer. Our proposed PAR algorithm only adjusts 0.75% learnable parameters compared with the fine-tuning strategy. It also achieves new state-of-the-art performance on both standard and zero-shot settings for PAR, including RAPv1, RAPv2, WIDER, PA100K, and PETA-ZS, RAP-ZS datasets. The source code and pre-trained models will be released on https://github.com/Event-AHU/OpenPAR.

cs.CV↗

arXiv2024

Ig3D: Integrating 3D Face Representations in Facial Expression Inference

Reconstructing 3D faces with facial geometry from single images has allowed for major advances in animation, generative models, and virtual reality. However, this ability to represent faces with their 3D features is not as fully explored by the facial expression inference (FEI) community. This study therefore aims to investigate the impacts of integrating such 3D representations into the FEI task, specifically for facial expression classification and face-based valence-arousal (VA) estimation. To accomplish this, we first assess the performance of two 3D face representations (both based on the 3D morphable model, FLAME) for the FEI tasks. We further explore two fusion architectures, intermediate fusion and late fusion, for integrating the 3D face representations with existing 2D inference frameworks. To evaluate our proposed architecture, we extract the corresponding 3D representations and perform extensive tests on the AffectNet and RAF-DB datasets. Our experimental results demonstrate that our proposed method outperforms the state-of-the-art AffectNet VA estimation and RAF-DB classification tasks. Moreover, our method can act as a complement to other existing methods to boost performance in many emotion inference tasks.

cs.CV↗

arXiv2024

Magnetization oscillations in a periodically driven transverse field Ising chain

We investigate the nonequilibrium dynamics of the magnetization in an Ising chain subjected to a slowly rotating transverse field. The magnetization oscillations are found to be explained by the contributions from different particle excitations in the quantum $E_8$ model. We study the magnetization in the frequency domain in detail, uncovering a series of singular peaks for the $z$ (Ising) component. These singular peaks are split into two sets for the magnetization along $x$ and $y$ directions with frequency shifts set by the rotational-field frequency. The peaks include both $δ$-function type and edge-singularity type peaks. The $δ$-function peaks can be attributed to particle excitations involving an $E_8$ particle with either the vacuum or a different particle. The edge-singularity peaks are contributed by particle excitations of two $E_8$ particles with either the vacuum or another particle, or by particle excitations that contain two sets of two particles with each set including at least a particle of the same type. We propose a Rydberg qubit array for possible experimental investigation.

cond-mat.str-el↗

arXiv2024

VFM-Det: Towards High-Performance Vehicle Detection via Large Foundation Models

Existing vehicle detectors are usually obtained by training a typical detector (e.g., YOLO, RCNN, DETR series) on vehicle images based on a pre-trained backbone (e.g., ResNet, ViT). Some researchers also exploit and enhance the detection performance using pre-trained large foundation models. However, we think these detectors may only get sub-optimal results because the large models they use are not specifically designed for vehicles. In addition, their results heavily rely on visual features, and seldom of they consider the alignment between the vehicle's semantic information and visual representations. In this work, we propose a new vehicle detection paradigm based on a pre-trained foundation vehicle model (VehicleMAE) and a large language model (T5), termed VFM-Det. It follows the region proposal-based detection framework and the features of each proposal can be enhanced using VehicleMAE. More importantly, we propose a new VAtt2Vec module that predicts the vehicle semantic attributes of these proposals and transforms them into feature vectors to enhance the vision features via contrastive learning. Extensive experiments on three vehicle detection benchmark datasets thoroughly proved the effectiveness of our vehicle detector. Specifically, our model improves the baseline approach by $+5.1\%$, $+6.2\%$ on the $AP_{0.5}$, $AP_{0.75}$ metrics, respectively, on the Cityscapes dataset.The source code of this work will be released at https://github.com/Event-AHU/VFM-Det.

cs.CV↗

arXiv2024

MambaEVT: Event Stream based Visual Object Tracking using State Space Model

Event camera-based visual tracking has drawn more and more attention in recent years due to the unique imaging principle and advantages of low energy consumption, high dynamic range, and dense temporal resolution. Current event-based tracking algorithms are gradually hitting their performance bottlenecks, due to the utilization of vision Transformer and the static template for target object localization. In this paper, we propose a novel Mamba-based visual tracking framework that adopts the state space model with linear complexity as a backbone network. The search regions and target template are fed into the vision Mamba network for simultaneous feature extraction and interaction. The output tokens of search regions will be fed into the tracking head for target localization. More importantly, we consider introducing a dynamic template update strategy into the tracking framework using the Memory Mamba network. By considering the diversity of samples in the target template library and making appropriate adjustments to the template memory module, a more effective dynamic template can be integrated. The effective combination of dynamic and static templates allows our Mamba-based tracking algorithm to achieve a good balance between accuracy and computational cost on multiple large-scale datasets, including EventVOT, VisEvent, and FE240hz. The source code will be released on https://github.com/Event-AHU/MambaEVT

cs.CV↗

arXiv2024

ORBIT: Oak Ridge Base Foundation Model for Earth System Predictability

Earth system predictability is challenged by the complexity of environmental dynamics and the multitude of variables involved. Current AI foundation models, although advanced by leveraging large and heterogeneous data, are often constrained by their size and data integration, limiting their effectiveness in addressing the full range of Earth system prediction challenges. To overcome these limitations, we introduce the Oak Ridge Base Foundation Model for Earth System Predictability (ORBIT), an advanced vision transformer model that scales up to 113 billion parameters using a novel hybrid tensor-data orthogonal parallelism technique. As the largest model of its kind, ORBIT surpasses the current climate AI foundation model size by a thousandfold. Performance scaling tests conducted on the Frontier supercomputer have demonstrated that ORBIT achieves 684 petaFLOPS to 1.6 exaFLOPS sustained throughput, with scaling efficiency maintained at 41% to 85% across 49,152 AMD GPUs. These breakthroughs establish new advances in AI-driven climate modeling and demonstrate promise to significantly improve the Earth system predictability.

physics.ao-ph↗

arXiv2024

Pedestrian Attribute Recognition: A New Benchmark Dataset and A Large Language Model Augmented Framework

Pedestrian Attribute Recognition (PAR) is one of the indispensable tasks in human-centered research. However, existing datasets neglect different domains (e.g., environments, times, populations, and data sources), only conducting simple random splits, and the performance of these datasets has already approached saturation. In the past five years, no large-scale dataset has been opened to the public. To address this issue, this paper proposes a new large-scale, cross-domain pedestrian attribute recognition dataset to fill the data gap, termed MSP60K. It consists of 60,122 images and 57 attribute annotations across eight scenarios. Synthetic degradation is also conducted to further narrow the gap between the dataset and real-world challenging scenarios. To establish a more rigorous benchmark, we evaluate 17 representative PAR models under both random and cross-domain split protocols on our dataset. Additionally, we propose an innovative Large Language Model (LLM) augmented PAR framework, named LLM-PAR. This framework processes pedestrian images through a Vision Transformer (ViT) backbone to extract features and introduces a multi-embedding query Transformer to learn partial-aware features for attribute classification. Significantly, we enhance this framework with LLM for ensemble learning and visual feature augmentation. Comprehensive experiments across multiple PAR benchmark datasets have thoroughly validated the efficacy of our proposed framework. The dataset and source code accompanying this paper will be made publicly available at \url{https://github.com/Event-AHU/OpenPAR}.

cs.CV↗

arXiv2024

Event Stream based Human Action Recognition: A High-Definition Benchmark Dataset and Algorithms

Human Action Recognition (HAR) stands as a pivotal research domain in both computer vision and artificial intelligence, with RGB cameras dominating as the preferred tool for investigation and innovation in this field. However, in real-world applications, RGB cameras encounter numerous challenges, including light conditions, fast motion, and privacy concerns. Consequently, bio-inspired event cameras have garnered increasing attention due to their advantages of low energy consumption, high dynamic range, etc. Nevertheless, most existing event-based HAR datasets are low resolution ($346 \times 260$). In this paper, we propose a large-scale, high-definition ($1280 \times 800$) human action recognition dataset based on the CeleX-V event camera, termed CeleX-HAR. It encompasses 150 commonly occurring action categories, comprising a total of 124,625 video sequences. Various factors such as multi-view, illumination, action speed, and occlusion are considered when recording these data. To build a more comprehensive benchmark dataset, we report over 20 mainstream HAR models for future works to compare. In addition, we also propose a novel Mamba vision backbone network for event stream based HAR, termed EVMamba, which equips the spatial plane multi-directional scanning and novel voxel temporal scanning mechanism. By encoding and mining the spatio-temporal information of event streams, our EVMamba has achieved favorable results across multiple datasets. Both the dataset and source code will be released on \url{https://github.com/Event-AHU/CeleX-HAR}

cs.CV↗

arXiv2024

Treat Stillness with Movement: Remote Sensing Change Detection via Coarse-grained Temporal Foregrounds Mining

Current works focus on addressing the remote sensing change detection task using bi-temporal images. Although good performance can be achieved, however, seldom of they consider the motion cues which may also be vital. In this work, we revisit the widely adopted bi-temporal images-based framework and propose a novel Coarse-grained Temporal Mining Augmented (CTMA) framework. To be specific, given the bi-temporal images, we first transform them into a video using interpolation operations. Then, a set of temporal encoders is adopted to extract the motion features from the obtained video for coarse-grained changed region prediction. Subsequently, we design a novel Coarse-grained Foregrounds Augmented Spatial Encoder module to integrate both global and local information. We also introduce a motion augmented strategy that leverages motion cues as an additional output to aggregate with the spatial features for improved results. Meanwhile, we feed the input image pairs into the ResNet to get the different features and also the spatial blocks for fine-grained feature learning. More importantly, we propose a mask augmented strategy that utilizes coarse-grained changed regions, incorporating them into the decoder blocks to enhance the final changed prediction. Extensive experiments conducted on multiple benchmark datasets fully validated the effectiveness of our proposed framework for remote sensing image change detection. The source code of this paper will be released on https://github.com/Event-AHU/CTM_Remote_Sensing_Change_Detection

cs.CV↗

arXiv2024

Temporal Residual Guided Diffusion Framework for Event-Driven Video Reconstruction

Event-based video reconstruction has garnered increasing attention due to its advantages, such as high dynamic range and rapid motion capture capabilities. However, current methods often prioritize the extraction of temporal information from continuous event flow, leading to an overemphasis on low-frequency texture features in the scene, resulting in over-smoothing and blurry artifacts. Addressing this challenge necessitates the integration of conditional information, encompassing temporal features, low-frequency texture, and high-frequency events, to guide the Denoising Diffusion Probabilistic Model (DDPM) in producing accurate and natural outputs. To tackle this issue, we introduce a novel approach, the Temporal Residual Guided Diffusion Framework, which effectively leverages both temporal and frequency-based event priors. Our framework incorporates three key conditioning modules: a pre-trained low-frequency intensity estimation module, a temporal recurrent encoder module, and an attention-based high-frequency prior enhancement module. In order to capture temporal scene variations from the events at the current moment, we employ a temporal-domain residual image as the target for the diffusion model. Through the combination of these three conditioning paths and the temporal residual framework, our framework excels in reconstructing high-quality videos from event flow, mitigating issues such as artifacts and over-smoothing commonly observed in previous approaches. Extensive experiments conducted on multiple benchmark datasets validate the superior performance of our framework compared to prior event-based reconstruction methods.

cs.CV↗