arXiv subjects

Peng Wang

Publications and source records attributed to Peng Wang.

At least 433 records · Page 24Linked to original sources

arXiv2024

VSFormer: Mining Correlations in Flexible View Set for Multi-view 3D Shape Understanding

View-based methods have demonstrated promising performance in 3D shape understanding. However, they tend to make strong assumptions about the relations between views or learn the multi-view correlations indirectly, which limits the flexibility of exploring inter-view correlations and the effectiveness of target tasks. To overcome the above problems, this paper investigates flexible organization and explicit correlation learning for multiple views. In particular, we propose to incorporate different views of a 3D shape into a permutation-invariant set, referred to as \emph{View Set}, which removes rigid relation assumptions and facilitates adequate information exchange and fusion among views. Based on that, we devise a nimble Transformer model, named \emph{VSFormer}, to explicitly capture pairwise and higher-order correlations of all elements in the set. Meanwhile, we theoretically reveal a natural correspondence between the Cartesian product of a view set and the correlation matrix in the attention mechanism, which supports our model design. Comprehensive experiments suggest that VSFormer has better flexibility, efficient inference efficiency and superior performance. Notably, VSFormer reaches state-of-the-art results on various 3d recognition datasets, including ModelNet40, ScanObjectNN and RGBD. It also establishes new records on the SHREC'17 retrieval benchmark. The code and datasets are available at \url{https://github.com/auniquesun/VSFormer}.

cs.CV↗

arXiv2024

BeNeRF: Neural Radiance Fields from a Single Blurry Image and Event Stream

Neural implicit representation of visual scenes has attracted a lot of attention in recent research of computer vision and graphics. Most prior methods focus on how to reconstruct 3D scene representation from a set of images. In this work, we demonstrate the possibility to recover the neural radiance fields (NeRF) from a single blurry image and its corresponding event stream. We model the camera motion with a cubic B-Spline in SE(3) space. Both the blurry image and the brightness change within a time interval, can then be synthesized from the 3D scene representation given the 6-DoF poses interpolated from the cubic B-Spline. Our method can jointly learn both the implicit neural scene representation and recover the camera motion by minimizing the differences between the synthesized data and the real measurements without pre-computed camera poses from COLMAP. We evaluate the proposed method with both synthetic and real datasets. The experimental results demonstrate that we are able to render view-consistent latent sharp images from the learned NeRF and bring a blurry image alive in high quality. Code and data are available at https://github.com/wu-cvgl/BeNeRF.

cs.CV↗

arXiv2024

Qwen2 Technical Report

This report introduces the Qwen2 series, the latest addition to our large language models and large multimodal models. We release a comprehensive suite of foundational and instruction-tuned language models, encompassing a parameter range from 0.5 to 72 billion, featuring dense models and a Mixture-of-Experts model. Qwen2 surpasses most prior open-weight models, including its predecessor Qwen1.5, and exhibits competitive performance relative to proprietary models across diverse benchmarks on language understanding, generation, multilingual proficiency, coding, mathematics, and reasoning. The flagship model, Qwen2-72B, showcases remarkable performance: 84.2 on MMLU, 37.9 on GPQA, 64.6 on HumanEval, 89.5 on GSM8K, and 82.4 on BBH as a base language model. The instruction-tuned variant, Qwen2-72B-Instruct, attains 9.1 on MT-Bench, 48.1 on Arena-Hard, and 35.7 on LiveCodeBench. Moreover, Qwen2 demonstrates robust multilingual capabilities, proficient in approximately 30 languages, spanning English, Chinese, Spanish, French, German, Arabic, Russian, Korean, Japanese, Thai, Vietnamese, and more, underscoring its versatility and global reach. To foster community innovation and accessibility, we have made the Qwen2 model weights openly available on Hugging Face and ModelScope, and the supplementary materials including example code on GitHub. These platforms also include resources for quantization, fine-tuning, and deployment, facilitating a wide range of applications and research endeavors.

cs.CL↗

arXiv2024

MCDGLN: Masked Connection-based Dynamic Graph Learning Network for Autism Spectrum Disorder

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder characterized by complex physiological processes. Previous research has predominantly focused on static cerebral interactions, often neglecting the brain's dynamic nature and the challenges posed by network noise. To address these gaps, we introduce the Masked Connection-based Dynamic Graph Learning Network (MCDGLN). Our approach first segments BOLD signals using sliding temporal windows to capture dynamic brain characteristics. We then employ a specialized weighted edge aggregation (WEA) module, which uses the cross convolution with channel-wise element-wise convolutional kernel, to integrate dynamic functional connectivity and to isolating task-relevant connections. This is followed by topological feature extraction via a hierarchical graph convolutional network (HGCN), with key attributes highlighted by a self-attention module. Crucially, we refine static functional connections using a customized task-specific mask, reducing noise and pruning irrelevant links. The attention-based connection encoder (ACE) then enhances critical connections and compresses static features. The combined features are subsequently used for classification. Applied to the Autism Brain Imaging Data Exchange I (ABIDE I) dataset, our framework achieves a 73.3\% classification accuracy between ASD and Typical Control (TC) groups among 1,035 subjects. The pivotal roles of WEA and ACE in refining connectivity and enhancing classification accuracy underscore their importance in capturing ASD-specific features, offering new insights into the disorder.

cs.LG↗

arXiv2024

Observational Signatures of Traversable Wormholes

In this paper, we study the observational signatures of traversable Simpson-Visser wormholes illuminated by luminous celestial spheres and orbiting hot spots. We demonstrate that when light sources and observers are on the same side of the wormholes, the images of the wormholes mimic those of black holes. However, when the light sources are positioned on the opposite side from observers, photons traversing the wormhole throat generate distinct observational signatures. Specifically, unlike black hole images, the wormhole images are confined within the critical curve, resulting in smaller centroid variations. Furthermore, the light curve of hot spots can exhibit additional peaks.

gr-qc↗

arXiv2024

Polarized Image of a Synchrotron-emitting Ring in Einstein-Maxwell-scalar Theory

This study investigates polarized images of an equatorial synchrotron-emitting ring surrounding hairy black holes within the Einstein-Maxwell-scalar theory. Our analysis demonstrates qualitative similarities between the polarization patterns of hairy black holes and Schwarzschild black holes. However, due to the non-minimal coupling between the scalar and electromagnetic fields, an increase in black hole charge and coupling constant can substantially amplify polarization intensity and induce deviations in the electric vector position angle. These effects may offer observational signatures to distinguish hairy black holes from Schwarzschild black holes.

gr-qc↗

arXiv2024

Deep Learning for Video Anomaly Detection: A Review

Video anomaly detection (VAD) aims to discover behaviors or events deviating from the normality in videos. As a long-standing task in the field of computer vision, VAD has witnessed much good progress. In the era of deep learning, with the explosion of architectures of continuously growing capability and capacity, a great variety of deep learning based methods are constantly emerging for the VAD task, greatly improving the generalization ability of detection algorithms and broadening the application scenarios. Therefore, such a multitude of methods and a large body of literature make a comprehensive survey a pressing necessity. In this paper, we present an extensive and comprehensive research review, covering the spectrum of five different categories, namely, semi-supervised, weakly supervised, fully supervised, unsupervised and open-set supervised VAD, and we also delve into the latest VAD works based on pre-trained large models, remedying the limitations of past reviews in terms of only focusing on semi-supervised VAD and small model based methods. For the VAD task with different levels of supervision, we construct a well-organized taxonomy, profoundly discuss the characteristics of different types of methods, and show their performance comparisons. In addition, this review involves the public datasets, open-source codes, and evaluation metrics covering all the aforementioned VAD tasks. Finally, we provide several important research directions for the VAD community.

cs.CV↗

arXiv2024

OneEdit: A Neural-Symbolic Collaboratively Knowledge Editing System

Knowledge representation has been a central aim of AI since its inception. Symbolic Knowledge Graphs (KGs) and neural Large Language Models (LLMs) can both represent knowledge. KGs provide highly accurate and explicit knowledge representation, but face scalability issue; while LLMs offer expansive coverage of knowledge, but incur significant training costs and struggle with precise and reliable knowledge manipulation. To this end, we introduce OneEdit, a neural-symbolic prototype system for collaborative knowledge editing using natural language, which facilitates easy-to-use knowledge management with KG and LLM. OneEdit consists of three modules: 1) The Interpreter serves for user interaction with natural language; 2) The Controller manages editing requests from various users, leveraging the KG with rollbacks to handle knowledge conflicts and prevent toxic knowledge attacks; 3) The Editor utilizes the knowledge from the Controller to edit KG and LLM. We conduct experiments on two new datasets with KGs which demonstrate that OneEdit can achieve superior performance.

cs.AI↗

arXiv2024

Goal-Reaching Policy Learning from Non-Expert Observations via Effective Subgoal Guidance

In this work, we address the challenging problem of long-horizon goal-reaching policy learning from non-expert, action-free observation data. Unlike fully labeled expert data, our data is more accessible and avoids the costly process of action labeling. Additionally, compared to online learning, which often involves aimless exploration, our data provides useful guidance for more efficient exploration. To achieve our goal, we propose a novel subgoal guidance learning strategy. The motivation behind this strategy is that long-horizon goals offer limited guidance for efficient exploration and accurate state transition. We develop a diffusion strategy-based high-level policy to generate reasonable subgoals as waypoints, preferring states that more easily lead to the final goal. Additionally, we learn state-goal value functions to encourage efficient subgoal reaching. These two components naturally integrate into the off-policy actor-critic framework, enabling efficient goal attainment through informative exploration. We evaluate our method on complex robotic navigation and manipulation tasks, demonstrating a significant performance advantage over existing methods. Our ablation study further shows that our method is robust to observation data with various corruptions.

cs.LG↗

arXiv2024

Enhancing Adaptive Deep Networks for Image Classification via Uncertainty-aware Decision Fusion

Handling varying computational resources is a critical issue in modern AI applications. Adaptive deep networks, featuring the dynamic employment of multiple classifier heads among different layers, have been proposed to address classification tasks under varying computing resources. Existing approaches typically utilize the last classifier supported by the available resources for inference, as they believe that the last classifier always performs better across all classes. However, our findings indicate that earlier classifier heads can outperform the last head for certain classes. Based on this observation, we introduce the Collaborative Decision Making (CDM) module, which fuses the multiple classifier heads to enhance the inference performance of adaptive deep networks. CDM incorporates an uncertainty-aware fusion method based on evidential deep learning (EDL), that utilizes the reliability (uncertainty values) from the first c-1 classifiers to improve the c-th classifier' accuracy. We also design a balance term that reduces fusion saturation and unfairness issues caused by EDL constraints to improve the fusion quality of CDM. Finally, a regularized training strategy that uses the last classifier to guide the learning process of early classifiers is proposed to further enhance the CDM module's effect, called the Guided Collaborative Decision Making (GCDM) framework. The experimental evaluation demonstrates the effectiveness of our approaches. Results on ImageNet datasets show CDM and GCDM obtain 0.4% to 2.8% accuracy improvement (under varying computing resources) on popular adaptive networks. The code is available at the link https://github.com/Meteor-Stars/GCDM_AdaptiveNet.

cs.CV↗

arXiv2024

Sequential-Scanning Dual-Energy CT Imaging Using High Temporal Resolution Image Reconstruction and Error-Compensated Material Basis Image Generation

Dual-energy computed tomography (DECT) has been widely used to obtain quantitative elemental composition of imaged subjects for personalized and precise medical diagnosis. Compared with DECT leveraging advanced X-ray source and/or detector technologies, the use of the sequential-scanning data acquisition scheme to implement DECT may make a broader impact on clinical practice because this scheme requires no specialized hardware designs and can be directly implemented into conventional CT systems. However, since the concentration of iodinated contrast agent in the imaged subject varies over time, sequentially scanned data sets acquired at two tube potentials are temporally inconsistent. As existing material basis image reconstruction approaches assume that the data sets acquired at two tube potentials are temporally consistent, the violation of this assumption results in inaccurate quantification of material concentration. In this work, we developed sequential-scanning DECT imaging using high temporal resolution image reconstruction and error-compensated material basis image generation, ACCELERATION in short, to address the technical challenge induced by temporal inconsistency of sequentially scanned data sets and improve quantification accuracy of material concentration in sequential-scanning DECT. ACCELERATION has been validated and evaluated using numerical simulation data sets generated from clinical human subject exams and experimental human subject studies. Results demonstrated the improvement of quantification accuracy and image quality using ACCELERATION.

physics.med-ph↗

arXiv2024

Platypus: A Generalized Specialist Model for Reading Text in Various Forms

Reading text from images (either natural scenes or documents) has been a long-standing research topic for decades, due to the high technical challenge and wide application range. Previously, individual specialist models are developed to tackle the sub-tasks of text reading (e.g., scene text recognition, handwritten text recognition and mathematical expression recognition). However, such specialist models usually cannot effectively generalize across different sub-tasks. Recently, generalist models (such as GPT-4V), trained on tremendous data in a unified way, have shown enormous potential in reading text in various scenarios, but with the drawbacks of limited accuracy and low efficiency. In this work, we propose Platypus, a generalized specialist model for text reading. Specifically, Platypus combines the best of both worlds: being able to recognize text of various forms with a single unified architecture, while achieving excellent accuracy and high efficiency. To better exploit the advantage of Platypus, we also construct a text reading dataset (called Worms), the images of which are curated from previous datasets and partially re-labeled. Experiments on standard benchmarks demonstrate the effectiveness and superiority of the proposed Platypus model. Model and data will be made publicly available at https://github.com/AlibabaResearch/AdvancedLiterateMachinery/tree/main/OCR/Platypus.

cs.CV↗

arXiv2024

$\boldsymbol{Steiner}$-Hardness: A Query Hardness Measure for Graph-Based ANN Indexes

Graph-based indexes have been widely employed to accelerate approximate similarity search of high-dimensional vectors. However, the performance of graph indexes to answer different queries varies vastly, leading to an unstable quality of service for downstream applications. This necessitates an effective measure to test query hardness on graph indexes. Nonetheless, popular distance-based hardness measures like LID lose their effects due to the ignorance of the graph structure. In this paper, we propose $Steiner$-hardness, a novel connection-based graph-native query hardness measure. Specifically, we first propose a theoretical framework to analyze the minimum query effort on graph indexes and then define $Steiner$-hardness as the minimum effort on a representative graph. Moreover, we prove that our $Steiner$-hardness is highly relevant to the classical Directed $Steiner$ Tree (DST) problems. In this case, we design a novel algorithm to reduce our problem to DST problems and then leverage their solvers to help calculate $Steiner$-hardness efficiently. Compared with LID and other similar measures, $Steiner$-hardness shows a significantly better correlation with the actual query effort on various datasets. Additionally, an unbiased evaluation designed based on $Steiner$-hardness reveals new ranking results, indicating a meaningful direction for enhancing the robustness of graph indexes. This paper is accepted by PVLDB 2025.

cs.DB↗

arXiv2024

A duality theorem for harmonic maps into inner symmetric spaces

In this note, we show that for any harmonic map into a non-compact symmetric space one can find naturally a "dual" harmonic map into a compact symmetric space which can be constructed from the same basic data (called "potentials" in the loop group formalism). Locally also the inverse/converse duality theorem holds.

math.DG↗

arXiv2024

Harmonic maps of finite uniton number into inner symmetric spaces via based normalized extended frames

In this paper, we develop a loop group description of harmonic maps $\mathcal{F}: M \rightarrow G/K$ of finite uniton number, from a Riemann surface $M,$ compact or non-compact, into inner symmetric spaces of compact or non-compact type. As a main result we show that the theory of [Burstall-Guest, Math Ann, 97], largely based on Bruhat cells, can be transformed into the DPW theory which is mainly based on Birkhoff cells. Moreover, it turns out that the potentials constructed in [Burstall-Guest, Math Ann, 97], mainly see section 5, can be used to carry out the DPW procedure which uses essentially the fixed initial condition $e$ at a fixed base point $z_0$. This extends work of Uhlenbeck, Segal, and Burstall-Guest to non-compact inner symmetric spaces as target spaces (as a consequence of a "Duality Theorem"). It also permits to say that there is a 1-1-relation between finite uniton number harmonic maps and normalized potentials of a very specific and very controllable type. In particular, we prove that every harmonic map of finite uniton type from any (compact or non-compact) Riemann surface into any {compact or non-compact} inner symmetric space has a normalized potential taking values in some nilpotent Lie subalgebra, as well as a normalized frame with initial condition identity. This provides a straightforward way to construct all such harmonic maps. We also illustrate the above results exclusively by Willmore surfaces, since this problem is motivated by the study of Willmore two--spheres in spheres.

math.DG↗

arXiv2024

Algebraic Harmonic Maps, Totally Symmetric Harmonic Maps and a Conjecture

In this paper, we discuss the associated family of harmonic maps $\mathcal{F}: M \rightarrow G/K$ from a Riemann surface $M$ into inner symmetric spaces of compact or non-compact type which are either algebraic or totally symmetric. These notions are the two components of the definition of a harmonic map of finite uniton number, as stated by [2]. We finish this paper by comparing these to notions and by stating a conjecture.

math.DG↗

arXiv2024

Stationary Scalar Clouds around Kerr-Newman Black Holes

This study investigates scalar clouds around Kerr-Newman black holes within the Einstein-Maxwell-scalar model. Tachyonic instabilities are identified as the driving mechanism for scalar cloud formation. Employing the spectral method, we numerically compute wave functions and parameter space existence domains for both fundamental and excited scalar cloud modes. Our analysis demonstrates that black hole spin imposes an upper limit on the existence of scalar clouds, with excited modes requiring stronger tachyonic instabilities for their formation. These findings lay the groundwork for exploring the nonlinear dynamics and astrophysical implications of scalar clouds.

gr-qc↗

arXiv2024

Weakly Supervised Video Anomaly Detection and Localization with Spatio-Temporal Prompts

Current weakly supervised video anomaly detection (WSVAD) task aims to achieve frame-level anomalous event detection with only coarse video-level annotations available. Existing works typically involve extracting global features from full-resolution video frames and training frame-level classifiers to detect anomalies in the temporal dimension. However, most anomalous events tend to occur in localized spatial regions rather than the entire video frames, which implies existing frame-level feature based works may be misled by the dominant background information and lack the interpretation of the detected anomalies. To address this dilemma, this paper introduces a novel method called STPrompt that learns spatio-temporal prompt embeddings for weakly supervised video anomaly detection and localization (WSVADL) based on pre-trained vision-language models (VLMs). Our proposed method employs a two-stream network structure, with one stream focusing on the temporal dimension and the other primarily on the spatial dimension. By leveraging the learned knowledge from pre-trained VLMs and incorporating natural motion priors from raw videos, our model learns prompt embeddings that are aligned with spatio-temporal regions of videos (e.g., patches of individual frames) for identify specific local regions of anomalies, enabling accurate video anomaly detection while mitigating the influence of background information. Without relying on detailed spatio-temporal annotations or auxiliary object detection/tracking, our method achieves state-of-the-art performance on three public benchmarks for the WSVADL task.

cs.CV↗