| Total: 139
The rapid progress of identity-feature-based face-swapping technology has raised concerns about impersonation and privacy violations. Although proactive defenses aim to block identity extraction at the source, existing methods suffer from perceptible visual artifacts, poor generalization across diverse deepfake models, and vulnerability to post-processing techniques (e.g., diffusion purification, image compression, and transformations). This work proposes a robust, generalizable proactive face-swapping defense via semantic gradient divergence (SGD-Guard) to address these challenges. It introduces an integrated feature gallery that uses CLIP features and a generalized identity feature, obtained by iteratively refining heterogeneous identity features into a homogeneous representation. This framework facilitates our semantic distortion attack by leveraging consensus weighting to target specific facial attributes within a CLIP-identity joint embedding space, disrupting deepfake generation while preserving visual fidelity. Furthermore, to ensure robustness against purification and post-processing, this method incorporates a module that prioritizes critical transformations by exploiting directional discrepancies. Comprehensive experiments demonstrate that the method effectively defends against diverse face-swapping models with high cross-model transferability.
Test-Time Adaptation (TTA) aims to adapt pretrained models to unseen test data, which is crucial for resource-constrained edge devices that must handle distribution shifts on the fly without human supervision. However, conventional TTA methods often fail in realistic scenarios characterized by continuous shifts and severe class imbalances while incurring prohibitive memory overheads. To enable continuous adaptation to test data on edge devices under a realistic TTA setting, we propose a Bias-Resistant Online Statistical Alignment (BOSA) method. BOSA facilitates unbiased adaptation via a discrepancy-aware statistical alignment mechanism integrated with a class-balanced memory bank. To ensure memory efficiency, we further design a saliency-guided activation sparsification and gradient reconstruction scheme, which drastically reduces memory overhead without sacrificing gradient integrity. Extensive evaluations demonstrate that BOSA achieves superior accuracy with a compact memory consumption compared to state-of-the-art methods under realistic TTA settings.
Diffusion models show significant potential for low-light image enhancement. However, this task requires satisfying human perceptual preferences and content fidelity transcending simple brightness and color improvement. Existing methods rely on heuristic physical priors or incorporate perceptual metrics directly into timestep-wise training objectives. Such proxy constraints fail to provide reliable trajectory-level guidance for perceptual alignment. Furthermore, they often lead to artifacts or unnatural visual effects in this ill-posed inverse problem. To address these issues, we propose an unsupervised low-light enhancement framework based on Group Relative Policy Optimization (GRPO), which utilizes perceptual preferences to directly optimize the diffusion policy. We introduce a Sliding Window Hybrid ODE-SDE Sampling strategy that confines stochasticity to dynamic sub-intervals, thereby achieving efficient coarse-to-fine exploration and precise advantage attribution. To meet strict fidelity constraints, we construct a Synergistic Perception-Fidelity Reward and introduce an Independent Advantage Estimation strategy to mitigate signal collapse and gradient suppression in multi-objective optimization. Furthermore, we design a Temporal-Aware Dynamic Weighting Mechanism that adaptively adjusts perceptual weights across denoising stages to balance visual enhancement with structural preservation. Extensive experiments on multiple real-world benchmarks demonstrate that our method effectively improves the perceptual performance of existing models, yielding results that better align with human aesthetics.
In this paper, we revisit multimodal few-shot 3D point cloud semantic segmentation (FS-PCS), identifying a conflict in "Fuse-then-Refine" paradigms: the "Plasticity-Stability Dilemma." In addition, Contrastive Language-Image Pre-training (CLIP)'s inter-class confusion can result in semantic blindness. To address these issues, we present the Decoupled-experts Arbitration Few-Shot SegNet (DA-FSS), a model that effectively distinguishes between semantic and geometric paths and mutually regularizes their gradients to achieve better generalization. DA-FSS employs the same backbone and pre-trained text encoder as the baseline MultiModal Few-Shot SegNet (MM-FSS) to generate text embeddings, which can increase cost-free modalities' utilization rate and better leverage each modality's information space. To achieve this, we propose a Parallel Expert Refinement module to generate each modal correlation. We also propose a Stacked Arbitration Module (SAM) to perform convolutional fusion and arbitrate correlations for each modality pathway. The Parallel Experts decouple two paths: a Geometric Expert maintains plasticity, and a Semantic Expert ensures stability. They are coordinated via a Decoupled Alignment Module (DAM) that transfers knowledge without propagating confusion. Experiments on popular datasets (S3DIS, ScanNet) demonstrate the superiority of DA-FSS over MM-FSS. Meanwhile, geometric boundaries, completeness, and texture differentiation are all superior to the baseline. The code is available at: https://github.com/MoWenQAQ/DA-FSS/.
Visual grounding aims to localize target objects based on natural language descriptions, and the core challenge lies in the cross-modal gap, which is partly caused by the significant differences in semantic structure between language and vision. Existing methods typically rely on holistic sentence-level semantic representations to modulate visual features, while overlooking the inherent structure of textual prompts. In this work, we propose a Syntactic Structure-guided Visual Grounding framework, referred to as SSVG. Specifically, to inject syntactic priors into unstructured visual representations, we design a semantic structure-based feature refinement module to adaptively modulate subject-centric and contextual visual features. To perform cross-modal alignment, we further incorporate a visual semantic consistency verification module, which leverages a subject-aware contrastive learning strategy to constrain and verify the semantic correspondence between the visual prediction and subject-level textual representation, thereby enhancing the model's robustness against semantically similar distractors. Extensive experiments demonstrate that our approach consistently outperforms state-of-the-art methods, and detailed analyses verify the effectiveness of each component.
Supervised infrared-visible image fusion (IVIF) often overfits limited training distributions, creating a critical generalization gap under open-world degradations (rain, haze, low light, noise, blur). To address this issue, we propose AIR-Fusion, a parameter-efficient adaptation of a frozen, restoration-capable latent diffusion backbone for degraded IVIF without full fine-tuning, transferring restoration priors for robust fusion. A Cross-Modal Bridging Adapter (CMBA) aligns infrared cues and textual instructions with the frozen diffusion conditioning space and injects them into multi-scale denoising features to steer instruction-guided restoration-aware fusion. In addition, a Trajectory-Constrained Rectifier (TCR) regularizes stochastic sampling via a pixel-latent closed loop, rectifying intermediate predictions with source-referenced structures and re-encoding them to stabilize the denoising trajectory and recover fine details suppressed by latent compression. Experiments across multiple datasets and degradation settings show consistent improvements in restoration quality and fusion fidelity, with strong generalization under complex and compounded degradations.
Real-world systems increasingly require coherent reasoning and generation over diverse data modalities simultaneously. Current generative frameworks rely on complex, multi-stage training, resulting in low efficiency due to iterative inference and high computational cost. They also struggle with unified multimodal representation, failing to balance fine-grained details with global structures and long-term dependencies, which limits generative quality and practical usability. To overcome these limitations, we introduce the Inverse Heat Mean Flow (IHMF), a general-purpose solver that is compatible with a wide range of model backbones. Without requiring pre-training, IHMF directly learns an average velocity field through an inverse heat formul ation. By exploiting the inherent scale-space properties of the inverse heat process, IHMF explicitly decomposes multi-scale complexities, thereby simplifying trajectory learning and enabling adaptive topological alignment. Extensive experiments show that IHMF achieves a competitive performance with state-of-the-art methods, providing a robust and unified mathematical framework for various generative tasks. The code is publicly available at https://github.com/CHBonline/IHMF.
Video captioning models convert frames into visual tokens and generate descriptions with large language models (LLMs). Since encoding all frames is prohibitively expensive, uniform sampling is the default choice, but it enforces equal temporal coverage while ignoring the uneven events distribution. This motivates a Learnable Frame Selector (LFS) that selects temporally diverse and event-relevant frames. LFS explicitly models temporal importance to balance temporal diversity and event relevance, and employs a stratified strategy to ensure temporal coverage while avoiding clustering. Crucially, LFS leverages caption feedback from frozen video-LLMs to learn frame selection that directly optimizes downstream caption quality. Additionally, we identify the gap between existing benchmark and human's cognition. Thus, we introduce ICH-CC built from carefully designed questions by annotators that reflect human-consistent understanding of video. Experiments indicate that LFS consistently improves detailed video captioning across two representative community benchmarks and ICH-CC, achieving up to 2.0% gains on VDC and over 4% gains on ICH-CC. Moreover, we observe that enhanced captions with LFS leads to improved performance on video question answering. Overall, LFS provides an effective and easy-to-integrate solution for detailed video captioning.
Multimodal sentiment analysis relies on textual, acoustic, and visual signals, yet real-world data often suffer from modality missing and quality imbalance. Existing methods generate features for modality missing from available ones, but differences in expression mechanisms and sentiment dynamics across modalities may cause the generated features to deviate from true distributions and mislead prediction. In addition, unreliable modalities may dominate fusion, resulting in representation shift across modality combinations and unstable sentiment representations. To address these challenges, we propose a two-level reference alignment framework. The framework introduces stable references at the feature representation and sentiment decision levels to improve robustness under modality missing. First-level reference alignment leverages complete-modality samples to constrain representations and align different modality combinations into a shared sentiment space. Second-level reference alignment enforces cross-modal consistency at the decision level by suppressing unreliable modalities through prototype retrieval and voting. As a result, the framework maintains stable and reliable sentiment predictions under diverse missing-modality patterns. Experiments on CMU-MOSI and CMU-MOSEI show consistent improvements across various missing-modality settings. Under full-modality input, the proposed method achieves state-of-the-art performance, with ACC of 86.28% and 85.88%, and F1 of 86.24% and 85.86%.
Camouflaged Object Detection (COD) aims to segment objects that are hidden within complex backgrounds. Due to the low visual contrast of camouflaged objects, annotations are costly, motivating unsupervised COD (UCOD) to eliminate labeling expenses. Most UCOD methods follow the “MLLMs + other foundation models + SAM” paradigm, which relies on spatial interactions that are unreliable in camouflaged scenarios, leading to fundamental performance bottlenecks. In this paper, we propose a novel UCOD framework that leverages SAM3 through category-level interaction with MLLMs, bypassing unreliable spatial prompts. To address SAM3’s sensitivity to category granularity, we introduce Fine-grained Category Query, guiding MLLMs to generate full-granularity category chains for robust category prompting. To mitigate suboptimal segmentation caused by high camouflage and background confusion, we propose Semantic–Geometric Dual Confirmation, which jointly validates segmentation masks from semantic and spatial perspectives. Furthermore, we introduce Semantic–Geometric Reasoning Injection, which injects critical semantic and geometric cues into MLLMs to refine category reasoning and progressively correct segmentation errors under extreme camouflage or MLLM hallucinations. Extensive experiments show that our method significantly outperforms existing UCOD approaches and achieves performance comparable to weakly supervised COD.
Designing effective reward functions remains a major challenge in reinforcement learning (RL), particularly in open-ended environments where task goals are abstract and difficult to quantify. In this work, we present VLM-AR3L, a framework that leverages Vision-Language Models (VLMs) to provide both absolute and relative rewards for RL. VLM-AR3L interprets an agent’s visual observations in the context of a natural language task goal, and learns both absolute and relative rewards from VLM-generated preference labels. The absolute reward model predicts scalar evaluations for individual states, while the relative reward model compares consecutive observations to infer progress or regression toward the task goal. Their integration combines the stability of state-based evaluation with the robustness of comparative supervision. We evaluate VLM-AR3L across benchmarks spanning classic control, manipulation, and open-world embodied tasks, with a particular focus on Minecraft given its visual complexity and long-horizon decision-making requirements. Experimental results show that VLM-AR3L consistently outperforms prior VLM-based reward learning methods. Videos and code are available on the project website: https://vlm-ar3l.github.io/.
Large Vision-Language Models (LVLMs) often suffer from hallucinations, generating descriptions that include visual details absent from the input image. Recent preference alignment methods typically rely on supervision distilled from stronger models such as GPT. However, this offline paradigm introduces a Supervision-Perception Mismatch: the student model is forced to align with fine-grained details beyond its perceptual capacity, learning to guess rather than to see. To obtain reliable self-supervision for online learning, we identify a Generative-Discriminative Gap within LVLMs, where models exhibit higher accuracy on discriminative verification than open-ended generation. Leveraging this capability, we propose Online Self-CAlibRation (OSCAR), a framework that integrates Monte Carlo Tree Search with a Dual-Granularity Reward Mechanism to construct preference data and iteratively refines the model via Direct Preference Optimization. Extensive experiments demonstrate that OSCAR achieves state-of-the-art performance on hallucination benchmarks while preserving general multimodal capabilities.
Few-shot medical image segmentation relies on dense, boundary-sensitive prototype matching, yet common pre-training objectives mainly optimize global alignment or reconstruction, creating an objective gap that hurts boundary delineation and increases adaptation cost. This raises the question: how to pre-train representations intrinsically matchable for episodic FSS while requiring minimal adaptation-induced re-organization? We introduce a Drift-Gap diagnostic to quantify intrinsic dense-matching misalignment and adaptation-induced feature drift. Guided by this lens, we propose BOG-PRETRAIN, combining Reliability-Gated Alignment to mitigate noisy report supervision, Semantic-Guided MIM to emphasize boundary-informative regions, and Dual Consistency Regularization to stabilize episodic metric geometry. Across five benchmarks (1/4/16-shot), BOG-PRETRAIN improves mean Dice by +15.5/+15.9/+12.5 points over best priors and reduces mean HD95 by 0.9/4.6/10.1; it achieves the lowest Drift (0.052 vs. 0.155 baseline) and Gap_PT (0.256), with ablations confirming the components' complementarity.
Recently, transformer-based trackers have become the leading approach, surpassing traditional CNN-based trackers in accuracy. However, their high computational demands hinder their deployment on edge platforms, necessitating efficient solutions. To address this, we propose a novel Neural Architecture Search (NAS) framework designed for transformer-based trackers, named NASTrack. This framework incorporates token pruning to optimize both transformer block structures and the layer-wise token keeping ratio, striking a balance between performance and efficiency. To handle the larger search space introduced by the keeping ratio, we propose a blacklist strategy and a matching-based distillation driven by the Token Overlap Ratio (TOR). Our method discovers hundreds of high-performing trackers, with FLOPs ranging from 1G to 18G. The searched trackers consistently outperform existing efficient state-of-the-art trackers such as CompressTracker and LiteTrack under comparable computational budgets.The code and models are available at https://github.com/Cyhoon84/NASTrack.git.
Compositional Zero-Shot Learning (CZSL) aims to combine known attributes and objects as primitives for recognizing previously unseen attribute-object pairs. Prior works either predict attributes and objects independently, missing their strong contextual dependency, or use unidirectional conditional modeling (e.g., object-guided attribute prediction), which is prone to error propagation. We propose PRPC, a Progressive Reasoning framework with Primitive Correction, which explicitly models the bidirectional dependency between attributes and objects via step-wise inference. PRPC performs mutual correction of primitives to suppress prediction errors in earlier steps. Specifically, we formulate CZSL as structured, Q&A-style Chain-of-Thought reasoning process and constrain the MLLM to follow predefined semantic steps to generate intermediate decisions. To further enhance the reliability and logical consistency of intermediate reasoning, we introduce reinforcement learning post-training with a GRPO-based objective, providing step-level rewards aligned with the progressive inference procedure. Extensive experiments on three CZSL benchmarks demonstrate that PRPC achieves state-of-the-art performance, validating the effectiveness of progressive reasoning and bidirectional correction for robust compositional generalization.
Monocular 3D object detection is a cost-efficient alternative to multisensor systems, yet it remains fragile to multi-component adversarial attacks that perturb the image and tamper with camera calibration. Compounded distortions degrade 3D reasoning by disrupting the correspondence between the 3D geometry and 2D image plane. To address this problem, this work proposes MonoPure, a monocular 3D object detection framework that performs multi-component purification via disentangled and projective representations. MonoPure incorporates a disentangled purification and segmentation module that purifies the image data, with a target-region probability map steering diffusion-based purification to focus on task-relevant regions. In addition, MonoPure presents a 3D detection decoder that integrates 2D skeleton keypoints as object-level spatial cues, enabling occlusion-robust 3D detection. Finally, a projective calib-purification module restores compromised intrinsics by iteratively minimizing the reprojection error between projected 3D boxes and calibration-invariant 2D detection boxes. The experiments confirm that MonoPure outperforms prior detectors under multi-component attacks and occlusion.
Accurate identification of non-rigid motion is crucial for geometric validity in self-supervised monocular depth estimation (MDE), yet it remains challenging for current methods. Inspired by Human Visual Perception (HVP), we present VFM-Dynamo, an efficient self-supervised MDE framework that disambiguates non-rigid objects by combining a vision foundation model (VFM) such as Grounding DINO and SAM with coarse to fine motion identification strategy: 1) Integrating visual-textual feature dependencies, we activate the capability of Grounding DINO global understanding with text prompts to detect potential object bounding boxes. 2) We then estimate coarse motion mask from reprojection error and photometric consistency to separate static from dynamic content. This mask provides coarse guidance for constraining rigid flow in static regions through two analogous estimates aligned by a consistency loss, and it drives a non-dynamical suppression module that removes boxes associated with static objects. 3) The remaining boxes are used to prompt SAM to produce refined motion identification, which in turn guide the joint optimization of depth and optical flow. Additionally, due to foreground–background mixing, standard interpolation-based upsampling often produces boundary artifacts. We introduce a learnable neighbor affinity interpolation (LNAI) module, which directly upsamples depth to full resolution and can be seamlessly integrated as a plug-and-play component. Experiments on a series of benchmarks demonstrate that proposed framework achieves state-of-the-art performance among unsupervised methods. Code is available at https://github.com/Qianqian3764/VFM-Dynamo.
High-resolution sinogram completion is critical for computed tomography reconstruction, as missing projections can introduce severe artifacts. While diffusion models provide strong generative priors for this task, their inference cost grows prohibitively with resolution. We propose HRSino, a training-free and efficient diffusion inference approach for high-resolution sinogram completion. By explicitly accounting for spatial heterogeneity in signal characteristics, such as spectral sparsity and local complexity, HRSino allocates inference effort adaptively across spatial regions and resolutions, rather than applying uniform high-resolution diffusion steps. This enables global consistency to be captured at coarse scales while refining local details only where necessary. Experimental results show that HRSino reduces peak memory usage by up to 30.81% and inference time by up to 17.58% compared to the state-of-the-art framework, and maintains completion accuracy across datasets and resolutions.
3D Gaussian Splatting enables efficient, high-fidelity novel view synthesis with explicit Gaussians and differentiable rendering. However, adverse weather introduces rain streaks and droplets as well as volumetric scattering, producing view-dependent, spatially varying degradations that break the clean multi-view consistency assumption and lead to geometric drift and unstable appearance. Existing approaches are largely confined to the 2D image domain and seldom model the 3D degradation formation process, limiting controllable weather synthesis and consistent restoration in 3DGS. To our knowledge, we are the first to incorporate real meteorological observations as an external prior and propose a 3D-level unified rendering–restoration framework for joint deraining and dehazing within a single 3DGS pipeline. Precipitation is mapped to interpretable parameters controlling the density and morphology of rain Gaussians, while an atmospheric-scattering extinction strength drives 3D fog generation for reproducible weather modeling. We adopt a closed-loop dual-branch optimization where the rendering branch fits degraded observations to capture weather degradation patterns, and the restoration branch regularizes scene Gaussians toward a clean domain with multi-scale perceptual consistency, suppressing artifacts and improving cross-view detail fidelity. Experiments across diverse scenes and weather conditions consistently outperform strong baselines on all three metrics, with a particularly notable PSNR improvement of 1.78 dB on average.
Vision-based trajectory prediction with BEV representations has achieved promising results, yet existing methods often suffer from limited temporal modeling and insufficient characterization of motion dynamics. To address these issues, we propose a temporally enhanced framework with explicit motion parameter prediction. Specifically, we introduce BEVFormer++, which leverages multi-view images and BEV features from multiple preceding timesteps to generate more robust BEV representations, along with BEV differential features to capture temporal variations. Moreover, we propose a motion-parameter-decoupled tracking module that explicitly estimates velocity, acceleration, and heading angle, providing informative motion cues for trajectory prediction. Extensive experimental results demonstrate that our method outperforms state-of-the-art approaches and can be seamlessly integrated into existing vision-based frameworks, consistently yielding performance improvements.
We present D3Adapter, a threat-aware framework that unifies adversarial example detection (AED) and robust inference. D3Adapter attaches a small library of lightweight adapters to a frozen ResNet backbone; the adapters are trained under two loss functions (cross-entropy and optimized reverse cross-entropy) and complementary objectives (clean training and adversarial training), yielding intentionally distinct logit behaviors. During inference, D3Adapter quantifies inter-adapter logit divergence to produce an agreement-based threat score without any external detector for AED. The same pass also performs robust inference by outputting prediction from the selected adapter when an adversarial example is detected, therefore unifying detection and defense into single-pass forward computation. We evaluate D3Adapter under transfer-based and adaptive white-box attacks, and we study scalability across datasets with varying numbers of classes, showing that unified detection and robust inference can be achieved with predictable overhead proportional to the number of adapters.
Recently, Visual State Space Models offer powerful global modeling for Dual-modal Salient Object Detection (SOD). However, they are still constrained by three inherent limitations: first, Mamba's strict reliance on sequential ordering makes it sensitive to cross-modal geometric misalignment, where spatial shifts disrupt token correspondence; second, general indiscriminate scanning treating all tokens equally may lead to signal dilution, where sparse foreground features are overwhelmed by background noise; third, conventional decoders rely on implicit upsampling, causing boundary degradation during resolution recovery. To address these challenges, we propose G-SalAlignMamba, a geometry-aware framework tailored for dual-modal SOD. We introduce Geometry-Aware Encoding with explicit alignment to correct spatial shifts, Semantics-Informed Refinement to prevent signal dilution by prioritizing foregrounds, and Structure-Preserving Decoding that integrates explicit alignment with unsupervised boundary refinement. Extensive experiments show that G-SalAlignMamba achieves state-of-the-art performance on RGB-D and RGB-T benchmarks with favorable efficiency (30.41 FPS, 83.80M parameters). The code is available at https://github.com/PC1-99/G-SalAlignMamb.git.
Acquiring three-dimensional(3D) microstructural images of cement hydration reveals critical microscale features essential for understanding hydration mechanisms and advancing material development. Micro-computed tomography(µCT) is widely used to capture these images due to its non-destructive, repeatable 3D imaging capability, despite at high operational cost. However, µCT suffers from limited resolution, weak texture, and missing phase information. In contrast, backscattered electron(BSE) provides high-resolution, phase-sensitive, and texture-rich images but are confined to 2D form. Inspired by the idea of fusing BSE style into µCT images for computationally imaging 3D BSE data, this paper proposes a cross-device generation method, termed CT2BSE, to construct 3D BSE microstructural images from µCT for cement hydration. A Voxel Swin Transformer is proposed to extract 3D μCT features by improving Video Swin Transformer with a Content-Aware Positional Encoding–3D, making encoder better suited for homogeneous images such as cement. Furthermore, a Holistic Style Injector–3D is proposed to fuse 3D μCT features with 2D BSE characteristics, thereby mitigating feature instability caused by the extreme intensity variations typically exhibited in cement images. Subsequently, the fused features are decoded into 3D volumes aligned with the BSE style while preserving original microstructure. Experimental results demonstrate that CT2BSE can generate high-fidelity 3D BSE images from μCT.
Multimodal Large Language Models (MLLMs) perform strongly in high-resource languages, yet often produce fluent but culturally "thin" descriptions in low-resource settings. We argue that this failure is not merely a linguistic limitation: culture-specific visual knowledge depends on native visual-textual alignments that translation-centric pipelines rarely provide. We present MELLA, a multimodal dataset across eight low-resource languages, designed to jointly support linguistic fluency and cultural groundedness. MELLA uses a dual-source strategy that combines native web image-alt-text pairs for culture-grounded supervision with generated-and-translated image descriptions for linguistically rich supervision, explicitly separating two learning signals often conflated in multilingual multimodal data. Through controlled diagnostic fine-tuning on multiple MLLM backbones, we show that MELLA mitigates cultural hallucination by helping models recognize and articulate culturally specific entities overlooked by translation-based adaptation. Our findings highlight data alignment, rather than model modification alone, as a key path toward culturally grounded multimodal understanding in low-resource languages.
Achieving visual coordination between egocentric (ego) and exocentric (exo) perspectives is a cornerstone of augmented reality and human-machine collaboration. However, extreme viewpoint shifts and occlusions often cause semantic drift in existing methods, making robust cross-view correspondence a formidable challenge. In this paper, we propose SARA (Semantic-Anchored Referential Alignment), a framework designed to bridge the ego-exo gap by leveraging viewpoint-invariant, high-level semantic information as region-level semantic anchors for robust feature mapping. Specifically, our approach incorporates: (1) the Semantic Anchoring Module extracts cross-view category priors and invariant features to provide stable region-level references across perspectives, and (2) the Multimodal Semantic Vector Fusion mechanism achieves language-guided manifold fusion of semantic vectors to synthesize unified embeddings, effectively establishing representational correspondence across disparate perspectives. Extensive experiments across diverse, complex scenarios demonstrate SARA’s superior performance in establishing stable mappings,validating the effectiveness of semantic-invariant features and multimodal fusion in addressing the core hurdles of cross-view understanding.