Computer Vision
Co-Evolutionary Prompt Optimization with Cross-Category Transfer for Zero-Shot Anomaly Detection
Sisi Zhu, Changwei Yu, Renshuai Tao et al. (+1 more)
Zero-shot anomaly detection (ZSAD) has gained significant
attention for its practical value in industrial inspection. Recently, CLIP-based approaches have been widely adopted in ZSAD due to their strong
vision-
language generalization capabilities. However, existing methods commonly employ continuous
prompt embeddings for
prompt optimization and encode semantics in latent vectors, which lack interpretability and scalability. To this end, we propose CoEvoAD, a co-evolutionary framework for discrete
prompt selection. CoEvoAD performs
prompt search in the discrete natural-
language space using an evolutionary
algorithm. Candidate
prompts are iteratively generated, evaluated, and selected throughout population
evolution, thus preserving the interpretability and composability of natural
language. Furthermore, we introduce a Cross-Category Transfer Objective (CCTO), which treats held-out source categories as proxies for unseen categories and scores
prompt rules based on their estimated cross-category transferability, effectively improving cross-category generalization. Extensive experiments are conducted to validate the effectiveness of CoEvoAD, and the results show that it achieves state-of-the-art performance across multiple anomaly detection
datasets. The code is available at https://github.com/rstao-bjtu/CoEvoAD.
Read the full abstract ▾
All authors Sisi Zhu, Changwei Yu, Renshuai Tao, Zhenliang Ni
Computer Vision
Text-Guided Diffusion-Based Adversarial Attacks on Chest X-Ray Images
Basudha Pal, Arjun Narayanan, Neha Ajith et al. (+2 more)
As artificial intelligence is increasingly integrated into chest X-ray (CXR) interpretation, triage, and clinical decision support, understanding its vulnerability to
adversarial manipulation is critical for safe deployment. Existing robustness evaluations, however, predominantly rely on pixel-space attacks that introduce numerically constrained perturbations but may not represent plausible radiographic variation. This limitation is particularly important in multi-disease CXR classification, where models simultaneously evaluate multiple overlapping pathologies and
adversarial failures may alter several diagnostic predictions. We propose a text-guided
diffusion-based
adversarial framework that optimizes learnable text conditioning while keeping the
diffusion generator and target classifier frozen, enabling
adversarial generation through a learned image prior rather than direct pixel manipulation. We evaluate the framework across multiple classifier architectures in both binary atelectasis and multi-disease CXR classification and compare it with FGSM, PGD, and Carlini-Wagner attacks. Our approach consistently produced the greatest degradation in classifier performance, reducing AUROC to 0.3885-0.5646 in binary classification and 0.4441-0.4878 in the multi-disease setting, while achieving superior image fidelity (SSIM 0.9080, LPIPS 0.1670, FID 51.23). Importantly, clinician interpretation remained unchanged for 95.9% of binary and 73.8% of multi-disease
adversarial images despite substantial changes in model predictions. These findings reveal a clinically important discrepancy between human and machine interpretation and demonstrate the need to extend medical AI robustness evaluation beyond conventional pixel-space attacks toward generative threat models that can expose failures under visually and clinically plausible image variations.
Read the full abstract ▾
All authors Basudha Pal, Arjun Narayanan, Neha Ajith, Vikas R Bhat, Muhammad Umair
Computer Vision · Cross-listed from cs.LG
Does Latent Planning Survive Point Clouds? Action-Conditioned JEPA World Models for Geometric Observations and Goals
Fabio F. Oberweger, Michael Schwingshackl and Markus Murschitz
Latent action world models let
agents plan new behaviors at test time by predicting how actions change the environment, and joint-
embedding predictive architectures (JEPAs) do so by
forecasting future latent states rather than pixels. Yet nearly all such models see the world through a camera, even though robotic manipulation is fundamentally
geometric: in robotics goals for manipulation are traditionally specified by target object poses, not by images of the object once placed. We ask whether latent planning survives a shift from appearance to geometry, on the observation side as well as on the goal specifications side. To answer this, we extend the stable-worldmodel evaluation platform with simulated
LiDAR-style raycast point clouds as a new sensor modality, and adapt three JEPA designs to point clouds: a frozen-encoder model built on Utonia features, a distribution-prior model based on LeWM, and an action-sensitive model based on Delta-JEPA. We further introduce a goal-encoding mechanism that constructs the goal latent from the current latent and a 3D target pose, removing the need for goal images or goal point clouds. A comparative evaluation of the different anti-collapse mechanisms shows that point-cloud world models can match their image-based counterparts, demonstrating that the modality shift from appearance to geometry is achievable. All models are released as open weights with open-source training and inference code, to make world-model planning accessible for
LiDAR-driven and pose-directed robotic tasks.
Read the full abstract ▾
Computer Vision
Calibration and Comparative Analysis of Forward-Looking Sonar and 3D Sonar for Enhanced Underwater Object Recognition
Aditya Penumarti, Khanh Dong, Zi-Hao Zhang et al. (+6 more)
Sonars generate a significant amount of noise. With the advent of new technology capable of producing full 3D point clouds, the noise is amplified in sparse point clouds, making it challenging to recognize features for
navigation, recognition, or reconstruction. To address this challenge, we propose using two different sonar modalities: one that produces a 2D intensity image and another that generates a 3D point cloud. By implementing auto-calibration, we can filter out noisy features between the modalities to enhance feature extraction. Experiments demonstrate that auto-calibration improves performance over manual calibration by 5% and that filtering enhances feature extraction by more than 40% relative to the raw point cloud. Code and
datasets are given at https://theaprilab.org/fls-3d-calibrator
Read the full abstract ▾
All authors Aditya Penumarti, Khanh Dong, Zi-Hao Zhang, Yongkyoon Park, Zhenqi Wu, Trung Dong, Shahriar Negahdaripour, Xiaomin Lin, Jane Shin
Computer Vision
Polis: 3D Self-Supervision at City Scale
Alexander Rusnak, Sophia Kovalenko, Jingru Wang et al. (+3 more)
Reliable semantic representations derived from city-scale 3D models are increasingly important for urban analysis, infrastructure monitoring, autonomous systems, and heritage conservation. However, urban scenes of large spatial extent captured through aerial surveying differ substantially from the indoor, object-level, and self-driving
LiDAR data used to pretrain most 3D self-supervised models. We introduce Polis, to our knowledge the first application of Sketched Isotropic Gaussian Regularization (SIGReg) as an objective for a native point cloud encoder, and evaluate it through a frozen-feature
benchmark spanning fourteen city- and building-scale corpora. Polis combines geometrically matched cosine invariance, SIGReg, and VICReg-style anti-collapse terms with a 12.8k-scene outdoor pretraining mixture and
gravity-preserving spatial view sampling. Controlled ablations show that this objective outperforms student–teacher architecture alternatives, as well as Polis versions without anti-collapse terms, on the same representative outdoor corpus. On three pretraining-disjoint city
datasets, Polis reaches $23.8\%$ mean mIoU versus $16.3\%$ for the next-best encoder under high-capacity frozen probing, and $17.3\%$ versus $16.1\%$ at a matched point and voxel budget. The same city-scale lead holds on
datasets whose training sets were seen in pretraining. On localized terrestrial captures with fine-grained facade and streetscape labels, the ranking reverses. Our results show that distributionally-regularized joint
embedding architectures can be successful on challenging city-scale 3D scenes, and that transfer improves when self-supervision is designed for the capture geometry and spatial context of this domain while also revealing the limits of this specialization.
Read the full abstract ▾
All authors Alexander Rusnak, Sophia Kovalenko, Jingru Wang, Ismail Moudden, Xiru Wang, Frédéric Kaplan
Computer Vision
An Integrated Vision-and-Language Pretraining (VLP) and Visual Question Answering (VQA) model to Automate Nondestructive Evaluation Image Analysis
Mehrdad Shafiei Dizaji and Hoda Azari
An AI-based approach called ChatNDE Figure to Caption is introduced, which aims to automate the interpretation of NDE images using deep learning and natural
language processing (NLP). A
Vision-and-
Language Pretraining (VLP) strategy is developed to help the model learn how to connect visual features with meaningful
language. Basically, we built a large NDE image
dataset, trained the model using annotated examples, and then evaluated how well it performed using BLEU scores to compare its output to expert written descriptions. So, the system combines a ResNet50 model to extract important features from the images and a GPT2
language model to turn those features into natural sounding text. Even though the accuracy of the model has been low the generated caption results have been solid so far, the captions were shorter but mentioned some important features of images what human experts would say, which shows the model is learning to pick up on key details. Also, a Visual Question Answering (VQA) model is used as part of the system. VQA models are designed to take an image and a question about that image (like Is there a crack? or Where is the defect located?) and generate a useful answer. By adding this layer, the platform will not just describe what it sees, it can also respond to specific questions, making it even more interactive and helpful for inspectors in the field. This whole approach is a big step toward speeding up NDE workflows, reducing human error, and making the technology more accessible.
Read the full abstract ▾
Computer Vision
GATE: Reliability-Gated Gaussian Evidence Fusion for Training-Free Test-Time Adaptation of Vision-Language Models
Pedram MohajerAnsari, Amir Salarpour, Run Wang et al. (+1 more)
Vision-
language models such as CLIP and SigLIP provide strong zero-shot recognition, but their predictions can degrade when deployed on target data that differ from the pretraining distribution. Test-time adaptation offers a practical way to improve robustness without source data or target labels, yet existing methods often rely on either
prompt-side adaptation or image-side target evidence alone. In this work, we introduce GATE, a training-free two-pass transductive test-time adaptation framework that uses the unlabeled target set while keeping the image encoder, text encoder, and
prompt parameters fully frozen. Instead of representing each class with a single prototype, GATE builds two complementary Gaussian sources of evidence in the shared
vision-
language feature space: a text Gaussian estimated from multiple
language descriptions and an image Gaussian estimated from reliable unlabeled target samples. A class-wise reliability gate controls the influence of image-derived pseudo-evidence, and a score-level generalized Product-of-Experts fusion produces a normalized residual correction to the original zero-shot logits. Across fine-grained recognition
datasets, ImageNet-family distribution shifts, multiple CLIP backbones, and SigLIP-B/16, GATE achieves the best average accuracy in every
benchmark/backbone group. It improves zero-shot performance by an average of 5.41 points and outperforms the strongest non-GATE baseline by 1.94 points, demonstrating the benefit of reliability-gated distributional evidence for frozen VLM adaptation.
Read the full abstract ▾
All authors Pedram MohajerAnsari, Amir Salarpour, Run Wang, Mert D. Pesé
Computer Vision
FiLM-GPNet: Geometry-Aware Pseudo-Supervised Phase Restoration with Zero-Shot Generalization for Large Temporal InSAR Stacks
Getnet Demil, Muhammad Farhan Humayun, Tomi Westerlund et al. (+2 more)
The growing availability of dense commercial Synthetic Aperture Radar (SAR) time series enables temporal Interferometric SAR (InSAR) analysis, but fixed classical filters fail under heterogeneous acquisition geometries, degrading phase quality and temporal consistency. We propose FiLM-GPNet, a geometry-conditioned network for wrapped-phase restoration that explicitly adapts to acquisition differences using Feature-wise Linear Modulation (FiLM) and a 7D per-pair geometry descriptor. The model is trained with pseudo-supervision from Goldstein-filtered interferograms and regularized by interferometric physics via triplet-closure consistency, while also estimating per-pixel aleatoric uncertainty. Experiments on three Capella Spotlight stacks from the IEEE GRSS 2026 Data Fusion Contest show that FiLM-GPNet reduces temporal residual by 68% (Hawaii) and 66% (Western Australia) relative to the Goldstein baseline, alongside closure error reductions of 10% and 13%, respectively. In Western Australia, it further improves unwrapping success rate by 7.7 percentage points and Digital Elevation Model (DEM) Normalized Median Absolute Deviation (NMAD) by 31%. The model also shows strong zero-shot generalization to a geographically and geometrically distinct third stack (Los Angeles) without retraining, supporting geometry-conditioned restoration as an effective alternative to fixed classical filtering across heterogeneous stacks.
Read the full abstract ▾
All authors Getnet Demil, Muhammad Farhan Humayun, Tomi Westerlund, Jukka Heikkonen, Mourad Oussalah
Computer Vision
Think, Look, and Revise: Inconsistency-Aware Visual Self-Correction in MLLMs
Yu Cheng, Arushi Goel and Hakan Bilen
Tool-augmented
multimodal reasoning integrates external tools (e.g., object detection, depth estimation) into
multimodal large
language models (MLLMs) to address perceptual bottlenecks in complex visual tasks. However, existing approaches rarely verify tool outputs, limiting their ability to detect and recover from tool failures. We propose ReVISE, a framework that equips MLLMs with verification and dynamic error recovery for tool-augmented
reasoning. ReVISE introduces (1) a curated training
dataset that supervises reflective behaviors, enabling models to validate tool-derived evidence, reformulate queries when visual mismatches arise, and fall back to intrinsic grounding when external tools are unreliable; and (2) a reinforcement learning based targeted rewards that encourage internal reflection and penalize spatial misalignment. Experiments on several
benchmarks demonstrate consistent improvements over existing methods, highlighting the importance of error detection and correction in tool-augmented
multimodal reasoning.
Read the full abstract ▾
Computer Vision
Sketch2Inspire: Structure-Sensitive Evaluation for Product Retrieval
Ge Kong
Early-stage product design
retrieval often requires more than category recognition: designers may need reference examples that match both a short semantic intent and a rough structural cue. Existing product-image resources and generic image–text
retrieval benchmarks rarely separate category
retrieval from within-category structural fit. We present Sketch2Inspire, built from a curated subset of Amazon Berkeley Objects with aligned text queries, edge-based sketch-proxy queries, and fused text–sketch queries. The resource separates broad category-level
retrieval from structure-sensitive within-category
retrieval and includes a human-graded reference protocol for calibration. We evaluate a lightweight reference system based on pretrained CLIP-family encoders, comparing text-only
retrieval, sketch-only
retrieval, weighted late fusion, and text-first reranking without updating model weights. Under broad relevance, late fusion obtains the highest score (nDCG = 0.9962). Under automatic structure-sensitive relevance, late fusion again obtains the highest score (nDCG = 0.7015), exceeding text-only
retrieval (nDCG = 0.5912). In the human-graded results, late fusion obtains the highest nDCG@10 (0.9133), while text-only
retrieval ranks second (0.9030). These results show that the
retrieval gain from
multimodal input depends on how relevance is defined. Sketch2Inspire therefore provides a diagnostic resource for evaluating modality contribution and supports the development of structure-aware product-
retrieval protocols with independent human annotation.
Read the full abstract ▾
Computer Vision
GSPotential: Camera Potential Field for Sparse-View 3D Gaussian Splatting
Zeyuan An, Yanghang Xiao, Zhiying Leng et al. (+2 more)
3D Gaussian Splatting has achieved remarkable success in photorealistic rendering, yet it suffers from severe overfitting and
geometric artifacts in sparse-view scenarios due to the inherent deficiency of photometric supervision. Recent advances have attempted to regularize optimization by incorporating external priors, such as depth, point clouds, or
diffusion models. However, these methods typically overlook the non-uniform distribution of supervision across the viewing space, resulting in limited specificity in prior use and primitive control. In this paper, we propose GSPotential, a framework that quantifies view-space supervision imbalance using a Camera Potential Field. Our key insight is to identify supervision valleys where photometric constraints are most deficient, and use the potential field to guide reconstruction from two complementary aspects. First, we devise a probabilistic spherical sampling strategy that places informative virtual cameras in low-potential regions. Point-cloud renderings from these views then provide targeted
geometric guidance. Second, the same field provides a directional coverage cue for conservative Gaussian updates in weakly covered spatial sectors. Extensive experiments demonstrate that GSPotential achieves high reconstruction fidelity while maintaining competitive training efficiency.
Read the full abstract ▾
All authors Zeyuan An, Yanghang Xiao, Zhiying Leng, Yijun Feng, Xiaohui Liang
Computer Vision
FISICA: A Deployed Service for Plantar-Pressure and Posture Assessment with Ontology-Grounded Recommendation
Juhwan Song, Heejung Kim, Juntae Noh et al. (+5 more)
FISICA is a body-assessment and recommendation service running in production. One standing session with two photographs returns foot-loading measures, posture coordinates, a driven 3D avatar, a visual report, and ranked shoe and exercise candidates. Measurement comes from a purpose-built scale carrying 634 force-sensitive elements on a 1 cm grid and four load
cells, and a rule-based evaluator controls every recommendation while a
language model only explains the stored result. The method contribution is the avatar. Instead of mapping a measured angle onto a rig through a tuned gain, we measure the avatar with the same function used on the subject and solve until the two agree, on a sampling-invariant spinal metric that separated a normal from a kyphotic record by 7.2 degrees against 0.9 degrees for a single-joint formulation. In production, general APIs respond at a 0.023 s median, plantar-pressure analysis at 0.45 s, and recommendation at 2.16 s to 2.26 s with the rule-based portion under one second in every trial. The served keypoint graph reaches 0.960 PCK@0.2 on public data, and the catalog holds 699 shoes with 10,500 typed facts. An approved study supplies the radiographic reference for the validation still ahead.
Read the full abstract ▾
All authors Juhwan Song, Heejung Kim, Juntae Noh, Jonghak Ryu, Huiju Park, Junseong Lee, Dohyeon Ahn, Byungwoo Jo
Computer Vision
GenFirst: Generation Before Reconstruction for Stable End-to-End Latent Generative Modeling
Guangting Zheng, Yiyuan Zhang, Tao Yang et al. (+4 more)
Latent generative models typically follow a two-stage pipeline, training a variational autoencoder for reconstruction and then a generative model on the frozen latent space. Since reconstruction-optimized latents are not necessarily generation-friendly, jointly training both models is an appealing alternative. However, direct end-to-end training remains challenging, as it is prone to latent collapse and faces a generation-reconstruction conflict. We revisit this problem by analyzing how different objectives shape the latent space and identify two key insights. First, the
entropy term in the Kullback-Leibler divergence objective is essential for preventing collapse: reconstruction and prior fitting tend to shrink the posterior, while
entropy preserves non-degenerate latent uncertainty. Second, reconstruction and generation exhibit asymmetric learning dynamics: reconstruction is fast and strongly supervised, whereas generation is slower and harder to optimize. Based on these insights, we achieve the first direct end-to-end training without latent collapse and propose GenFirst, a simple generation-before-reconstruction strategy. The generative objective first shapes the latent space under weak reconstruction pressure, after which reconstruction is progressively strengthened to recover visual details. We validate GenFirst with continuous autoregressive priors with exact likelihoods and SiT priors with implicit likelihoods. With our end-to-end objective and GenFirst, SiT achieves a gFID of 0.97 with CFG and 1.45 without CFG on ImageNet-256, while MMDiT reaches a GenEval score of 0.90 on text-to-image generation. Beyond image generation, we extend the framework to shared visual latents for generation and representation learning, and to continuous unified text-image generation. These results demonstrate the generality of stable end-to-end latent learning across generative priors and modalities.
Read the full abstract ▾
All authors Guangting Zheng, Yiyuan Zhang, Tao Yang, Yunpeng Chen, Rui Zhu, Jiajun Deng, Yanyong Zhang
Computer Vision
Nikolay Safonov, Nikita Gornostaev, Alexandra Dubonos et al. (+1 more)
Video traffic constitutes a significant share of global web traffic. To reduce its volume,
video codecs have been developed and continuously improved. While the industry has achieved substantial progress in traditional
video coding, neural
video codecs (NVCs) have recently emerged as a new approach that applies deep learning to
video compression. This creates new challenges for compression quality assessment, which is essential for the further development and improvement of such codecs. In particular, it is important to evaluate the novel temporal compression paradigms introduced by NVCs. In this work, we present a large-scale subjective
dataset of
videos compressed with both neural and traditional
video codecs. The subjective scores were collected through crowd-sourced pairwise comparisons. The proposed
dataset provides a valuable resource for the development and benchmarking of
video quality metrics tailored to neural
video codecs. The
dataset is available at the following link: https://videoprocessing.github.io/nvc-
dataset-
benchmark
Read the full abstract ▾
All authors Nikolay Safonov, Nikita Gornostaev, Alexandra Dubonos, Dmitriy Vatolin
Computer Vision
Test-Time Scaling for Video Diffusion Models via Diagnosis-Guided Candidate Recycling
Hangzhou He, Lunhao Duan, Shanshan Zhao et al. (+4 more)
Recent
video diffusion models have achieved remarkable generation quality, but high-fidelity results still largely depend on closed-source systems or costly large-scale infrastructure. Test-time scaling (TTS) offers a training-free way to improve lightweight generators by spending additional inference compute, yet existing methods mostly remain within a noise-search paradigm: they sample, select, or perturb denoising trajectories and discard low-scoring candidates after expensive generation. This generate-and-discard process wastes not only computation but also the partial motion, layout, or appearance structure already encoded in recoverable samples. We present GEARS (Guided Editing for Adaptive Recycling Search), a training-free framework that introduces {diagnosis-guided candidate recycling} into
video TTS by turning such candidates into editable priors through a generation-evaluation-editing loop. GEARS consists of two collaborative components. The Stage-Aware Scheduler determines what to repair, when to repair it, and which candidates should be preserved, recycled, or discarded. The Candidate Recycler diagnoses recoverable failures from keyframes and multi-dimensional reward feedback, derives candidate-specific repair
prompts, and repairs the corresponding candidates through
manifold-aware latent SDEdit. The repaired candidates are recycled into the search pool, creating refinement paths beyond standard noise perturbation while preserving useful structure. Under matched NFE budgets, GEARS consistently outperforms existing
video TTS methods on VBench, bringing a 1.3B model to a total score comparable to a 14B counterpart, and ablations verify the necessity of adaptive scheduling, diagnosis-conditioned editing, and
manifold-aware re-denoising. Code is available on GitHub.
Read the full abstract ▾
All authors Hangzhou He, Lunhao Duan, Shanshan Zhao, Kaiwen Li, Qing-Guo Chen, Weihua Luo, Yanye Lu
Computer Vision
Matin Mahmood, Antonio Rueda-Toicen, Mohamed ElBassat et al. (+3 more)
CLIP-like
vision-
language models (VLMs) trained with contrastive objectives learn strong global image-text representations, but their Euclidean
embeddings and global pooling fail to encode relational structure such as part-whole and parent-child relations.
Hyperbolic VLMs address this gap with entailment-based objectives, and text-conditioned variants improve fine-grained
alignment through sentence- and phrase-level queries. However, these two lines of work remain separate:
hyperbolic VLMs use static image and region features, while query-conditioned methods lack hierarchical
geometric structure. We present Hyper3-CLIP, a hierarchy-conditioned
hyperbolic VLM that combines global, local, and global-local contrastive learning with query-conditioned visual pooling. To train the model, we construct lightweight query hierarchies from text, comprising full captions, sentence fragments, localized part descriptions, and extracted phrases. Each query conditions the pooling of visual patches, and the resulting representations support image-text, whole-part, and parent-child entailment losses. Query-conditioned pooling is active only during training. Hyper3-CLIP improves R@5 and R@10
retrieval on COCO and Flickr, as well as multi-label classification on VOC and COCO, while remaining competitive on hierarchy metrics. We also audit zero-shot
prompt sensitivity under fixed
prompt regimes and study the effect of the localized GRIT part budget used during training. Code is available at https://github.com/Hyper3Labs/hyper3-clip.
Read the full abstract ▾
All authors Matin Mahmood, Antonio Rueda-Toicen, Mohamed ElBassat, Seifeldin Elkerdany, Weixing Wang, Gerard de Melo
Computer Vision
AOI-Net: Structural Face AOI-Guided Eye-Gaze Track Representation Learning for Autism Spectrum Disorder Detection
Zhanpei Huang, Binbin Sun, Jialiang Chen et al. (+5 more)
Eye-movement tracking has emerged as a promising non-invasive approach to Autism Spectrum Disorder (ASD) screening, with systematic differences in attentional allocation and revisit behaviors observed during socially interactive tasks. Existing computational methods typically characterize eye-movements using discrete gaze trajectories and fixation events, yielding representations dominated by short-range temporal dynamics and limiting models that primarily emphasize long-range dependencies. Meanwhile, gaze behavior is naturally organized across semantically meaningful Areas of Interest (AOIs), whose
attention allocation and transitions provide important structural cues, yet their relationships are rarely modeled explicitly. To address these limitations, we propose a structural face AOI-guided Eye-Gaze Track Network (AOI-Net) that jointly models short-term temporal dynamics and AOI-level structural organization. A network gating mechanism adaptively integrates the complementary temporal and structural representations according to their contributions to gaze-behavior characterization. To mitigate the pronounced class imbalance commonly encountered between individuals with ASD and Typically Developing (TD) participants in clinical
datasets, class-distribution-aware learning is further employed to facilitate discriminative
embedding learning under skewed class distributions. Experiments on a unique and large-scale clinical eye-tracking database comprising eight stimulus subsets and more than 1,300 participants show that AOI-Net consistently outperforms state-of-the-art methods. The proposed framework also enables interpretable gaze-behavior modeling and provides a practical basis for scalable AI-driven ASD screening in real-world healthcare. The code is available at https://github.com/Zhanpei-ai/CIM-AOI-Net/tree/main/Code
Read the full abstract ▾
All authors Zhanpei Huang, Binbin Sun, Jialiang Chen, Yiou Wang, Taochen Chen, Yuzhu Ji, Yiqun Zhang, Yiu-Ming Cheung
Computer Vision
PERSIST: Persistent-State Discrimination for Shot Boundary Detection
Tingyu Lin, Christian Stippel, Armin Dadras et al. (+4 more)
Shot boundary detection (SBD) is widely treated as the localisation of local visual discontinuities, yet many false positives such as hand-held shake, illumination flicker, motion blur, occlusion, and damaged archival material produce equally sharp local change without introducing a new shot. We reformulate SBD as boundary semantic discrimination: a frame is favoured as a boundary only when its local change evidence is accompanied by a persistent update of the
video's latent temporal state, rather than a transient excursion that returns to the surrounding trend. This persistence test is operationalised with a continuous latent state from a FiLM-conditioned sinusoidal representation network and a structured discriminator that combines three semantic cues, local change, transient impulse, and return-to-trend, into a single interpretable per-frame signal over a dual-rate temporal backbone. The resulting framework, PERSIST, turns every decision into an inspectable one: the persistence criterion is trained into the classifier, its per-frame effect stays readable from the gate triple, and its learned latent state is measurably boundary-discriminative. On a 2,727-
video per-subtype diagnostic it removes 33-80% of flash, text-overlay, and archival false positives relative to an identically trained cue detector, and at matched true-transition recall it roughly halves TransNetV2's pseudo-event false positives on that diagnostic and cuts its false positives on ClipShots footage by about a quarter, while preserving recall. It does so while reaching parity with the strongest public detector across online, broadcast, short-form, and historical-archive transfer evaluations, under markedly stricter training: it learns from ClipShots real transitions only, whereas the anchor draws on additional corpora whose transitions are 85% synthetic. Code is available at https://github.com/linty5/PERSIST.
Read the full abstract ▾
All authors Tingyu Lin, Christian Stippel, Armin Dadras, Jakob Zenzmaier, Florian Kleber, Wolfgang Aigner, Robert Sablatnig
Computer Vision
3D-MRL: Nested Multimodal 3D Representations via Matryoshka Representation Learning
Márcus Lobo, Vitor Matias, Jeová Farias et al. (+1 more)
Vision-
Language Models align point clouds with image and text
embeddings, enabling zero-shot recognition,
retrieval, and open-vocabulary understanding of 3D shapes. Existing
multimodal 3D pre-training methods produce fixed-dimensional
embeddings, requiring separate models for different computational budgets. We propose 3D Matryoshka Representation Learning (3D-MRL), a
multimodal 3D pre-training framework based on Matryoshka Representation Learning. 3D-MRL learns nested 3D representations by aligning point clouds with frozen CLIP image and text
embeddings while applying contrastive supervision across multiple
embedding dimensions. The Matryoshka objective is applied only to the 3D encoder, allowing a single model to produce representations at different dimensionalities without retraining. Experiments on the Objaverse-LVIS, ModelNet40, and ScanNet
datasets show that 3D-MRL achieves competitive performance on zero-shot and few-shot 3D recognition tasks. In addition, the learned representations support
retrieval across different
embedding dimensions within a single model. On Objaverse-LVIS, 3D-MRL improves Top-1 accuracy from 46.8% to 50.9%.
Retrieval experiments further show that different
embedding dimensions yield varying levels of semantic and
geometric specificity.
Read the full abstract ▾
All authors Márcus Lobo, Vitor Matias, Jeová Farias, Moacir Ponti
Computer Vision
Eduard Zamfir, Christian Reisswig, Zongwei Wu et al. (+2 more)
Natural images concentrate their detail in a small fraction of the frame, yet
diffusion models spend a full
token on every patch, in every layer and at every timestep. The waste is largest in pixel-space models, with no autoencoder to absorb low-level redundancy first. Probing a pretrained pixel text-to-image
transformer, we find its middle-block
tokens redundant wherever the image is flat. The redundancy occupies connected, content-shaped regions, and exploiting it requires
tokens with the same geometry. Cutting a
Hilbert ordering of the patches provides them. Consecutive positions are always image neighbours, so any contiguous run is a connected region whose size and shape follow the content, and grouping in two dimensions becomes a cut in one. Existing reductions each lose part of this. Similarity merging scatters its groups, latent bottlenecks discard position, and skipping deletes what it should summarize. We cut where the model's features change most and pool each run into one region
token. Our Region
Token Interface (\method{}) adapts a
diffusion model to these
tokens, with the region count drawn at random during fine-tuning so one checkpoint serves every budget. \method{} leads prior reduction methods at matched budgets, matches dense quality at $2.0\times$ the speed, and stays close at $2.6\times$. The code and models are open-sourced at https://eduardzamfir.github.io/rti
Read the full abstract ▾
All authors Eduard Zamfir, Christian Reisswig, Zongwei Wu, Yongqin Xian, Radu Timofte
Computer Vision
RAGDiffusion++: From Macro-Retrieval to Micro-Fidelity Alignment for Garment Generation
Yuhan Li, Xianfeng Tan, Fangao Zeng et al. (+6 more)
Standard clothing asset generation—restoring forward-facing flat-lay garment images from diverse real-world contexts—holds immense commercial value yet demands both macroscopic topological accuracy and microscopic physical fidelity. Although our previous work RAGDiffusion effectively eradicated large-scale structural
hallucinations via
retrieval-augmented macro-constraints, achieving industrial-grade micro-texture realism remains an unsolved bottleneck. We formally identify this limitation as High-Frequency Trajectory Collapse: supervised fine-tuning (SFT) converges to the conditional mean of the training distribution, which is dominated by smooth, low-frequency textures, causing high-frequency patterns (e.g., fabric weaves, intricate logos) to become nearly un-sampleable. Naively applying Reinforcement Learning (RL) post-training further triggers Artifact Hacking, where models exploit semantic biases in generic reward models by generating deceptive checkerboard noise. Our key insight is that RL can fundamentally reshape the sampling distribution of flow models—elevating the probability of high-fidelity trajectories under accurate reward guidance—while
adversarial regularization prevents exploitation of reward blind spots. Realizing this principle requires three prerequisites: (i)inherent capacity, established through a 27,725-pair high-complexity garment
dataset (STGarment-Plus) and a Dual-Image-Stream FLUX architecture upgrade; (ii)perceptive reward, provided by a novel attribute-aware reward model (Garment-RM) trained on 500K images via fine-grained contrastive learning, achieving 84.67% human preference accuracy; and (iii)hacking prevention, enforced by our
Adversarial-Regularized GRPO (AR-GRPO) strategy that integrates a dynamic discriminator into the RL sampling trajectory to penalize artifacts while enriching authentic high-frequency details.
Read the full abstract ▾
All authors Yuhan Li, Xianfeng Tan, Fangao Zeng, Wenxiang Shang, Pipei Huang, Hao Zhou, Zhiyu Jin, Wenjun Zhang, Bingbing Ni
Computer Vision
LightFuse: Relightable Interactive Gaussian Scene Reconstruction via Multi-Scan Fusion and 2D Gaussian Ray Tracing
Haonan Zhou, Gaoxiang Linghu, Youlin Jia et al. (+5 more)
Relightable interactive scene reconstruction aims to build an editable 3D model from scans of different object arrangements and render new layouts under novel illumination. Existing methods either bake lighting into appearance or recover material and illumination only for fixed scenes, leaving edited layouts with inconsistent shadows and indirect lighting. We present LightFuse, a 2D Gaussian framework that extends interactive scene reconstruction with explicit material-illumination decomposition and physically based relighting. LightFuse first fuses observations across states to reconstruct a shared background and movable objects. It then conducts ray-tracing-oriented geometry refinement to produce more complete and consistent surfaces. On the refined geometry, staged training with differentiable one-bounce ray tracing separates shared metallic–roughness material from state-specific environment lighting. The resulting scene supports object rearrangement, material editing, and relighting, while ray tracing recomputes appearance after each interaction. Experiments across synthetic scenes demonstrate state-of-the-art relighting quality, outperforming the strongest baseline by +9.74\,dB PSNR and +0.121 SSIM on average. Project page: https://zhn202.github.io/LightFuse/
Read the full abstract ▾
All authors Haonan Zhou, Gaoxiang Linghu, Youlin Jia, Hongyu Cui, Kewei Wei, Kaiyue Zhou, Bruce X.B. Yu, Gaoang Wang
Computer Vision
Learning to Ground Before Reading: Unified PCB Engineering Drawing Parsing with Compact Vision-Language Models
Jinghao Liu, Xingrun Liu, Gengchen Sun et al. (+3 more)
PCB engineering drawings mix sparse graphics, dense tables, and text whose meaning depends on page position. Localizing the regions and sending crops to specialized recognizers are determined as the methods for most parsers, so missed regions cannot be recovered downstream. We train a compact VLM to read the full page and get a sequence of region classes, normalized boxes, and text or HTML content. Bounding boxes are converted to coordinate
tokens for supervision. Inference uses no detector or crop parser. The joint target is difficult to optimize because class and box
tokens are sparse relative to the much longer content sequences. Our localization-first curriculum learns the class-box format before adding content targets with content-aware resampling. On the fixed validation split of the Engineering Drawing
Dataset (ED
dataset), Localization-First improves strict localization F1 by 0.0955 over joint training (paired image-bootstrap 95% interval: [0.0350, 0.1572]). G-Unified has the lowest NED, highest
cell F1, and only nonzero exact-match score. It provides a detector-free baseline for full-page PCB drawing parsing.
Read the full abstract ▾
All authors Jinghao Liu, Xingrun Liu, Gengchen Sun, Han Xiao, Xingyu Chen, Yuhui Deng
Computer Vision
QCell: Recombining and Aligning Cell Queries for Overlapping Instance Segmentation
Yaroslav Prytula, Anton Popov and Dmytro Fishman
Instance
segmentation of overlapping
cells in microscopy remains challenging due to semi-transparent structures that produce weak boundaries and mixed visual evidence in overlap regions. Existing methods address this through local regions of interest or shape priors but lack global
reasoning across overlapping objects. We present QCell, a novel query-based model that de-overlaps
cell instances in microscopy scenes. Our approach combines (i) an instance recombination module that decomposes and recombines query representations in latent space, enabling the model to reason about complete object structure under overlap, and (ii) a contrastive query
alignment objective that combines distinctive instance feature learning and separation of overlapping
cell queries. We additionally introduce a new Organoid
dataset benchmark for overlapping
cell segmentation. We show that QCell outperforms state-of-the-art methods across multiple
benchmarks, achieving +2.2 AP and +2.7 AJI on ISBI2014. Code is available at https://github.com/SlavkoPrytula/QCell
Read the full abstract ▾
Computer Vision · Cross-listed from eess.IV
The MYOSAIQ Challenge: Myocardial Segmentation with Automated Infarct Quantification
Olivier Bernard, William A. Romero R., Cyprien Bouton et al. (+24 more)
Late gadolinium enhancement (LGE) cardiac
magnetic resonance (MR) imaging is the modality of choice to assess myocardial infarction (MI) lesions. Nowadays MI volume quantification is not performed routinely in clinical practice. Numerous deep learning (DL) methods have been developed to automate the
segmentation of the myocardium and infarct regions. However, most studies rely on relatively small
datasets which typically undergo pre-processing steps to standardize images and focus on a specific phase of myocardial infarction following reperfusion therapy. These limitations have impeded the development of models that are generalizable across diverse conditions and thus suitable for routine clinical use. To advance research and establish
benchmarks in generalizable learning for myocardial infarct quantification, this paper presents findings from the Myocardial
Segmentation with Automated Infarct Quantification (MYOSAIQ) challenge. The
dataset set up for the challenge combines 439 CMR volumes from two multicenter clinical trials, with representative data acquired in acute and chronic phases after acute MI. Data were acquired in 16 centers using MRI scanners from three different vendors. Six teams participated until the end of the challenge, employing various baseline models, data augmentation techniques, and confidence strategies. To enhance the significance of this study, we compare the challengers' results with those of fine-tuned foundation models. Our results indicate that well-designed UNet-based techniques outperform fully automatic foundation models for LGE MR
segmentation. While the best methods achieve high-quality and stable delineations of the left ventricle and myocardium under various conditions, they remain improvable in accurately segmenting infarct regions.
Read the full abstract ▾
All authors Olivier Bernard, William A. Romero R., Cyprien Bouton, Celia Goujat, Hang Jung Ling, Pierre-Marc Jodoin, Fumin Guo, Calder Sheagren, Graham Wright, Abdul Qayyum, Moona Mazher, Steven A. Niederer, Hairui Wang, Xiaomei Wu, Franz Thaler, Gernot Plank, Martin Urschler, Ricardo M. Rosales, Esther Pueyo, Nicolas Duchateau, Frederic Cervenansky, Patrick Clarysse, Loic Belle, Thomas Bochaton, Nathan Mewton, Magalie Viallon, Pierre Croisille
Computer Vision
DARD: Zero-Shot Degradation-Aware Retinex-Guided Diffusion for Low-Light Image Enhancement
Wenjie Cai, Yuezhe Yang, Jianyang Xia et al. (+2 more)
Existing
diffusion-based enhancement methods provide strong generative capability for low-light image enhancement (LLIE), yet they either rely on paired supervision or lack reliable scene constraints in zero-shot settings, often leading to structural inconsistency and color drift. Motivated by conventional Retinex models, which offer physically interpretable priors that can serve as reliable scene constraints yet struggle with mixed degradations in real-world scenarios, we propose DARD, a zero-shot Degradation-Aware Retinex-guided
Diffusion framework for LLIE. DARD first extracts image-specific physical priors from the degraded input through a test-time degradation-aware Retinex decomposition, thereby providing reliable structural guidance for zero-shot restoration. It then injects these priors into reverse
diffusion through a timestep-adaptive frequency fusion strategy to balance structural anchoring and detail generation. Finally, a guided reverse refinement process with physical consistency and Contrastive
Language-Image Pre-training (CLIP)-based semantic guidance is introduced to suppress structural artifacts and semantic drift during sampling. Extensive experiments show that DARD achieves strong distortion and perceptual performance and consistently outperforms existing zero-shot baselines across multiple real-world low-light
benchmarks. To further validate the practical utility of our method for downstream applications, we evaluated its impact on semantic
segmentation. Experiments demonstrate that images enhanced by DARD achieve a 28.10% relative improvement in mIoU over AGLLDiff.
Read the full abstract ▾
All authors Wenjie Cai, Yuezhe Yang, Jianyang Xia, Xingbo Dong, Zhe Jin
Computer Vision
AGRICAM: A Track-Mounted Crop Pollination Monitoring Robot
Malika Nisal Ratnayake, Adel N. Toosi, James Cook et al. (+2 more)
Insect pollination is critical for global food production, yet monitoring pollinators at commercial farm scale remains a challenge. Recent advances in computer
vision and deep learning have enabled detailed analysis of pollinator behaviour, but monitoring must trade-off detail against spatial coverage and human or technological resources. This paper presents the Automated Guided
Robot for Insect and Crop Activity Monitoring (AGRICAM), a purpose-built robotic system designed to meet the requirements of large-scale pollination monitoring in protected cropping systems. AGRICAM operates autonomously on low-cost, easily installed track for movement along crop rows, without disrupting farm operations or insect behaviour. The platform integrates two RGB cameras, microclimate sensors, GPS and RFID modules, motion sensors, and 4G cellular network connectivity for data transmission. A web interface enables remote device configuration and scheduling. The system autonomously captures
video and image data of insects' locations and local environmental conditions. These are transferred to the cloud and analysed using computer
vision models to quantify pollinator visitation and spatio-temporal activity variation. We deployed the system on a commercial blueberry farm to demonstrate and test its capability. It successfully mapped insect pollination patterns across 80 m long industrial polytunnels over 30 hours. This data enabled spatial analyses of insect activity we used to confirm a uniform pollinator distribution within polytunnels, as desired by the farm management team. The data also highlighted variation of insect activity associated with time of day and microclimate. AGRICAM therefore has been shown to be a scalable, automated crop pollination monitor that can support data-driven decisions to enhance pollination management, thereby improving crop productivity and food security.
Read the full abstract ▾
All authors Malika Nisal Ratnayake, Adel N. Toosi, James Cook, Romina Rader, Alan Dorin
Computer Vision
Uncertainty-Aware Multimodal Anti-UAV Detection via Evidential Fusion and Conflict-Discounted Belief Aggregation
Sharanda Suttorp, Seyed Sahand Mohammadi Ziabari and Ali Mohammed Mansour Alsahag
Anti-
UAV perception systems must remain reliable when sensor streams degrade under occlusion, fast motion, or modality-specific failure. Existing
multimodal anti-
UAV systems fuse RGB and thermal streams deterministically, without modeling predictive uncertainty, and cannot express doubt when streams disagree. Evidential Deep Learning (EDL) produces calibrated per-class uncertainty in a single forward pass. EDTC already exploits this for thermal-only perception, yet cross-modal evidential fusion remains unaddressed. This paper extends EDTC to
multimodal RGB-Thermal perception via Discounted Belief Fusion (DBF), which converts inter-modal conflict into uncertainty mass before aggregating stream opinions. Bounding boxes are resolved by selecting the lower-uncertainty modality. On the Anti-
UAV benchmark,
multimodal fusion consistently outperforms either single stream (test Acc 0.670 vs. 0.604 IR, 0.598 RGB) at real-time speed (at least 38 FPS). However, DBF is empirically indistinguishable from undiscounted averaging: near-zero inter-modal conflict on this presence-dominated
benchmark leaves the discounting step inert. The fused uncertainty is well-calibrated (ECE 0.057) yet expectedly a weaker localization failure detector than spatial variance (AUROC 0.626 vs. 0.739). The null result is structural: the
benchmark's near-universal presence and vacuous miss-encoding jointly suppress inter-modal conflict, a diagnosis that delimits where conflict-aware fusion provides measurable benefit.
Read the full abstract ▾
Computer Vision
Generalization over Memorization: Generalization-Aware Diffusion Adaptation for Single-Image Multi-View Synthesis
Jie Li, Xingchen Zou and Yuxuan Liang
We present the winning solution to the ACM Multimedia 2026 Grand Challenge on Single-Image Guided Multi-Angle Image Synthesis. It ranks first among 293 registered teams; 56 teams obtained at least one scored submission on the public Phase-A leaderboard. With only 40 training scenes, the challenge requires 26 target views from one RGB model and one forward pass per view; it prohibits explicit geometry, external rendering, chained generation, candidate selection, and post-processing. We identify a critical model-selection failure: shared training and validation scenes make memorization appear as transferable view control. We therefore introduce GoM. Short for Generalization over Memorization, the framework combines scene-disjoint validation, exposure-matched selection, and targeted
diffusion adaptation. Its synthesis model adapts a 4B rectified-flow DiT using rank-32 LoRA, optimizer restarts, late-checkpoint averaging, and VAE decoder tuning. More than 300 offline experiments and 24 online submissions show that validation design and training-trajectory control can matter as much as architecture scale in small-data generative modeling.
Read the full abstract ▾
Computer Vision
Background-Free Objectness Learning for Class-Agnostic Detection
Dania Batool, Liliana Lo Presti, Marco La Cascia et al. (+1 more)
Object detectors are typically trained under closed-set supervision, where unlabeled regions are implicitly treated as background. Under incomplete annotations, this assumption introduces objectness bias: visually valid but unlabeled objects are used as negatives, tying objectness to the annotated taxonomy rather than generic object structure. This limitation is particularly problematic for class-agnostic and open-world detection. This paper proposes Background-Free Objectness Learning (B-FOR), a dense class-agnostic detection framework that learns objectness without explicit background supervision on unlabeled regions. B-FOR formulates detection as the prediction of dense multi-scale object-center and scale fields, from which object hypotheses emerge as local spatial structures. Supervision is confined to reliable annotated regions through spatially structured soft targets, avoiding foreground-background discrimination. To support decoding from emergent local maxima, the paper further introduces displacement-aware scale fields that model object extent as a spatially varying property of the learned objectness field. Experiments on PASCAL VOC, MS-COCO, and Open Images demonstrate strong generalization to unseen categories and cross-
dataset object distributions. B-FOR improves recall by more than +10 AR points over prior class-agnostic baselines. Ablation studies show that both localized objectness supervision and displacement-aware scale fields are critical for class-agnostic localization under incomplete annotations. Code available at: https://github.com/Daniaawan/B-FOR.
Read the full abstract ▾
All authors Dania Batool, Liliana Lo Presti, Marco La Cascia, Filippo Vella