Computer Vision · Cross-listed from cs.LG
PRISM: Powerful Time Series to Image (TS2I) Representations for Multivariate Anomaly Detection
Mateusz Smendowski, Kamil Faber, Piotr Nawrocki et al. (+2 more)
Time series anomaly detection (TSAD) underpins applications in predictive maintenance, finance, and cloud computing, however performance remains sensitive to representation choices, especially in multivariate settings. While transforming time series into images has shown success in
forecasting and classification, it remains unclear how multivariate, high-dimensional series should be mapped to multi-channel images and whether
vision backbones can match time-domain baselines in TSAD. We introduce PRISM, a plug-and-play meta-workflow enabling systematic construction and evaluation of image-based representations for multivariate TSAD. Our evaluation spanning over 7,000 experiments shows that well-designed PRISM configurations are competitive with 24 time-domain baselines, achieving the best VUS-PR on 10 of 14
datasets, with an average improvement of 41% over the best competing method on those
datasets. Further, we identify channelization - how the channel dimension of multi-channel images is constructed - as a critical and previously understudied design dimension, and introduce MSM, a novel statistics-based scheme achieving 11-27% gains over PCA-based alternatives. Finally, ImageNet-pretrained encoders transfer effectively to TSAD, with frozen encoders retaining 92% of fine-tuned performance while training 1.8 times faster. Our code is available at: https://github.com/Smendowski/PRISM.
Read the full abstract ▾
All authors Mateusz Smendowski, Kamil Faber, Piotr Nawrocki, Nathalie Japkowicz, Roberto Corizzo
Computer Vision
GeoMAR: Unleashing Geometrically Aligned Features for Masked Autoregressive Blind Face Restoration
Lu Gan, Hanyu Yan, Chaofeng Chen et al. (+2 more)
Codebook-based blind face restoration (BFR) often suffers from ambiguous conditioning features and a fragile prediction mechanism under severe degradation. To address these challenges, we propose GeoMAR, a framework designed to unleash geometrically aligned features with masked autoregressive (MAR) refinement for robust face restoration. For feature conditioning, we introduce a dual-input extraction pipeline to extract component-based
geometric descriptions with explicit, spatially faithful anchors. These textual priors are integrated with low-quality (LQ) features via an Aligned
Geometric Priors Injector, which employs a KV-Q exchange strategy to generate geometrically aligned features. For prediction mechanism, we reformulate the one-step mapping into a multi-step MAR process. This coarse-to-fine generation progressively refines complex facial regions based on increasingly reliable context. Experiments on one synthetic and three real-world
benchmarks demonstrate that GeoMAR achieves highly competitive perceptual quality and coherent visual structures compared with existing methods. The code is available at https://github.com/BRL-SYSU/GeoMAR.git.
Read the full abstract ▾
All authors Lu Gan, Hanyu Yan, Chaofeng Chen, Junqi Hu, Dan Zeng
Computer Vision
Low-Dimensional High-Leverage Subspace Optimization: Beyond Full-Parameter Coupled Training for Neural Network Quantization
Peng Xia, Junbiao Pang and Zheng Huang
Low-bit quantization suffers severe accuracy degradation on compact networks, rooted in the dominant full-parameter coupled training paradigm that ignores parameter subspace heterogeneity. Their limited feature redundancy leaves little room to absorb quantization errors. Conventional pipelines adopt monolithic optimization: PTQ reconstructs fixed pretrained models without improving inherent quantization friendliness; QAT updates all parameters jointly, suffering from gradient coupling between backbone weights and calibration parameters. In this paper, we identify normalization affine parameters as a low-dimensional high-leverage subspace dominating quantization robustness, and propose Normalization Affine Preconditioning (NAP) for targeted subspace optimization. For PTQ, NAP freezes backbone weights and fine-tunes only affine parameters under the target fake-quantization graph on full-precision models, proactively boosting quantization friendliness before downstream reconstruction. For QAT, we introduce an alternating QAT-NAP schema that decouples feature learning and numerical calibration, breaking the performance ceiling of saturated joint training. Theoretical analysis confirms BN affine parameters fully cancel the channel-wise affine component of quantization distortion, while nonlinear rounding and clipping residuals form the irreducible error boundary;
distillation-guided NAP acts as directional flatness optimization, projecting teacher-student logit mismatch onto the restricted subspace. Experiments on ImageNet and CIFAR-100 show NAP recovers severely collapsed low-bit quantization, consistently boosts reconstruction-based PTQ, and outperforms saturated full-parameter QAT with negligible tuning cost. This work reveals the principle of targeted low-dimensional subspace optimization, offering a new perspective beyond full-parameter coupled training for efficient deep learning.
Read the full abstract ▾
Computer Vision
When and Where to Look: Adaptive Visual Evidence Scheduling for Efficient Long Video Understanding
Ke Li, Jiayu Chen, Maoliang Li et al. (+5 more)
Efficient long-
video understanding requires
vision–
language models (VLMs) to reason over a small number of frames selected as sparse visual evidence. Existing relevance-based methods rely on static one-shot selection with fixed frame budgets and candidate pools, while
agent-based schedulers achieve adaptivity through costly multi-round
reasoning and interactive search. We propose EcoFrame, a training-free framework for low-overhead query-adaptive visual evidence scheduling. EcoFrame leverages the VLM's inference feedback to determine when to increase the frame budget and where to search for additional candidate evidence. Specifically,
entropy-gated budget scheduling uses output uncertainty to stop early when the current evidence is sufficient or progressively expand the frame budget otherwise. Meanwhile,
attention-guided candidate proposal converts frame-level
attention into a temporal prior, enabling dense local search in informative regions while preserving global coverage when
attention is diffuse. Experiments on
Video-MME, LongVideoBench, and MLVU demonstrate that EcoFrame achieves a better accuracy–efficiency trade-off across multiple VLM backbones. On Qwen2.5-VL, EcoFrame achieves an average accuracy of 64.4, surpassing BOLT at 63.5, while providing a $1.85\times$ speedup over AKS and BOLT. Compared with the
agent-based A.I.R., EcoFrame maintains comparable accuracy with up to a $13.5\times$ inference speedup. Code will be available at https://github.com/AK-DREAM/EcoFrame.
Read the full abstract ▾
All authors Ke Li, Jiayu Chen, Maoliang Li, Zihao Zheng, Hailong Zou, Hengyi Zhang, Xuanzhe Liu, Xiang Chen
Computer Vision
StreamDAM: Presence-Aware Memory for Real-Time Streaming Video Object Segmentation
Xiang Chen
Quality-tier
video object
segmentation (VOS) trackers such as DAM4SAM top accuracy leaderboards, but they are measured offline, one frame at a time with no clock. Under an honest streaming protocol at 30 frames per second, where a frame that misses its budget is served the last mask already computed, the winner collapses: the rich
memory that makes it accurate is too slow to keep up, and what it emits is blind to whether the object is even present. We trace both failures to one place, the tracker's
memory pipeline, and rebuild it for streaming. \method{} makes the
memory machinery itself run at frame rate through in-model optimization rather than a bolted-on fallback, and governs it with a single learned presence signal that decides what enters
memory, how far back the tracker reads, when to withhold output, and when to re-detect. A mechanism analysis shows why a fixed policy cannot win: the control that helps when an object truly disappears is the one that hurts when it is merely hard to see, so the choice must be made per frame. Across four
benchmarks and five modern baselines, \method{} is the strongest streaming tracker, recovers nearly all of the offline model's accuracy under the clock, and on the hardest content exceeds the offline model it is built from.
Read the full abstract ▾
Computer Vision
UniEvo-RS: Omni-Prompt Unified Remote Sensing Segmentation with Representative Exemplar-Driven Prototype Evolution
Kunquan Zhang, Peilang Li, Xikun Hu et al. (+4 more)
Prompt-driven
vision-
language models (VLMs) hold immense promise for accelerating dense remote sensing (RS) annotation, but static models suffer from severe performance degradation when deployed on novel scenes, unseen categories, or visually confusing backgrounds. Moreover, existing unified paradigms primarily rely on intra-image specific
prompts, lacking flexible task routing to adapt to multi-intent operational workflows. In practical batch mapping, annotators typically refine a small set of representative samples before processing large
datasets. Motivated by this practice, we propose UniEvo-RS, an omni-
prompt unified RS
segmentation framework equipped with representative exemplar-driven prototype
evolution. First, we construct a multi-instruction
prompt dataset that unifies text-driven and visual-driven
prompts within a single architecture, establishing a dynamic task-routing mechanism for highly diverse RS annotation scenarios. Second, we introduce a representative feedback-driven, training-free prototype
evolution mechanism. By contrasting manual annotations with initial predictions on exemplars, UniEvo-RS distills prediction errors into positive and negative prototypes. These prototypes enhance LLM query recall and suppress spatial background noise under a fixed-budget clustering
memory. Extensive experiments show that UniEvo-RS unifies diverse prompting tasks, achieving state-of-the-art performance across most settings. Crucially, with minimal interaction on a few exemplars, it enables training-free, progressive accuracy enhancement on unseen categories during batch annotation.
Read the full abstract ▾
All authors Kunquan Zhang, Peilang Li, Xikun Hu, Yunkai Yang, Yushan Zou, Zhiwei Zhang, Runmin Dong
Computer Vision
NCGR: Noise-Conditional Gated Rectification for Camera Extrinsic Perturbations in BEV 3D Object Detection
Wenbin Pan, Wanhao Liu, Liwei Luo et al. (+3 more)
Camera-based bird's-eye-view (BEV) 3D detection typically assumes accurate and fixed camera extrinsics. In detectors using spatial cross-
attention (SCA), extrinsic perturbations displace the image-plane projections of BEV reference points, causing queries to sample features from incorrect regions and degrading detection performance. To address this failure mode, Noise-Conditional Gated Rectification (NCGR) is proposed to compensate for projection errors without explicitly estimating a full six-degree-of-freedom extrinsic correction. For each query-camera pair, a 2D rectification offset is predicted and modulated by a camera-level gate to rectify the base projection before native deformable sampling. During training, the perturbation-derived quantities used to construct the condition and gate are gradually replaced through scheduled interpolation by counterparts generated from an auxiliary scalar predicted from camera features. This transition enables blind inference without perturbation metadata. During training, a weight-shared clean-teacher/perturbed-student pair is used, and the rectification module is supervised by a BEV-consistency objective between the two branches. NCGR is evaluated on nuScenes with simulated dynamic and static extrinsic perturbations. In a five-camera dynamic stress test, NCGR achieves 39.69% NDS, compared with 28.00% for BEVFormer and 33.23% for CAPE. Under clean extrinsics, NCGR maintains performance comparable to that of BEVFormer.
Read the full abstract ▾
All authors Wenbin Pan, Wanhao Liu, Liwei Luo, Panshuo Li, Yong Xu, Renquan Lu
Computer Vision
CARE-X: Towards Clinically Useful Radiology VLMs with Auxiliary Supervision, Reward-Aligned Learning, and Tool-Augmented Measurement
Mercy Prasanna Ranjit, Anirban Porya, Sathvik Joel et al. (+8 more)
A clinically useful chest X-ray system must go beyond fluent report generation: it should classify findings with tunable decision thresholds, localize them spatially, and derive the anatomical measurements upon which many diagnoses depend. Today's
Vision-
Language Models (VLMs) treat these as separate problems, if they address them at all, leaving a gap between what radiologists need and what generative models provide. We introduce CARE-X, a chest X-ray VLM that narrows this gap by unifying auxiliary discriminative supervision with reward-aligned generation. CARE-X augments its generative backbone with focal-loss classification and composite-loss grounding heads, co-trained alongside the
language-modeling objective. This auxiliary supervision produces discriminative diagnostic predictions with tunable decision thresholds and precise spatial localization while also improving report quality, providing evidence that structured prediction and generation reinforce one another. Building on this foundation, Decoupled Clip and Dynamic Sampling Policy Optimization (DAPO) leverages task-specific reward signals for report generation, visual question answering (VQA), and spatial grounding, directly optimizing the clinical quality metrics that matter in practice. The result is state-of-the-art performance on the majority of metrics across four report-generation
benchmarks, 94.0% VQA accuracy on ReXVQA (+6.0 pp over the next-best baseline), and generative spatial decoding that reaches near parity with dedicated detection heads. Separately, to address measurement-dependent diagnoses, we couple Qwen3-VL-4B-Instruct with native tool-calling capabilities for invoking deterministic measurement tools, while retaining full visual access to the image. This hybrid inference yields +43.6 pp average F1 over perception-only baselines across five measurement-dependent conditions.
Read the full abstract ▾
All authors Mercy Prasanna Ranjit, Anirban Porya, Sathvik Joel, Niharika Vadlamudi, Nikhilesh Chowdary Eathamukkala, Prasanth V V, Abhyuday Kumara Swamy, Pranay Narhari Umredkar, Pradeep Narayan, Vivek Rajagopal, Tanuja Ganu
Computer Vision
MuRA: Multi-Rank Adaptation for Efficient and Effective Test-Time Vision-Language Generalization
Gengyuan Liu, Nanzhou Wang, Chang Liu et al. (+5 more)
Vision-
language models exhibit remarkable zero-shot capabilities but suffer significant performance degradation under distribution shifts. While test-time adaptation (TTA) via Low-Rank Adaptation offers a parameter-efficient solution, we identify a fundamental bottleneck in current methods: the reliance on static rank configurations. Because visual inputs inherently possess varying information densities, a fixed rank forces an inevitable optimization compromise, leading to underfitting on complex scenes and overfitting on simple ones. To bridge this gap, we propose Multi-Rank Adaptation (MuRA), a novel framework that dynamically selects and fuses adaptation modules of varying capacities based on
token-level visual complexity. MuRA synergizes Multi-Rank Orthogonal Decomposition to provide a superior, knowledge-preserving initialization, and Unified Component Fusion with Continuous Router Updating to sustainably learn semantic-to-rank mappings. Furthermore, we provide rigorous theoretical justifications mathematically proving the necessity and gradient stability of this adaptive mechanism. Crucially, MuRA's dynamic design uniquely thrives at the deepest visual layer, capitalizing on the shortest gradient backpropagation path. Extensive experiments demonstrate that MuRA achieves state-of-the-art accuracy across extensive domain generalization and cross-
dataset benchmarks while significantly reducing both computational and
memory overhead.
Read the full abstract ▾
All authors Gengyuan Liu, Nanzhou Wang, Chang Liu, Qinwen Wu, Zhenhao Wang, Jiacong Wang, Bokui Chen, Xiangyang Ji
Computer Vision
BanglaWild: An In-the-Wild Bengali Scene Text Recognition Benchmark for OCR and Vision-Language Models
Sadab Shiper, Tawsif Tashwar Dipto, Mir Md Inzamam et al. (+1 more)
In-the-wild Bengali scene text recognition is largely unmeasured: existing resources target handwritten documents or constrained sign-board parsing, report only aggregate edit-distance metrics, and evaluate either conventional OCR or VLMs, never both on the same in-the-wild data. To address this gap, we introduce BANGLAWILD, a
benchmark of 2,535 Bengali scene text images, each paired with a verbatim gold transcription, two categorical axes, four diagnostic attributes, and an orthographically standard form where the in-image text deviates from canonical spelling. We evaluate fifteen VLMs and three conventional OCR systems under three prompting strategies, fine-tune 6 open-source models with LoRA, and complement edit-distance metrics with an LLM-as-a-Judge evaluation. Our results reveal a persistent gap in which larger models within the same family do not outperform smaller ones. Our fifteen-class error taxonomy shows that visual mis-recognition accounts for ~60% of errors in the strongest systems, while conjunct-related errors contribute under 2%, challenging a long-standing assumption in Bengali OCR research; the same visual dominant profile also holds across architectures, including the one conventional baseline that reads Bengali reliably.
Prompt language mainly affects cross-script drift and LoRA reduces catastrophic failures in weak models without lifting the ceiling on already competent ones. Code and data will be publicly released.
Read the full abstract ▾
All authors Sadab Shiper, Tawsif Tashwar Dipto, Mir Md Inzamam, Eshat Tanzeem
Computer Vision
CPrefix: A Combinatorial Tensor Framework for Structured Discrete Color Mappings
Yvan Richard
Discrete multi-channel mappings are typically represented through sampled values, providing accurate evaluations but limited insight into their underlying structure. We introduce CPrefix, a combinatorial observable representation for discrete mappings, realized within a unified tensor framework that enables representation, reconstruction, and structural analysis. The framework is based on a counting tensor induced by multinomial counting observables. Its support forms a discrete Pascal simplex, not as a constraint on the observable space, but as a latent combinatorial representation from which mappings are reconstructed. This formulation separates the combinatorial organization of a mapping from its measured values, exposing the observable structure underlying the mapping. The framework is validated on ICC display and printer profiles through latent reconstruction and perceptual gamut transport. Accurate reconstruction demonstrates that color mappings admit faithful observable representations, while reconstruction residuals provide insight into the compatibility of the underlying mapping with the proposed representation. Although demonstrated on color transformations, the framework is independent of the physical interpretation of the observables, making it applicable to structured multi-channel mappings arising from color imaging, spectral measurements and other discrete systems.
Read the full abstract ▾
Computer Vision
LiteMVS: Efficient Multi-View Stereo with Foundation Distillation and Expert Aggregation
Tianbao Zhang, Zeyu Liu, Shuyu Wu et al. (+4 more)
Real-time 3D perception is crucial for robotics, augmented reality, and
embodied intelligence applications. Existing multi-view stereo (MVS) methods primarily rely on
geometric correspondences, which often fail in textureless or repetitive regions, while
monocular depth models leverage strong image-level priors but lack robust multi-view
geometric constraints. More importantly, in robotics and
embodied manipulation scenarios, high-quality 3D geometry is not only essential for static reconstruction, but also serves as a critical foundation for learning temporally consistent 4D representations. To obtain visual representations with stronger structural awareness and greater potential for spatiotemporal extension, we present LiteMVS, a lightweight multi-view depth estimation model that integrates plane-sweep
geometric reasoning with strong
monocular semantic and structural priors. The central idea of LiteMVS is to efficiently inject high-level
monocular knowledge, obtained from lightweight
segmentation models and large-scale
vision foundation models, into a multi-view stereo framework. In particular, LiteMVS enriches the cost volume with semantic descriptors and employs a Mixture-of-Experts (MoE) formulation to enable adaptive
geometric aggregation across depth hypotheses. Moreover,
geometric priors distilled from
vision foundation models further strengthen
monocular guidance without increasing inference cost. Through this design, LiteMVS not only improves depth estimation and 3D reconstruction quality in static scenes, but also provides a more reliable
geometric foundation for subsequent temporal modeling and 4D representation learning. Experiments on ScanNetv2 and 7-Scenes demonstrate that LiteMVS achieves high-quality depth prediction and 3D reconstruction while maintaining competitive efficiency.
Read the full abstract ▾
All authors Tianbao Zhang, Zeyu Liu, Shuyu Wu, Fanxing Li, Zhaoxin Fan, Wenjun Wu, Danping Zou
Computer Vision
Geo-Embed: Towards Unified Multimodal Embeddings for Urban Understanding
Jiapeng Li, Yong Li, Junjie Zhou et al. (+2 more)
Geospatial and urban applications increasingly require models to compare heterogeneous evidence across street-view imagery, remote-sensing observations, text descriptions, region proposals, and temporal change cues. However, existing
multimodal embedding models and
benchmarks are still largely designed and evaluated around general-purpose image-text matching, leaving unclear whether unified
embedding space can support heterogeneous geospatial tasks involving spatial relationships, fine-grained semantics, and temporal changes. To address this gap, we make three key contributions. First, we introduce GeoMEB, a large-scale
multimodal embedding benchmark that standardizes 45 urban evaluation tasks across
retrieval, visual question answering, change detection, classification, and visual grounding, together with training collections comprising 1.32M examples and 286K evaluation queries. Second, we present Geo-Embed, a unified
embedding model that adapts a shared
vision-
language backbone to instruction-conditioned query-target matching over heterogeneous geospatial inputs, including single images, multiple images, text, regions, and masks. On GeoMEB, Geo-Embed achieves the strongest overall performance among representative
multimodal embedders, with a 15.3% relative improvement over the strongest baseline. These results motivate future geospatial embedders that organize training and evaluation around explicit query-target relations, including semantic, cross-view, region-level, and temporal correspondence.
Read the full abstract ▾
All authors Jiapeng Li, Yong Li, Junjie Zhou, Fan Zhang, Yu Liu
Computer Vision
FlowForm: Synergizing Fluid Physics with Topological Consistency for Satellite Flood Synthesis
Zhang Weihui, Wang Ruizhi, Xu Hongye et al. (+3 more)
Developing robust flood assessment models requires high-quality paired satellite imagery, yet such data remain scarce for flood-specific image generation. Although generative models provide a promising means of data augmentation, existing methods often yield implausible spatial layouts of flooded regions and distort scene structures. We propose FlowForm, a framework for satellite flood synthesis that integrates SWE-inspired latent regularization with structure-aware conditioning. The Flood Descriptor Module (FDM) imposes differentiable penalties on residuals of the steady-state Shallow Water Equation in auxiliary latent fields at the
diffusion bottleneck. The Terrain Anchor Adapter (TAA) injects depth, semantic, and edge features at four encoder scales of the U-Net. We further curate FloodScape, a large-scale, high-resolution
dataset comprising paired satellite images acquired before and after disasters. In addition to standard image-generation metrics, we evaluate the consistency of flooded regions, zero-shot generalization to a geographically held-out flood event, and sensitivity to individual components. Across all reported comparisons, FlowForm achieves higher visual fidelity, greater similarity between paired images, and stronger consistency of flooded regions.
Read the full abstract ▾
All authors Zhang Weihui, Wang Ruizhi, Xu Hongye, Wang Huiqiong, Sun Li, Song Mingli
Computer Vision
UHP Detection: LVLMs have their Unique Hallucination Pattern in the Consistency Space
Amir Mohammad Ezzati, Kiyan Rezaee, Bardiya Kariminia et al. (+4 more)
Large
vision–
language models (LVLMs) demonstrate strong
multimodal reasoning capabilities but remain prone to
hallucination, where model predictions are not grounded in visual evidence. Existing black-box
hallucination detection methods estimate uncertainty through a single consistency metric, implicitly assuming that model uncertainty can be adequately characterized by a single measure. However,
hallucinations exhibit diverse manifestations of uncertainty across different behavioral probes, making a single measure insufficient to characterize their underlying behavior. We propose Unique
Hallucination Pattern (UHP) Detection, a fully black-box framework that models
hallucination as a structured uncertainty pattern defined by two axes: perturbation modality (image vs.\ text) and logical polarity (a statement vs.\ its negation). Their intersection produces four complementary consistency groups that capture distinct manifestations of model uncertainty, from which both within-group and between-group features are extracted to train a lightweight classifier. Through comprehensive experiments on AMBER and PhD across three LVLMs, UHP Detection consistently outperforms prior black-box and white-box baselines, with improvements of up to $+18.72\%$ AUC-ROC and $+20.07\%$ AUC-PR over the strongest black-box methods. Extensive ablation studies demonstrate that each consistency group contributes complementary information and that their combination forms a structured
hallucination pattern. Furthermore, cross-
dataset evaluation shows that this learned pattern generalizes across
benchmarks, indicating that
hallucination behavior reflects a model-specific consistency pattern. Code is publicly available at https://github.com/amirezzati/uhpdet.
Read the full abstract ▾
All authors Amir Mohammad Ezzati, Kiyan Rezaee, Bardiya Kariminia, Mohamad Amin Yousefi, Asal Mohammadjafari Mamaqani, Behrad Samimi, Mohammad Hossein Rohban
Computer Vision
OmniPack: Unified Token Compression for Efficient Omni-modal Large Language Models
Wanshun Su, Yang Shi, Feihu Liu et al. (+10 more)
Omni-modal large
language models (Omni-LLMs) have achieved remarkable performance on audio-visual understanding tasks, but processing long and highly redundant visual and audio
token sequences incurs substantial computational overhead, demanding aggressive
token compression for efficient deployment. Existing methods often degrade at low
token budgets: pre-LLM compression may discard structurally important and globally distributed evidence, whereas inner-LLM compression often underexploits query-conditioned audio-visual collaboration. To address these limitations, we propose OmniPack, a training-free framework that coordinates structural compression before the LLM with task-relevant semantic refinement within the LLM. Before the LLM, OmniPack removes structural redundancy through modality-specific importance, global coverage, and similarity-aware merging. After sufficient
multimodal interaction, it further consolidates diverse, task-relevant representations through textual guidance and audio-visual collaboration. Extensive experiments on five
benchmarks with three Omni-LLM backbones demonstrate that OmniPack consistently achieves the best performance-efficiency trade-off across diverse retention ratios, outperforming all existing methods. Notably, on Qwen2.5-Omni-7B, OmniPack preserves 98.0% of the original performance while reducing FLOPs to 16.7%, and still retains 92.9% of the original performance with only 6.8% of the original FLOPs.
Read the full abstract ▾
All authors Wanshun Su, Yang Shi, Feihu Liu, Ziwen Yu, Yan Min, Zhuoran Zhang, Qixun Wang, Haotian Wang, Shixuan Liu, Yuanxing Zhang, Peng Wu, Chengfu Huo, Liang Ding
Computer Vision
AgenticVAU: Multi-Agent Explore-Verify Reasoning for Video Anomaly Understanding
Yuxiang Duan, Huining Li, Ao Li et al. (+6 more)
Video anomaly understanding (VAU) focuses on comprehensively interpreting abnormal events in
videos, requiring models to identify anomalous occurrences, discover their supporting evidence, and explain the underlying causes beyond simple anomaly detection. Existing VAU methods often rely on specialized training or limited observations, restricting generalization or evidence coverage. Although single-
agent alternatives support adaptive
video observation, they still integrate exploration, observation, and decision-making within a unified
reasoning process, offering limited role specialization and structured evidence coordination. To address these limitations, we present AgenticVAU, a training-free multi-
agent framework that casts VAU as an explore–verify process, where the system first discovers potential anomalies and then verifies them through targeted observations. To achieve this, four specialized
agents are introduced to handle visual-rule construction, search planning,
video observation, and final decision, respectively. These
agents communicate through an anchor registry, a shared evidence
memory that binds each observation. Guided by this
agent framework, AgenticVAU interleaves broad temporal exploration, dense local verification, and cross-interval comparison until sufficient evidence is collected. We conduct extensive experiments on the ECVA, UCF-Crime, and MSAD subsets of VAU-Bench, the results show that AgenticVAU outperforms zero-shot inference and reinforcement learning-based baselines, demonstrating the value of multi-
agent collaboration for
video anomaly understanding.
Read the full abstract ▾
All authors Yuxiang Duan, Huining Li, Ao Li, Shuai Feng, Lanju Kong, Ning Liu, Jian Zhang, Xingdong Sheng, Yuntao Du
Computer Vision
TDVR: Joint Text Disambiguation and Viewpoint Reasoning for Zero-Shot 3D Visual Grounding
Qingxi Du, Junbo Wang, Yuke Li et al. (+1 more)
Zero-shot 3D visual grounding aims to localize specific objects based on textual descriptions and 3D visual input. However, the effectiveness of existing methods is significantly hindered by the ambiguous query text and deficient viewpoints. To address these issues, we propose TDVR, a training-free
reasoning framework that disambiguates the input text and infers accurate viewpoints for zero-shot 3D visual grounding. First, we construct semantic 3D scene graph from the detected instances in the 3D point cloud. Subsequently, we put the original query, appearance and spatial relationship descriptions into the LLM for fusion, thereby disambiguating the initial input. We leverage chain-of-thought
reasoning to generate the structured representation of disambiguated query. Then taking the scene graph and structured query as input, we get the optimal view via viewpoint
reasoning to solve the problem of missing viewpoints during grounding. Based on the obtained optimal viewpoint, we further discriminate the distracting objects, enabling the model with the ability to distinguish similar instances. After that, we match the category text and appearance images with the query by computing the similarity of feature vectors. Finally, the target object was identified by integrating the viewpoint score, confusion score, category score, and appearance score. Compared with previous methods, our TDVR has stronger capabilities in viewpoint
reasoning, similar object discrimination, and ambiguous query understanding. Experimental results on the public ScanRefer
dataset show that our method outperforms the existing state-of-the-art methods by 15.25% and 14.46% in Acc@0.25 and Acc@0.5 respectively, demonstrating the effectiveness of our TDVR in addressing ambiguous query text and deficient viewpoints.
Read the full abstract ▾
All authors Qingxi Du, Junbo Wang, Yuke Li, Yining Zhu
Computer Vision · Cross-listed from eess.IV
Unsupervised Adversarial Domain Adaptation for Uterine layer Segmentation: From Labeled Cine to Unlabeled Dynamic EPI MRI
Smiti Tripathy, Milauni Desai, Jordina Aviles Verdera et al. (+1 more)
Uterine peristalsis is a key physiological phenomenon responsible for various functions across the menstrual cycle, intimately linked to uterine wall microstructure. Alterations in uterine motion and tissue properties are implicated in the etiology of gynecological diseases, yet these processes have been studied in isolation. We introduce a dynamic multi-echo gradient echo EPI framework for simultaneous characterization and correlation of uterine peristaltic activity and time-resolved T2* changes at 0.55T. Inherent susceptibility artifacts, reduced resolution, and burden of manual uterine layer annotation are addressed by an unsupervised
adversarial domain adaptation framework, transferring
segmentation knowledge from labeled cine MRI to unlabeled dynamic EPI. We implemented Unet-LSTM with multi-scale domain discriminators that exploits temporal layer dynamics. A Dice score of 0.88 and Jaccard index of 0.80 was achieved. Mean T2* values were 108ms, 76ms, and 124ms for the myometrium, junctional zone, and endometrium. A negative correlation between junctional zone area and T2* was observed in 14/39 cases, providing first insights into oxygenation patterns associated with junctional zone contraction and motion, demonstrating feasibility of assessing the interplay between contractility and dynamic T2* changes.
Read the full abstract ▾
All authors Smiti Tripathy, Milauni Desai, Jordina Aviles Verdera, Jana Hutter
Computer Vision
Towards Reliable and Reproducible Fetal Brain Biometry: A Deep Learning Approach Using MRI
Francesca Maccarone, Marina Di Stefano, Giorgio Longari et al. (+7 more)
Fetal
brain biometry is essential for quantitative assessment of
brain development, supporting gestational age estimation, developmental monitoring, and detection of abnormalities. In clinical practice, measurements are manually performed, making them time-consuming and prone to variability. While automated approaches have been proposed, reproducible methods remain limited, particularly those providing anatomically interpretable landmark localization. We present a fully automated deep learning-based framework for reliable and reproducible
brain biometry from 3D super-resolution-reconstructed fetal
brain MRI. The proposed four-step pipeline derives biometric parameters by jointly estimating linear measurements and their corresponding anatomical landmarks. A 3D convolutional neural network is trained to regress landmark coordinates from
brain segmentation label maps, followed by measurement-specific
geometric optimization to refine landmark positions and compute measurements. The pipeline is evaluated on two publicly available fetal MRI
datasets comprising 150 volumes (gestational age range: 20-37 weeks) acquired across different scanners and protocols, assessing five key biometric measurements across varying acquisition settings and providing a comprehensive evaluation of both measurement accuracy and landmark localization using quantitative metrics and visual assessment. Compared with the only available automated pipeline, the proposed method achieves comparable or improved accuracy for most measurements. In conclusion, we introduce a straightforward pipeline for reliable biometry estimations, with efficiency, interpretability and scalability that support integration into clinical workflows.
Read the full abstract ▾
All authors Francesca Maccarone, Marina Di Stefano, Giorgio Longari, Giulia Frigerio, Gloria Rizzato, Rocco Prudentino, Nivedita Agarwal, Tommaso Ciceri, Denis Peruzzo, Simone Melzi
Computer Vision
Maximilian Dillitzer, Tin Stribor Sohn, Jason J. Corso et al. (+1 more)
In human visual perception, uppercase lettering serves as a natural salience cue that captures
attention within lowercase text. In this paper, we present a systematic empirical characterization study revealing that Large
Language Models (LLMs) exhibit an analogous property: letter casing modulates internal
attention allocation. Through analysis across 13 models, nine LLMs and four
Vision-
Language Models (VLMs), with diverse tokenization schemes, we show that formatting target information in alternating or uppercase against a lowercase context concentrates
attention on those textual spans. In text this effect is universal, holding across every evaluated non-
reasoning model. We frame it as a previously under-explored latent property of pretrained
transformers rather than a prescriptive method. Our investigation reveals a central
attention-performance divergence: while this "casing effect" robustly shifts
attention, its impact on downstream accuracy is non-trivial, increased concentration does not inherently improve task accuracy and, in high-
entropy contexts like alternating case, can degrade it. We further identify a boundary condition: the deliberative "thinking" phase in
reasoning models acts as a semantic buffer that mitigates typographic sensitivity in text. Extending the study to VLMs, we find the effect transfers partially: the same
prompt-side casing reorganizes cross-modal
attention along two coupled axes, predominantly a macroscopic disengagement from the image toward the text
prompt, and secondarily a concentration of the residual visual
attention on the target region. By isolating casing as a zero-shot mechanism for
attention steering that requires no model access or fine-tuning, we provide a new foundational understanding of how pretraining internalizes typographic emphasis.
Read the full abstract ▾
All authors Maximilian Dillitzer, Tin Stribor Sohn, Jason J. Corso, Michael Auerbach
Computer Vision
MultiCompose: Multi-Concept Personalized Composition with Per-Subject Attribute Binding
Ruirui Zhang, Zhengkai Zhao and Pan Gao
Text-to-image
diffusion models enable personalization of specific visual concepts from a small number of reference images. However, generating a single image that contains multiple personalized subjects, each bound to user-specified attributes such as clothing, accessories, and held objects, remains largely unaddressed. Without explicit spatial constraints, concurrently activated concept checkpoints produce overlapping cross-
attention responses, causing per-subject identity degradation and attribute misalignment. Moreover, no established
benchmark jointly evaluates these two failure modes in the personalized multi-subject setting. We present MultiCompose, a composition framework that decouples per-concept personalization from multi-subject inference. A semantic preservation regularization maintains attribute binding capacity during fine-tuning, while a two-phase inference procedure automatically establishes subject layout and composes per-concept predictions through spatially exclusive masks. We further introduce MSP-Bench, a
benchmark that jointly evaluates identity fidelity (ID), attribute binding accuracy (BIND), and attribute misalignment (MIS) through a dual-pathway protocol. Experiments show that MultiCompose outperforms existing methods on both conventional metrics and MSP-Bench, confirming the
benchmark's ability to reveal failure modes that conventional metrics overlook. Code is available at https://github.com/I2-Multimedia-Lab/MultiCompose
Read the full abstract ▾
Computer Vision · Cross-listed from cs.SE
Pattern over Pixels: Measuring Pattern Completion Bias in Multimodal Code Generation
Khai-Nguyen Nguyen, Oscar Chaparro and Antonio Mastropaolo
Multimodal large
language models (MLLMs) are increasingly used to translate webpage screenshots into front-end code, but repeated UI patterns may sway them toward visually incorrect yet pattern-consistent outputs. In this work, we test how repeated webpage patterns hurt MLLM accuracy on an objective screenshot-to-code fill-in-the-blank task. We introduce the first
benchmark for visual pattern-completion bias, where one localized element in a repeated UI pattern is perturbed and the model must recover the masked width or font-size value from the screenshot and HTML context. Starting from 30 webpages curated from the Design2Code
dataset, we build 1,440 evaluated screenshots spanning structural card and text-style patterns under standard and noise-overlaid conditions. We evaluate five frontier MLLMs and find that all are strongly biased toward the repeated baseline. Mean bias rate reaches 69.78% on card-width perturbations and 80.22% on text font-size perturbations, while mean accuracy is only 21.17% and 7.89%, respectively. Codex-5.3 performs best but still drops from 68.61% accuracy on cards to 13.89% on text, while Flash-3.0 reaches 96.11% bias on text. Noise, subtler perturbations, and boundary positions further increase bias rate.
Reasoning analysis further shows that greater
reasoning effort correlates with lower bias, yet qualitative evidence reveals that models can identify the anomalous element and still override it with the pattern-consistent answer. Our results identify a concrete failure mode in
multimodal code generation and show that its severity is strongly associated with visual saliency
Read the full abstract ▾
Computer Vision
Keep the Needle, Prune the Haystack: Defect-Preserving Token Pruning for Efficient Zero-Shot Anomaly Detection
Yanning Hou, Jingyuan Zhang, Xiaoyun Wang et al. (+3 more)
Zero-shot visual anomaly detection has achieved remarkable progress, with recent
vision-only approaches further improving performance while simplifying the inference pipeline. However, existing methods typically perform dense computation over all images and spatial
tokens, despite the fact that normal samples dominate real-world scenarios and anomalies usually occupy only small regions.
Token pruning offers a promising solution, but introduces an asymmetric
pruning risk in anomaly detection: retaining normal
tokens mainly incurs redundant computation, whereas removing anomalous
tokens may eliminate the only evidence for detection and localization. This risk is particularly severe in early layers, where
pruning provides the greatest computational benefit but anomaly semantics remain unreliable. We propose KeepAD, a defect-preserving
token pruning framework that formulates
token selection as high-recall, anomaly-aware routing. In shallow layers, KeepAD combines coverage-preserving selection over local $2\times2$ patch neighborhoods with deterministic anomaly rescue to reduce the risk of discarding subtle defects. In deeper layers, frozen normal and abnormal prototypes guide
pruning under an image-adaptive
token budget, aggressively removing low-risk normal
tokens while preserving local anomaly evidence. Dense-to-sparse self-
distillation further supervises early
token routing without introducing additional inference overhead. Experiments on six industrial and seven medical zero-shot anomaly detection
benchmarks show that KeepAD reduces the
token retention ratio to below $20\%$, while limiting the average degradation in image-level and pixel-level AUROC to within $2.7$ percentage points. At the most aggressive operating point, KeepAD achieves a $7.9\times$ speedup over the strongest CLIP-based baseline.
Read the full abstract ▾
All authors Yanning Hou, Jingyuan Zhang, Xiaoyun Wang, Qixiang Ma, Sihang Zhou, Ke Xu
Computer Vision
XiDepth: a Lightweight and Efficient Network for Self-supervised Monocular Depth Estimation
Elena Izzo, Riccardo Toniolo and Lamberto Ballan
Self-supervised
monocular depth estimation has emerged as an appealing solution to design lightweight and effective models for deployment on computationally constrained devices due to its reduced reliance on expensive depth sensors. By eliminating the need for ground-truth annotations and leveraging the simplicity of
monocular camera setups, this approach facilitates cost-effective data collection and broad applicability across fields such as computer
vision and robotics. A critical challenge is achieving resource-efficient neural networks without compromising the overall performance. State-of-the-art models generally adopt depth-wise convolutions and
attention mechanisms; however, these functions often incur high energy costs and face compatibility issues in embedded environments. To address this, we propose XiDepth, a lightweight architecture based on the XiNet operator block, designed to enhance feature extraction while maintaining low computational complexity and energy demand. On the KITTI
dataset, XiDepth achieves state-of-the-art performance with only 0.8M parameters. Tests on a Raspberry Pi 4 further confirm its suitability for real-world embedded applications, reducing FLOPs by 40% and energy consumption by 35% compared to leading methods.
Read the full abstract ▾
Computer Vision
Morphology-Aware Implicit Super-Resolution Network for Pathological Images
Jiaming Liang, QiHui Han, Haolin Chen et al. (+5 more)
Accurate diagnosis in Digital Pathology (DP) relies on high-resolution whole-slide images, yet clinical deployment is often limited by hardware costs. Super-Resolution (SR) offers a promising alternative by computationally enhancing low-resolution acquisitions. However, existing SR methods frequently struggle to preserve fine-grained cellular morphology, leading to texture oversmoothing and blurred structural boundaries under complex tissue variability. To address this issue, we propose Morph-ISR, a morphology-aware implicit super-resolution framework for DP that restores diagnostically relevant details with sub-pixel precision. Morph-ISR reformulates SR as a continuous coordinate-based reconstruction problem and integrates an Implicit Position-aware Kernel Generator (IPKG) to adaptively model spatially varying tissue morphology. To further enhance structural fidelity, a Morphological Fidelity Prior (MFP) is introduced, leveraging semantic guidance from a pre-trained
cell segmentation network to enforce boundary-preserving and region-aware reconstruction, thereby improving the representation of critical cellular boundaries and
nuclear textures. Experiments on TCGA and SurGen
datasets show that Morph-ISR achieves the best LPIPS and ST-LPIPS among the evaluated methods, reducing them by up to 38.37% and 39.55%, respectively, over the second-best methods while maintaining strong PSNR and SSIM. These results demonstrate superior preservation of diagnostically relevant cellular boundaries and
nuclear textures, while compact parameterization and high throughput support efficient edge deployment. Code and trained models will be released upon publication.
Read the full abstract ▾
All authors Jiaming Liang, QiHui Han, Haolin Chen, Chengxin Ye, Jiawen Liu, Jiazhou Chen, Xiaoqi Sheng, Hongmin Cai
Computer Vision
When Do Fewer Visual Tokens Accelerate Multimodal Inference? A Break-Even Study Across Decision Locations and Hardware
Hao Dou and Ruiwen Tian
Fewer visual
tokens do not guarantee lower end-to-end latency. We evaluate break-even with a reproducible protocol that accounts for decision overhead, shared work, and the operators each policy can avoid. A stage-level decomposition reconciles these components with measured end-to-end latency. In a 30-example pilot, the two tested autoregressive probes remain slower than Full despite state reuse. A lightweight post-
vision predictor yields paired confidence intervals below zero on RTX 3090 and A100 and remains significant after a conservative all-pairs Holm correction. A pre-
vision image-size rule also yields intervals below zero on both GPUs, although neither comparison remains significant after the same correction. Pre-
vision routing has a structural opportunity unavailable to post-
vision pruning: it can avoid preprocessing and
vision encoding. On A100, this opportunity outweighs a nearly eightfold larger downstream
token reduction by the post-
vision policy. Reported quality is conditional on examples answered correctly by Full and is not
benchmark accuracy.
Read the full abstract ▾
Computer Vision
Learning Biomechanically Plausible Human Motion from Sparse Radar Point Clouds
Jonas Leo Mueller, Markus Gambietz, Alexander Weiss et al. (+2 more)
Radar-based human pose estimation has focused on improving learning
algorithms while representing the body as unconstrained keypoint coordinates. We address the underexplored dimension of anatomical fidelity by integrating a full-body skeletal model into a differentiable, end-to-end trainable radar-based pose estimation framework, in which the pose network is supervised through forward kinematics while subject-specific geometry is fitted beforehand. Subject-specific body segment proportions are predicted from radar point cloud features to scale a biomechanical skeleton. A motion prediction network maps temporal radar sequences to generalized coordinates, and differentiable forward kinematics converts predicted joint angles into 3D positions. A contact classification loss encourages physically plausible foot-ground interaction. Under leave-one-subject-out cross-validation on 11 healthy participants performing rehabilitation exercises, the framework achieves 6.456 +/- 1.759 cm mean per-joint position error (MPJPE), 8.083 +/- 0.884 degrees mean per-joint angle error (MPJAE), 0.935 +/- 0.009 contact classification F1, and 3.4 +/- 1.3 % scaling error. This proof-of-concept study demonstrates the feasibility of recovering interpretable biomechanical descriptors from a single low-cost radar sensor in a controlled laboratory setting, a prerequisite for future clinical motion analysis.
Read the full abstract ▾
All authors Jonas Leo Mueller, Markus Gambietz, Alexander Weiss, Daniel Krauss, Bjoern M. Eskofier
Computer Vision
SEER: A Self-Grounded Evidence Interface for Controlled Spatial Relation Classification
Feixiang Liu, Likun Wang, Qiang Qiu et al. (+3 more)
Spatial relation questions require a model to identify the queried subject and object before comparing their layout. Yet a VLM can recognize both entities and still answer from the wrong instance or an ambiguous global view. We ask whether making query-specific evidence explicit can mitigate this failure and propose SEER (Self-grounded Evidence for Entity-Relation
Reasoning), a training-free inference-time evidence interface for frozen VLMs. SEER hides candidate relations during pair localization, constructs a query-specific view with explicit subject/object roles, and retains the full image and sparse box geometry as complementary evidence. For relation-choice protocols with exact inverse support, an optional refinement swaps the entity roles and changes the forward decision only when exactly one visual state obeys the corresponding inverse relation. On an image-disjoint GQA-Train900 test frozen before model scoring, SEER pools to +3.94 [2.17,5.72] over Full; the gain remains positive under label-independent grounding-order counterbalancing and on the 535 rows whose entity names are unique. The unchanged protocol yields +4.35 to +11.79 on all 2,434 filtered EmbSpatial pair-relation questions across three models. Matched controls separate local refocus from role-explicit conditioning. These results establish query-specific evidence construction as the principal intervention, with reciprocal consistency as a smaller protocol-specific refinement.
Read the full abstract ▾
All authors Feixiang Liu, Likun Wang, Qiang Qiu, Hui Xu, Huawei Shen, Xueqi Cheng
Computer Vision
Geospatial-Prior Guidance for 3D Semantic Scene Completion
Meng Wang, Shougao Zhang, Wenzhe He et al. (+4 more)
Inferring complete 3D geometry and semantics from onboard images remains challenging because occlusions and restricted fields of view leave large scene regions underconstrained. Although satellite imagery provides wide-area context, appearance cues alone offer limited structural guidance and may be unreliable because of spatial or temporal discrepancies. We present GeoScene, a geospatially guided framework that jointly uses satellite imagery and structured OpenStreetMap cues as soft priors for 3D semantic scene completion. GeoScene learns complementary voxel-wise reliability weights for onboard observations and geospatial guidance, and uses them to control feature refinement in observed and unobserved regions. This design preserves local visual evidence while exploiting large-scale road and building structure beyond onboard visibility. Experiments on SemanticKITTI and SSCBench-KITTI-360 demonstrate that GeoScene consistently improves both
geometric and semantic completion under the geospatial-prior-assisted setting, with the most pronounced benefits for large-scale static and geospatially structured classes.
Read the full abstract ▾
All authors Meng Wang, Shougao Zhang, Wenzhe He, Ruihui Li, Nan Hu, Zhuo Tang, Kenli Li