arXiv subjects

Shuo Ye

Publications and source records attributed to Shuo Ye.

At least 19 recordsLinked to original sources

arXiv2026

Asymmetric Cross-Modal Fine-Grained Visual Categorization: ACF-Net and the BirdPro Benchmark

Audio-visual cross-modal Fine-Grained Visual Categorization (FGVC) aims to identify fine-grained categories by jointly leveraging visual and auditory information. However, FGVC under asymmetric cross-modal scenarios has received limited attention, where paired video and audio are not strictly synchronized and may not even correspond to the same individual or moment. Such weak and ambiguous cross-modal correspondence poses substantial challenges to effective representation learning and modality alignment. To address these issues, we propose ACF-Net, a novel optical flow-guided framework for asymmetric audio-visual fine-grained learning. ACF-Net consists of two key modules: Optical Flow-Guided Motion (OFGM) and Asymmetric CrossModal Adaptive Fusion (ACAF). OFGM captures motion-sensitive visual cues and suppresses irrelevant background interference, thereby enhancing discriminative dynamic representations in videos. ACAF estimates modality reliability under weakly matched audio-video pairs and performs uncertainty-aware adaptive fusion to improve category-level recognition robustness. To support research on asymmetric cross-modal FGVC, we further construct BirdPro, a new bird-oriented audio-visual benchmark, since existing datasets often lack large-scale category-level audio-video associations under non-strict temporal and instance correspondence. BirdPro contains 1,919 audio recordings and 11,965 videos covering 194 bird species. Extensive experiments show that ACF-Net achieves the best results compared with representative baseline methods, outperforming the strongest baselines by 2.97% and 1.92% in the fused and mismatched settings, respectively.

cs.CV↗

arXiv2026

PCA: Persistence-Aware Compression and Aggregation for Fast Video Large Language Models

Despite advances in Video Large Language Models (VLLMs) that have displayed promising outcomes in video understanding, the redundancy in the long-duration frames remains a hindrance to efficient reasoning. This paper introduces a training-free $\mathbf{P}$ersistence-Aware $\mathbf{C}$ompression and $\mathbf{A}$ggregation (PCA) method designed to preserve high-fidelity raw visual information before the encoding stage. PCA can be built on arbitrary VLLMs and consists of two modules: 1) A Dynamic Downsampling (DD) module that adaptively removes redundant frames by analyzing frame-wise similarity. 2) A Persistence-Aware Motion Enhancement (PAME) module that enriches each selected keyframe by aggregating the temporal context of its neighbors, ensuring that essential information is preserved even after aggressive frame reduction. Our approach substantially reduces the computation of long-context modeling, while enhancing the performance of the baseline model. Extensive experiments demonstrate that PCA consistently outperforms existing state-of-the-art approaches in both efficiency and accuracy, achieving a speedup of 1.8$\times$ to 2.5$\times$ compared to the baseline VLLM. The code is open-sourced at https://github.com/Heisenberg10110/PCA.

cs.CV↗

arXiv2026

RSICCLLM: A Multimodal Large Language Model for Remote Sensing Image Change Captioning

Remote Sensing Image Change Captioning (RSICC) aims to describe changes between bi-temporal remote sensing images and holds significant research and application value. However, most existing methods rely on conventional deep learning architectures, and the limited model capacity constrains performance. Although large-model post-training techniques have achieved great success in general domains, their direct transfer to RSICC remains challenging due to data scarcity and the need for fine-grained change understanding. To address this, we propose RSICCLLM, the first post-training framework for large vision-language models in RSICC. Specifically, we design a data generation paradigm, release the instruction dataset RSICI, and establish a task-specific RSICC benchmark. We further introduce Difference-aware Supervised Fine-tuning to explicitly extract change representations and guide the model in perceiving and understanding temporal differences. In addition, we propose Dual-Negative Preference Optimization (DNPO), which employs two complementary negative-sample construction strategies to construct the preference dataset RSICP and further refine model performance. Extensive experiments validate the superior capability of RSICCLLM, which achieves outstanding results with only 7B parameters, surpassing models of substantially larger scales. The code and dataset will be made publicly available at https://github.com/keaill/RSICCLLM.

cs.CV↗

arXiv2026

DeceptionX: From Multimodal Evidence to Explainable Deception Detection

Deception detection is a critical and highly challenging task within affective computing and behavioral analysis. Existing deep learning methods typically treat this task as a straightforward classification problem; however, this black-box approach lacks interpretability and fails to capture the complex logical deduction processes utilized by human experts when identifying lies. While Multimodal Large Language Models (MLLMs) have shown potential, applying them effectively requires a bridge between low-level audiovisual cues and high-level logical reasoning. In this paper, we propose DeceptionX, a novel MLLM framework that shifts the paradigm of deception detection from black-box classification to an interpretable Observe-Think-Summarize reasoning process. To address the scarcity of high-quality reasoning data, we first constructed DeceptChain, a high-quality dataset developed through a human-in-the-loop process. This dataset synthesizes fine-grained visual and auditory evidence (such as micro-expressions and vocal tremors) into structured chain-of-thought reasoning data. Furthermore, we propose a three-stage training pipeline and a Discrepancy-Aware Redundancy Elimination~(DARE) strategy for DeceptionX to further enhance the model's generalization capabilities. Extensive experiments demonstrate that DeceptionX not only outperforms existing MLLM baselines and state-of-the-art methods on standard real-world benchmarks but also provides transparent, expert-level reasoning paths, bridging the critical gap between accuracy and interpretability in multimodal deception detection.

cs.CV↗

arXiv2026

Seg-Agent: Test-Time Multimodal Reasoning for Training-Free Language-Guided Segmentation

Language-guided segmentation transcends the scope limitations of traditional semantic segmentation, enabling models to segment arbitrary target regions based on natural language instructions. Existing approaches typically adopt a two-stage framework: employing Multimodal Large Language Models (MLLMs) to interpret instructions and generate visual prompts, followed by foundational segmentation models (e.g., SAM) to produce masks. However, due to the limited spatial grounding capabilities of off-the-shelf MLLMs, these methods often rely on extensive training on large-scale datasets to achieve satisfactory accuracy. While recent advances have introduced reasoning mechanisms to improve performance, they predominantly operate within the textual domain, performing chain-of-thought reasoning solely based on abstract text representations without direct visual feedback. In this paper, we propose Seg-Agent, a completely training-free framework that pioneers Explicit Multimodal Chain-of-Reasoning. Unlike prior text-only reasoning, our approach constructs an interactive visual reasoning loop comprising three stages: generation, selection, and refinement. Specifically, we leverage Set-of-Mark (SoM) visual prompting to render candidate regions directly onto the image, allowing the MLLM to ``see'' and iteratively reason about spatial relationships in the visual domain rather than just the textual one. This explicit multimodal interaction enables Seg-Agent to achieve performance comparable to state-of-the-art training-based methods without any parameter updates. Furthermore, to comprehensively evaluate generalization across diverse scenarios, we introduce Various-LangSeg, a novel benchmark covering explicit semantic, generic object, and reasoning-guided segmentation tasks. Extensive experiments demonstrate the effectiveness and robustness of our method.

cs.CV↗

arXiv2026

Text-Guided Multimodal Unified Industrial Anomaly Detection

Industrial anomaly detection based on RGB-3D multimodal data has emerged as a mainstream paradigm for intelligent quality inspection. However, existing unsupervised methods suffer from two critical limitations: ambiguous cross-modal alignment caused by the lack of high-level semantic guidance and insufficient geometric modeling for RGB-to-3D feature mapping. To address these issues, we propose a unified multimodal industrial anomaly detection framework guided by text semantics. The framework consists of two core modules: a Geometry-Aware Cross-Modal Mapper to preserve geometric structure during modality conversion, and an Object-Conditioned Textual Feature Adaptor to align multimodal features with semantic priors. Furthermore, we establish a unified learning paradigm for multimodal industrial anomaly detection, which breaks the one-model-one-class constraint and enables accurate anomaly detection across diverse classes using a single model. Extensive experiments on the MVTec 3D-AD and Eyecandies datasets demonstrate that our method achieves state-of-the-art performance in classification and localization under unsupervised settings.

cs.CV↗

arXiv2026

PISP: Projected-Space Inference of Stellar Parameters

To improve the accuracy and efficiency of high-dimensional stellar parameter inference in large spectroscopic datasets, we propose a projection-assisted parameter-inference framework -- Projected-Space Inference of Stellar Parameters (PISP). PISP constructs an orthonormal basis and optimizes in the projected space, reducing the impact of parameter correlations on inference. The basis is constructed using either principal component analysis (PCA) or the active-subspace (AS) method and is combined with two inference strategies -- Non-L1, which optimizes the projection coefficients for a user-specified projected dimensionality, and L1, which introduces L1 regularization in the full projected space to adaptively select projection directions -- yielding four strategies: PCA-Non-L1, AS-Non-L1, PCA-L1, and AS-L1. For different computational scenarios, we implement two versions: PISP-CurveFit for fast single-spectrum inference and PISP-Adam for large-scale GPU-parallel inference. Using a fully connected neural network and a residual network as spectral emulators, we evaluate PISP on Kurucz synthetic spectra and on $722{,}896$ APOGEE DR$17$ observed spectra. Compared to the baseline strategy, PISP improves inference accuracy for multiple parameters across all emulator-optimizer combinations. In synthetic data, PCA-L1 performs best, reducing the standard deviation of differences ($\sigma(\Delta)$) by at least $0.01$ dex for $12$ of $20$ elemental abundances, with [N/H], [O/H], [Na/H], [Co/H], [P/H], [V/H], [Cu/H] showing $0.05$--$0.72$ dex reductions. In observed data, PCA-Non-L1 reduces $\sigma(\Delta)$ by $>30$ K for effective temperature and by at least $0.01$ dex for $9$ of $17$ elemental abundances, with [O/H], [Na/H], [V/H] showing $0.05$--$0.20$ dex reductions, while achieving a $\sim$$4\times$ efficiency gain, slightly outperforming PCA-L1.

astro-ph.SR↗

arXiv2026

Retrieving to Recover: Towards Incomplete Audio-Visual Question Answering via Semantic-consistent Purification

Recent Audio-Visual Question Answering (AVQA) methods have advanced significantly. However, most AVQA methods lack effective mechanisms for handling missing modalities, suffering from severe performance degradation in real-world scenarios with data interruptions. Furthermore, prevailing methods for handling missing modalities predominantly rely on generative imputation to synthesize missing features. While partially effective, these methods tend to capture inter-modal commonalities but struggle to acquire unique, modality-specific knowledge within the missing data, leading to hallucinations and compromised reasoning accuracy. To tackle these challenges, we propose R$^{2}$ScP, a novel framework that shifts the paradigm of missing modality handling from traditional generative imputation to retrieval-based recovery. Specifically, we leverage cross-modal retrieval via unified semantic embeddings to acquire missing domain-specific knowledge. To maximize semantic restoration, we introduce a context-aware adaptive purification mechanism that eliminates latent semantic noise within the retrieved data. Additionally, we employ a two-stage training strategy to explicitly model the semantic relationships between knowledge from different sources. Extensive experiments demonstrate that R$^{2}$ScP significantly improves AVQA and enhances robustness in modal-incomplete scenarios.

cs.CV↗

arXiv2026

YUV20K: A Complexity-Driven Benchmark and Trajectory-Aware Alignment Model for Video Camouflaged Object Detection

Video Camouflaged Object Detection (VCOD) is currently constrained by the scarcity of challenging benchmarks and the limited robustness of models against erratic motion dynamics. Existing methods often struggle with Motion-Induced Appearance Instability and Temporal Feature Misalignment caused by complex motion scenarios. To address the data bottleneck, we present YUV20K, a pixel-level annoated complexity-driven VCOD benchmark. Comprising 24,295 annotated frames across 91 scenes and 47 kinds of species, it specifically targets challenging scenarios like large-displacement motion, camera motion and other 4 types scenarios. On the methodological front, we propose a novel framework featuring two key modules: Motion Feature Stabilization (MFS) and Trajectory-Aware Alignment (TAA). The MFS module utilizes frame-agnostic Semantic Basis Primitives to stablize features, while the TAA module leverages trajectory-guided deformable sampling to ensure precise temporal alignment. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art competitors on existing datasets and establishes a new baseline on the challenging YUV20K. Notably, our framework exhibits superior cross-domain generalization and robustness when confronting complex spatiotemporal scenarios. Our code and dataset will be available at https://github.com/K1NSA/YUV20K

cs.CV↗

arXiv2026

SVC 2026: the Second Multimodal Deception Detection Challenge and the First Domain Generalized Remote Physiological Measurement Challenge

Subtle visual signals, although difficult to perceive with the naked eye, contain important information that can reveal hidden patterns in visual data. These signals play a key role in many applications, including biometric security, multimedia forensics, medical diagnosis, industrial inspection, and affective computing. With the rapid development of computer vision and representation learning techniques, detecting and interpreting such subtle signals has become an emerging research direction. However, existing studies often focus on specific tasks or modalities, and models still face challenges in robustness, representation ability, and generalization when handling subtle and weak signals in real-world environments. To promote research in this area, we organize the Subtle visual Challenge, which aims to learn robust representations for subtle visual signals. The challenge includes two tasks: cross-domain multimodal deception detection and remote photoplethysmography (rPPG) estimation. We hope that this challenge will encourage the development of more robust and generalizable models for subtle visual understanding, and further advance research in computer vision and multimodal learning. A total of 22 teams submitted their final results to this workshop competition, and the corresponding baseline models have been released on the \href{https://sites.google.com/view/svc-cvpr26}{MMDD2026 platform}\footnote{https://sites.google.com/view/svc-cvpr26}

cs.CV↗

arXiv2026

High-Resolution Underwater Camouflaged Object Detection: GBU-UCOD Dataset and Topology-Aware and Frequency-Decoupled Networks

Underwater Camouflaged Object Detection (UCOD) is a challenging task due to the extreme visual similarity between targets and backgrounds across varying marine depths. Existing methods often struggle with topological fragmentation of slender creatures in the deep sea and the subtle feature extraction of transparent organisms. In this paper, we propose DeepTopo-Net, a novel framework that integrates topology-aware modeling with frequency-decoupled perception. To address physical degradation, we design the Water-Conditioned Adaptive Perceptor (WCAP), which employs Riemannian metric tensors to dynamically deform convolutional sampling fields. Furthermore, the Abyssal-Topology Refinement Module (ATRM) is developed to maintain the structural connectivity of spindly targets through skeletal priors. Specifically, we first introduce GBU-UCOD, the first high-resolution (2K) benchmark tailored for marine vertical zonation, filling the data gap for hadal and abyssal zones. Extensive experiments on MAS3K, RMAS, and our proposed GBU-UCOD datasets demonstrate that DeepTopo-Net achieves state-of-the-art performance, particularly in preserving the morphological integrity of complex underwater patterns. The datasets and codes will be released at https://github.com/Wuwenji18/GBU-UCOD.

cs.CV↗

arXiv2026

Spec-o3: A Tool-Augmented Vision-Language Agent for Rare Celestial Object Candidate Vetting via Automated Spectral Inspection

Due to the limited generalization and interpretability of deep learning classifiers, The final vetting of rare celestial object candidates still relies on expert visual inspection--a manually intensive process. In this process, astronomers leverage specialized tools to analyze spectra and construct reliable catalogs. However, this practice has become the primary bottleneck, as it is fundamentally incapable of scaling with the data deluge from modern spectroscopic surveys. To bridge this gap, we propose Spec-o3, a tool-augmented vision-language agent that performs astronomer-aligned spectral inspection via interleaved multimodal chain-of-thought reasoning. Spec-o3 is trained with a two-stage post-training recipe: cold-start supervised fine-tuning on expert inspection trajectories followed by outcome-based reinforcement learning on rare-type verification tasks. Evaluated on five rare-object identification tasks from LAMOST, Spec-o3 establishes a new State-of-the-Art, boosting the macro-F1 score from 28.3 to 76.5 with a 7B parameter base model and outperforming both proprietary VLMs and specialized deep models. Crucially, the agent demonstrates strong generalization to unseen inspection tasks across survey shifts (from LAMOST to SDSS/DESI). Expert evaluations confirm that its reasoning traces are coherent and physically consistent, supporting transparent and trustworthy decision-making. Code, data, and models are available at https://github.com/Maxwell-Jia/spec-o3.

cs.CL↗

arXiv2025

Scalable Stellar Parameter Inference Using Python-based LASP: From CPU Optimization to GPU Acceleration

To enhance the efficiency, scalability, and cross-survey applicability of stellar parameter inference in large spectroscopic datasets, we present a modular, parallelized Python framework with automated error estimation, built on the LAMOST Atmospheric Parameter Pipeline (LASP) originally implemented in IDL. Rather than a direct code translation, this framework refactors LASP with two complementary modules: LASP-CurveFit, a new implementation of the LASP fitting procedure that runs on a CPU, preserving legacy logic while improving data I/O and multithreaded execution efficiency; and LASP-Adam-GPU, a GPU-accelerated method that introduces grouped optimization by constructing a joint residual function over multiple observed and model spectra, enabling high-throughput parameter inference across tens of millions of spectra. Applied to 10 million LAMOST spectra, the framework reduces runtime from 84 to 48 hr on the same CPU platform and to 7 hr on an NVIDIA A100 GPU, while producing results consistent with those from the original pipeline. The inferred errors agree well with the parameter variations from repeat observations of the same target (excluding radial velocities), while the official empirical errors used in LASP are more conservative. When applied to DESI DR1, our effective temperatures and surface gravities agree better with APOGEE than those from the DESI pipeline, particularly for cool giants, while the latter performs slightly better in radial velocity and metallicity. These results suggest that the framework delivers reliable accuracy, efficiency, and transferability, offering a practical approach to parameter inference in large spectroscopic surveys. The code and DESI-based catalog are available via \dataset[DOI: 10.12149/101679]{https://doi.org/10.12149/101679} and \dataset[DOI: 10.12149/101675]{https://doi.org/10.12149/101675}, respectively.

astro-ph.GA↗

arXiv2025

AV-Master: Dual-Path Comprehensive Perception Makes Better Audio-Visual Question Answering

Audio-Visual Question Answering (AVQA) requires models to effectively utilize both visual and auditory modalities to answer complex and diverse questions about audio-visual scenes. However, existing methods lack sufficient flexibility and dynamic adaptability in temporal sampling and modality preference awareness, making it difficult to focus on key information based on the question. This limits their reasoning capability in complex scenarios. To address these challenges, we propose a novel framework named AV-Master. It enhances the model's ability to extract key information from complex audio-visual scenes with substantial redundant content by dynamically modeling both temporal and modality dimensions. In the temporal dimension, we introduce a dynamic adaptive focus sampling mechanism that progressively focuses on audio-visual segments most relevant to the question, effectively mitigating redundancy and segment fragmentation in traditional sampling methods. In the modality dimension, we propose a preference-aware strategy that models each modality's contribution independently, enabling selective activation of critical features. Furthermore, we introduce a dual-path contrastive loss to reinforce consistency and complementarity across temporal and modality dimensions, guiding the model to learn question-specific cross-modal collaborative representations. Experiments on four large-scale benchmarks show that AV-Master significantly outperforms existing methods, especially in complex reasoning tasks.

cs.CV↗

arXiv2025

HRR: Hierarchical Retrospection Refinement for Generated Image Detection

Generative artificial intelligence holds significant potential for abuse, and generative image detection has become a key focus of research. However, existing methods primarily focused on detecting a specific generative model and emphasizing the localization of synthetic regions, while neglecting the interference caused by image size and style on model learning. Our goal is to reach a fundamental conclusion: Is the image real or generated? To this end, we propose a diffusion model-based generative image detection framework termed Hierarchical Retrospection Refinement~(HRR). It designs a multi-scale style retrospection module that encourages the model to generate detailed and realistic multi-scale representations, while alleviating the learning biases introduced by dataset styles and generative models. Additionally, based on the principle of correntropy sparse additive machine, a feature refinement module is designed to reduce the impact of redundant features on learning and capture the intrinsic structure and patterns of the data, thereby improving the model's generalization ability. Extensive experiments demonstrate the HRR framework consistently delivers significant performance improvements, outperforming state-of-the-art methods in generated image detection task.

cs.CV↗

arXiv2025

Toward Realistic Camouflaged Object Detection: Benchmarks and Method

Camouflaged object detection (COD) primarily relies on semantic or instance segmentation methods. While these methods have made significant advancements in identifying the contours of camouflaged objects, they may be inefficient or cost-effective for tasks that only require the specific location of the object. Object detection algorithms offer an optimized solution for Realistic Camouflaged Object Detection (RCOD) in such cases. However, detecting camouflaged objects remains a formidable challenge due to the high degree of similarity between the features of the objects and their backgrounds. Unlike segmentation methods that perform pixel-wise comparisons to differentiate between foreground and background, object detectors omit this analysis, further aggravating the challenge. To solve this problem, we propose a camouflage-aware feature refinement (CAFR) strategy. Since camouflaged objects are not rare categories, CAFR fully utilizes a clear perception of the current object within the prior knowledge of large models to assist detectors in deeply understanding the distinctions between background and foreground. Specifically, in CAFR, we introduce the Adaptive Gradient Propagation (AGP) module that fine-tunes all feature extractor layers in large detection models to fully refine class-specific features from camouflaged contexts. We then design the Sparse Feature Refinement (SFR) module that optimizes the transformer-based feature extractor to focus primarily on capturing class-specific features in camouflaged scenarios. To facilitate the assessment of RCOD tasks, we manually annotate the labels required for detection on three existing segmentation COD datasets, creating a new benchmark for RCOD tasks. Code and datasets are available at: https://github.com/zhimengXin/RCOD.

cs.CV↗

arXiv2024

Deep learning interpretability analysis for carbon star identification in Gaia DR3

Context. A large fraction of Asymptotic Giant Branch (AGB) stars develop carbon-rich atmospheres during their evolution. Based on their color and luminosity, these carbon stars can be easily distinguished from many other kinds of stars. However, numerous G, K, and M giants also occupy the same region as carbon stars on the HR diagram. Despite this, their spectra exhibit differences, especially in the prominent CN molecular bands. Target. We aim to distinguish carbon stars from other kinds of stars using $Gaia$'s XP spectra, while providing attributional interpretations of key features necessary for identification, and even discovering additional new spectral key features. Method. We propose a classification model named `GaiaNet', an improved one-dimensional convolutional neural network specifically designed for handling $Gaia$'s XP spectra. We utilized the SHAP interpretability model to determine SHAP values for each feature in a spectrum, enabling us to explain the output of the `GaiaNet' model and provide further meaningful analysis. Compared to four traditional machine-learning methods, the `GaiaNet' model exhibits an average classification accuracy improvement of approximately 0.3% on the validation set, with the highest accuracy reaching 100%. Utilizing the SHAP model, we present a clear spectroscopic heatmap highlighting molecular band absorption features primarily distributed around CN773.3 and CN895.0, and summarize five key feature regions for carbon star identification. Upon applying the trained classification model to the CSTAR sample with Gaia `xp_sampled_mean' spectra, we obtained 451 new candidate carbon stars as a by-product.

astro-ph.IM↗

arXiv2023

Detail Reinforcement Diffusion Model: Augmentation Fine-Grained Visual Categorization in Few-Shot Conditions

The challenge in fine-grained visual categorization lies in how to explore the subtle differences between different subclasses and achieve accurate discrimination. Previous research has relied on large-scale annotated data and pre-trained deep models to achieve the objective. However, when only a limited amount of samples is available, similar methods may become less effective. Diffusion models have been widely adopted in data augmentation due to their outstanding diversity in data generation. However, the high level of detail required for fine-grained images makes it challenging for existing methods to be directly employed. To address this issue, we propose a novel approach termed the detail reinforcement diffusion model~(DRDM), which leverages the rich knowledge of large models for fine-grained data augmentation and comprises two key components including discriminative semantic recombination (DSR) and spatial knowledge reference~(SKR). Specifically, DSR is designed to extract implicit similarity relationships from the labels and reconstruct the semantic mapping between labels and instances, which enables better discrimination of subtle differences between different subclasses. Furthermore, we introduce the SKR module, which incorporates the distributions of different datasets as references in the feature space. This allows the SKR to aggregate the high-dimensional distribution of subclass features in few-shot FGVC tasks, thus expanding the decision boundary. Through these two critical components, we effectively utilize the knowledge from large models to address the issue of data scarcity, resulting in improved performance for fine-grained visual recognition tasks. Extensive experiments demonstrate the consistent performance gain offered by our DRDM.

cs.CV↗