Computer Vision · Cross-listed from cs.AI
Papers
Fresh from arXiv, typeset properly. Highlighted words trade on the market.
Saturday 4 October
Humans understand the world through the integration of multiple sensory modalities, enabling them to perceive, reason about, and imagine dynamic physical processes. Inspired by this capability, multimodal foundation models (MFMs) have emerged as powerful tools for multimodal understanding and generation. However, today's MFMs fall short of serving as effective world models. They lack the essential ability such as perform counterfactual reasoning, simulate dynamics, understand the spatiotemporal information, control generated visual outcomes, and perform multifaceted reasoning. We investigates what it takes to bridge the gap between multimodal foundation models and world models. We begin by improving the reasoning capabilities of MFMs through discriminative tasks and equipping MFMs with structured reasoning skills, such as causal inference, counterfactual thinking, and spatiotemporal reasoning, enabling them to go beyond surface correlations and understand deeper relationships within visual and textual data. Next, we explore generative capabilities of multimodal foundation models across both image and video modalities, introducing new frameworks for structured and controllable generation. Our approaches incorporate scene graphs, multimodal conditioning, and multimodal alignment strategies to guide the generation process, ensuring consistency with high-level semantics and fine-grained user intent. We further extend these techniques to controllable 4D generation, enabling interactive, editable, and morphable object synthesis over time and space.
Computer Vision
Mapping Rio de Janeiro's favelas: general-purpose vs. satellite-specific neural networks
While deep learning methods for detecting informal settlements have already been developed, they have not yet fully utilized the potential offered by recent pretrained neural networks. We compare two types of pretrained neural networks for detecting the favelas of Rio de Janeiro: 1. Generic networks pretrained on large diverse datasets of unspecific images, 2. A specialized network pretrained on satellite imagery. While the latter is more specific to the target task, the former has been pretrained on significantly more images. Hence, this research investigates whether task specificity or data volume yields superior performance in urban informal settlement detection.
Read the full abstract
Computer Vision
Person-Centric Annotations of LAION-400M: Auditing Bias and Its Transfer to Models
Vision-language models trained on large-scale multimodal datasets show strong demographic biases, but the role of training data in producing these biases remains unclear. A major barrier has been the lack of demographic annotations in web-scale datasets such as LAION-400M. We address this gap by creating person-centric annotations for the full dataset, including over 276 million bounding boxes, perceived gender and race/ethnicity labels, and automatically generated captions. These annotations are produced through validated automatic labeling pipelines combining object detection, multimodal captioning, and finetuned classifiers. Using them, we uncover demographic imbalances and harmful associations, such as the disproportionate linking of men and individuals perceived as Black or Middle Eastern with crime-related and negative content. We also show that a linear fit predicts 60-70% of gender bias in CLIP and Stable Diffusion from direct co-occurrences in the data. Our resources establish the first large-scale empirical link between dataset composition and downstream model bias. Code is available at https://github.com/ExplainableML/LAION-400M-Person-Centric-Annotations.
Read the full abstract
Computer Vision
Artery-Vein Segmentation from Fundus Images using Deep Learning
Segmenting of clinically important retinal blood vessels into arteries and veins is a prerequisite for retinal vessel analysis. Such analysis can provide potential insights and bio-markers for identifying and diagnosing various retinal eye diseases. Alteration in the regularity and width of the retinal blood vessels can act as an indicator of the health of the vasculature system all over the body. It can help identify patients at high risk of developing vasculature diseases like stroke and myocardial infarction. Over the years, various Deep Learning architectures have been proposed to perform retinal vessel segmentation. Recently, attention mechanisms have been increasingly used in image segmentation tasks. The work proposes a new Deep Learning approach for artery-vein segmentation. The new approach is based on the Attention mechanism that is incorporated into the WNet Deep Learning model, and we call the model as Attention-WNet. The proposed approach has been tested on publicly available datasets such as HRF and DRIVE datasets. The proposed approach has outperformed other state-of-art models available in the literature.
Read the full abstract
Computer Vision · Cross-listed from cs.RO
EmbodiSwap for Zero-Shot Robot Imitation Learning
We introduce EmbodiSwap - a method for producing photorealistic synthetic robot overlays over human video. We employ EmbodiSwap for zero-shot imitation learning, bridging the embodiment gap between in-the-wild ego-centric human video and a target robot embodiment. We train a closed-loop robot manipulation policy over the data produced by EmbodiSwap. We make novel use of V-JEPA as a visual backbone, repurposing V-JEPA from the domain of video understanding to imitation learning over synthetic robot videos. Adoption of V-JEPA outperforms alternative vision backbones more conventionally used within robotics. In real-world tests, our zero-shot trained V-JEPA model achieves an $82\%$ success rate, outperforming a few-shot trained $\pi_0$ network as well as $\pi_0$ trained over data produced by EmbodiSwap. We release (i) code for generating the synthetic robot overlays which takes as input human videos and an arbitrary robot URDF and generates a robot dataset, (ii) the robot dataset we synthesize over EPIC-Kitchens, HOI4D and Ego4D, and (iii) model checkpoints and inference code, to facilitate reproducible research and broader adoption.
Read the full abstract
Computer Vision
Referring Expression Comprehension for Small Objects
Referring expression comprehension (REC) aims to localize the target object described by a natural language expression. Recent advances in vision-language learning have led to significant performance improvements in REC tasks. However, localizing extremely small objects remains a considerable challenge despite its importance in real-world applications such as autonomous driving. To address this issue, we introduce a novel dataset and method for REC targeting small objects. First, we present the small object REC (SOREC) dataset, which consists of 100,000 pairs of referring expressions and corresponding bounding boxes for small objects in driving scenarios. Second, we propose the progressive-iterative zooming adapter (PIZA), an adapter module for parameter-efficient fine-tuning that enables models to progressively zoom in and localize small objects. In a series of experiments, we apply PIZA to GroundingDINO and demonstrate a significant improvement in accuracy on the SOREC dataset. Our dataset, codes and pre-trained models are publicly available on the project page.
Read the full abstract
Computer Vision
SAMSOD: Rethinking SAM Optimization for RGB-T Salient Object Detection
RGB-T salient object detection (SOD) aims to segment attractive objects by combining RGB and thermal infrared images. To enhance performance, the Segment Anything Model has been fine-tuned for this task. However, the imbalance convergence of two modalities and significant gradient difference between high- and low- activations are ignored, thereby leaving room for further performance enhancement. In this paper, we propose a model called SAMSOD, which utilizes unimodal supervision to enhance the learning of non-dominant modality and employs gradient deconfliction to reduce the impact of conflicting gradients on model convergence. The method also leverages two decoupled adapters to separately mask high- and low-activation neurons, emphasizing foreground objects by enhancing background learning. Fundamental experiments on RGB-T SOD benchmark datasets and generalizability experiments on scribble supervised RGB-T SOD, fully supervised RGB-D SOD datasets and full-supervised RGB-D rail surface defect detection all demonstrate the effectiveness of our proposed method.
Read the full abstract
Computer Vision · Cross-listed from q-bio.NC
Model-Guided Microstimulation Steers Primate Visual Behavior
Brain stimulation is a powerful tool for understanding cortical function and holds promise for therapeutic interventions in neuropsychiatric disorders. Initial visual prosthetics apply electric microstimulation to early visual cortex which can evoke percepts of simple symbols such as letters. However, these approaches are fundamentally limited by hardware constraints and the low-level representational properties of this cortical region. In contrast, higher-level visual areas encode more complex object representations and therefore constitute a promising target for stimulation - but determining representational targets that reliably evoke object-level percepts constitutes a major challenge. We here introduce a computational framework to causally model and guide stimulation of high-level cortex, comprising three key components: (1) a perturbation module that translates microstimulation parameters into spatial changes to neural activity, (2) topographic models that capture the spatial organization of cortical neurons and thus enable prototyping of stimulation experiments, and (3) a mapping procedure that links model-optimized stimulation sites back to primate cortex. Applying this framework in two macaque monkeys performing a visual recognition task, model-predicted stimulation experiments produced significant in-vivo changes in perceptual choices. Per-site model predictions and monkey behavior were strongly correlated, underscoring the promise of model-guided stimulation. Image generation further revealed a qualitative similarity between in-silico stimulation of face-selective sites and a patient's report of facephenes. This proof-of-principle establishes a foundation for model-guided microstimulation and points toward next-generation visual prosthetics capable of inducing more complex visual experiences.
Read the full abstract
Computer Vision
A Novel Cloud-Based Diffusion-Guided Hybrid Model for High-Accuracy Accident Detection in Intelligent Transportation Systems
The integration of Diffusion Models into Intelligent Transportation Systems (ITS) is a substantial improvement in the detection of accidents. We present a novel hybrid model integrating guidance classification with diffusion techniques. By leveraging fine-tuned ExceptionNet architecture outputs as input for our proposed diffusion model and processing image tensors as our conditioning, our approach creates a robust classification framework. Our model consists of multiple conditional modules, which aim to modulate the linear projection of inputs using time embeddings and image covariate embeddings, allowing the network to adapt its behavior dynamically throughout the diffusion process. To address the computationally intensive nature of diffusion models, our implementation is cloud-based, enabling scalable and efficient processing. Our strategy overcomes the shortcomings of conventional classification approaches by leveraging diffusion models inherent capacity to effectively understand complicated data distributions. We investigate important diffusion characteristics, such as timestep schedulers, timestep encoding techniques, timestep count, and architectural design changes, using a thorough ablation study, and have conducted a comprehensive evaluation of the proposed model against the baseline models on a publicly available dataset. The proposed diffusion model performs best in image-based accident detection with an accuracy of 97.32%.
Read the full abstract
Computer Vision
MonitorVLM:A Vision Language Framework for Safety Violation Detection in Mining Operations
Industrial accidents, particularly in high-risk domains such as surface and underground mining, are frequently caused by unsafe worker behaviors. Traditional manual inspection remains labor-intensive, error-prone, and insufficient for large-scale, dynamic environments, highlighting the urgent need for intelligent and automated safety monitoring. In this paper, we present MonitorVLM, a novel vision–language framework designed to detect safety violations directly from surveillance video streams. MonitorVLM introduces three key innovations: (1) a domain-specific violation dataset comprising 9,000 vision–question–answer (VQA) samples across 40 high-frequency mining regulations, enriched with augmentation and auxiliary detection cues; (2) a clause filter (CF) module that dynamically selects the Top-$K$ most relevant clauses, reducing inference latency by 13.56% while maintaining accuracy; and (3) a behavior magnifier (BM) module that enhances worker regions to improve fine-grained action recognition, yielding additional gains of 3.45% in precision and 8.62% in recall. Experimental results demonstrate that MonitorVLM significantly outperforms baseline vision–language models, achieving improvements of 22.01% in precision, 34.22% in recall, and 28.37% in F1 score over the 72B unfine-tuned baseline. A lightweight web-based interface further integrates MonitorVLM into practical workflows, enabling automatic violation reporting with video timestamping. This study highlights the potential of multimodal large models to enhance occupational safety monitoring in mining and beyond.
Read the full abstract
Computer Vision · Cross-listed from cs.CL
UNIDOC-BENCH: A Unified Benchmark for Document-Centric Multimodal RAG
Multimodal retrieval-augmented Generation (MM-RAG) is a key approach for applying large language models (LLMs) and agents to real-world knowledge bases, yet current evaluations are fragmented – focusing on either text or images in isolation, or simplified multimodal setup, failing to capture document-centric multimodal use cases. In this paper, we introduce UniDoc-Bench, the first large-scale, realistic benchmark for MM-RAG built from $k$ real-world PDF pages across domains. Our pipeline extracts and links evidence from text, tables, and figures, then generates multimodal QA pairs spanning factual retrieval, comparison, summarization, and logical reasoning queries. To ensure reliability, all of QA pairs are validated by multiple human annotators and expert adjudication. UniDoc-Bench supports apples-to-apples comparison across four paradigms: 1) text-only, 2) image-only, 3) multimodal text-image fusion and 4) multimodal joint retrieval – under a unified protocol with standardized candidate pools, prompts, and evaluation metrics. UniDoc-Bench can also be used to evaluate Visual Question Answering (VQA) tasks. Our experiments show that multimodal text-image fusion RAG systems consistently outperform both unimodal and jointly multimodal embedding-based retrieval, indicating that neither text nor images alone are sufficient and that current multimodal embeddings remain inadequate. Beyond benchmarking, our analysis reveals when and how visual context complements textual evidence, uncovers systematic failure modes, and offers actionable guidance for developing more robust MM-RAG pipelines.
Read the full abstract
Computer Vision
Diffusion-Classifier Synergy: Reward-Aligned Learning via Mutual Boosting Loop for FSCIL
Few-Shot Class-Incremental Learning (FSCIL) challenges models to sequentially learn new classes from minimal examples without forgetting prior knowledge, a task complicated by the stability-plasticity dilemma and data scarcity. Current FSCIL methods often struggle with generalization due to their reliance on limited datasets. While diffusion models offer a path for data augmentation, their direct application can lead to semantic misalignment or ineffective guidance. This paper introduces Diffusion-Classifier Synergy (DCS), a novel framework that establishes a mutual boosting loop between diffusion model and FSCIL classifier. DCS utilizes a reward-aligned learning strategy, where a dynamic, multi-faceted reward function derived from the classifier's state directs the diffusion model. This reward system operates at two levels: the feature level ensures semantic coherence and diversity using prototype-anchored maximum mean discrepancy and dimension-wise variance matching, while the logits level promotes exploratory image generation and enhances inter-class discriminability through confidence recalibration and cross-session confusion-aware mechanisms. This co-evolutionary process, where generated images refine the classifier and an improved classifier state yields better reward signals, demonstrably achieves state-of-the-art performance on FSCIL benchmarks, significantly enhancing both knowledge retention and new class learning.
Read the full abstract
Computer Vision
Unsupervised Transformer Pre-Training for Images: Self-Distillation, Mean Teachers, and Random Crops
Recent advances in self-supervised learning (SSL) have made it possible to learn general-purpose visual features that capture both the high-level semantics and the fine-grained spatial structure of images. Most notably, the recent DINOv2 has established a new state of the art by surpassing weakly supervised methods (WSL) like OpenCLIP on most benchmarks. In this survey, we examine the core ideas behind its approach, multi-crop view augmentation and self-distillation with a mean teacher, and trace their development in previous work. We then compare the performance of DINO and DINOv2 with other SSL and WSL methods across various downstream tasks, and highlight some remarkable emergent properties of their learned features with transformer backbones. We conclude by briefly discussing DINOv2's limitations, its impact, and future research directions.
Read the full abstract
Computer Vision
Exploring the Hierarchical Reasoning Model for Small Natural-Image Classification Without Augmentation
This paper asks whether the Hierarchical Reasoning Model (HRM) with the two Transformer-style modules $(f_L,f_H)$, one step (DEQ-style) training, deep supervision, Rotary Position Embeddings, and RMSNorm can serve as a practical image classifier. It is evaluated on MNIST, CIFAR-10, and CIFAR-100 under a deliberately raw regime: no data augmentation, identical optimizer family with one-epoch warmup then cosine-floor decay, and label smoothing. HRM optimizes stably and performs well on MNIST ($\approx 98\%$ test accuracy), but on small natural images it overfits and generalizes poorly: on CIFAR-10, HRM reaches 65.0% after 25 epochs, whereas a two-stage Conv–BN–ReLU baseline attains 77.2% while training $\sim 30\times$ faster per epoch; on CIFAR-100, HRM achieves only 29.7% test accuracy despite 91.5% train accuracy, while the same CNN reaches 45.3% test with 50.5% train accuracy. Loss traces and error analyses indicate healthy optimization but insufficient image-specific inductive bias for HRM in this regime. It is concluded that, for small-resolution image classification without augmentation, HRM is not competitive with even simple convolutional architectures as the HRM currently exist but this does not exclude possibilities that modifications to the model may allow it to improve greatly.
Read the full abstract
Computer Vision
A Hybrid Co-Finetuning Approach for Visual Bug Detection in Video Games
Manual identification of visual bugs in video games is a resource-intensive and costly process, often demanding specialized domain knowledge. While supervised visual bug detection models offer a promising solution, their reliance on extensive labeled datasets presents a significant challenge due to the infrequent occurrence of such bugs. To overcome this limitation, we propose a hybrid Co-FineTuning (CFT) method that effectively integrates both labeled and unlabeled data. Our approach leverages labeled samples from the target game and diverse co-domain games, additionally incorporating unlabeled data to enhance feature representation learning. This strategy maximizes the utility of all available data, substantially reducing the dependency on labeled examples from the specific target game. The developed framework demonstrates enhanced scalability and adaptability, facilitating efficient visual bug detection across various game titles. Our experimental results show the robustness of the proposed method for game visual bug detection, exhibiting superior performance compared to conventional baselines across multiple gaming environments. Furthermore, CFT maintains competitive performance even when trained with only 50% of the labeled data from the target game.
Read the full abstract
Computer Vision
FrameOracle: Learning What to See and How Much to See in Videos
Vision-language models (VLMs) advance video understanding but operate under tight computational budgets, making performance dependent on selecting a small, high-quality subset of frames. Existing frame sampling strategies, such as uniform or fixed-budget selection, fail to adapt to variations in content density or task complexity. To address this, we present FrameOracle, a lightweight, plug-and-play module that predicts both (1) which frames are most relevant to a given query and (2) how many frames are needed. FrameOracle is trained via a curriculum that progresses from weak proxy signals, such as cross-modal similarity, to stronger supervision with FrameOracle-41K, the first large-scale VideoQA dataset with validated keyframe annotations specifying minimal sufficient frames per question. Extensive experiments across five VLMs and six benchmarks show that FrameOracle reduces 16-frame inputs to an average of 10.4 frames without accuracy loss. When starting from 64-frame candidates, it reduces inputs to 13.9 frames on average while improving accuracy by 1.5%, achieving state-of-the-art efficiency-accuracy trade-offs for scalable video understanding.
Read the full abstract
Friday 3 October
Computer Vision
Beyond CNNs: Efficient Fine-Tuning of Multi-Modal LLMs for Object Detection on Low-Data Regimes
The field of object detection and understanding is rapidly evolving, driven by advances in both traditional CNN-based models and emerging multi-modal large language models (LLMs). While CNNs like ResNet and YOLO remain highly effective for image-based tasks, recent transformer-based LLMs introduce new capabilities such as dynamic context reasoning, language-guided prompts, and holistic scene understanding. However, when used out-of-the-box, the full potential of LLMs remains underexploited, often resulting in suboptimal performance on specialized visual tasks. In this work, we conduct a comprehensive comparison of fine-tuned traditional CNNs, zero-shot pre-trained multi-modal LLMs, and fine-tuned multi-modal LLMs on the challenging task of artificial text overlay detection in images. A key contribution of our study is demonstrating that LLMs can be effectively fine-tuned on very limited data (fewer than 1,000 images) to achieve up to 36% accuracy improvement, matching or surpassing CNN-based baselines that typically require orders of magnitude more data. By exploring how language-guided models can be adapted for precise visual understanding with minimal supervision, our work contributes to the broader effort of bridging vision and language, offering novel insights into efficient cross-modal learning strategies. These findings highlight the adaptability and data efficiency of LLM-based approaches for real-world object detection tasks and provide actionable guidance for applying multi-modal transformers in low-resource visual environments. To support continued progress in this area, we have made the code used to fine-tune the models available in our GitHub, enabling future improvements and reuse in related applications.
Read the full abstract
Computer Vision
Physics Knowledge in Frontier Models: A Diagnostic Study of Failure Modes
While recent Vision-Language Models (VLMs) have achieved impressive progress, it remains difficult to determine why they succeed or fail on complex reasoning tasks. Traditional benchmarks evaluate what models can answer correctly, not why they succeed or fail. In this work, we perform a failure-mode analysis of six frontier VLMs on three physics-based benchmarks - Physion, Physion++, and CLEVRER - by introducing custom subtests (for Physion and Physion++) and an integration of existing benchmark categories (for CLEVRER) to factor benchmark performance into distinct, testable capabilities. These subtests isolate perception (object, color, and occlusion recognition) and physics understanding (motion prediction and spatial reasoning), enabling us to test whether models attend to the correct entities and dynamics underlying their answers. Counterintuitively, subtest mastery correlates only weakly with benchmark accuracy: models often answer correctly without grounding in perception or physics. This suggests that current VLMs sometimes achieve benchmark scores for the wrong reasons, underscoring the need for diagnostics that expose hidden failure modes beyond aggregate metrics.
Read the full abstract
Computer Vision
multimodars: A Rust-powered toolkit for multi-modality cardiac image fusion and registration
Combining complementary imaging modalities is critical to build reliable 3D coronary models: intravascular imaging gives sub-millimetre resolution but limited whole-vessel context, while CCTA supplies 3D geometry but suffers from limited spatial resolution and artefacts (e.g., blooming). Prior work demonstrated intravascular/CCTA fusion, yet no open, flexible toolkit is tailored for multi-state analysis (rest/stress, pre-/post-stenting) while offering deterministic behaviour, high performance, and easy pipeline integration. multimodars addresses this gap with deterministic alignment algorithms, a compact NumPy-centred data model, and an optimised Rust backend suitable for scalable, reproducible experiments. The package accepts CSV/NumPy inputs including data formats produced by the AIVUS-CAA software
Read the full abstract
Computer Vision
Uncertainty Quantification In Surface Landmines and UXO Classification Using MC Dropout
Detecting surface landmines and unexploded ordnances (UXOs) using deep learning has shown promise in humanitarian demining. However, deterministic neural networks can be vulnerable to noisy conditions and adversarial attacks, leading to missed detection or misclassification. This study introduces the idea of uncertainty quantification through Monte Carlo (MC) Dropout, integrated into a fine-tuned ResNet-50 architecture for surface landmine and UXO classification, which was tested on a simulated dataset. Integrating the MC Dropout approach helps quantify epistemic uncertainty, providing an additional metric for prediction reliability, which could be helpful to make more informed decisions in demining operations. Experimental results on clean, adversarially perturbed, and noisy test images demonstrate the model's ability to flag unreliable predictions under challenging conditions. This proof-of-concept study highlights the need for uncertainty quantification in demining, raises awareness about the vulnerability of existing neural networks in demining to adversarial threats, and emphasizes the importance of developing more robust and reliable models for practical applications.
Read the full abstract
Computer Vision
DiT-VTON: Diffusion Transformer Framework for Unified Multi-Category Virtual Try-On and Virtual Try-All with Integrated Image Editing
The rapid growth of e-commerce has intensified the demand for Virtual Try-On (VTO) technologies, enabling customers to realistically visualize products overlaid on their own images. Despite recent advances, existing VTO models face challenges with fine-grained detail preservation, robustness to real-world imagery, efficient sampling, image editing capabilities, and generalization across diverse product categories. In this paper, we present DiT-VTON, a novel VTO framework that leverages a Diffusion Transformer (DiT), renowned for its performance on text-conditioned image generation, adapted here for the image-conditioned VTO task. We systematically explore multiple DiT configurations, including in-context token concatenation, channel concatenation, and ControlNet integration, to determine the best setup for VTO image conditioning. To enhance robustness, we train the model on an expanded dataset encompassing varied backgrounds, unstructured references, and non-garment categories, demonstrating the benefits of data scaling for VTO adaptability. DiT-VTON also redefines the VTO task beyond garment try-on, offering a versatile Virtual Try-All (VTA) solution capable of handling a wide range of product categories and supporting advanced image editing functionalities such as pose preservation, localized editing, texture transfer, and object-level customization. Experimental results show that our model surpasses state-of-the-art methods on VITON-HD, achieving superior detail preservation and robustness without reliance on additional condition encoders. It also outperforms models with VTA and image editing capabilities on a diverse dataset spanning thousands of product categories.
Read the full abstract
Computer Vision · Cross-listed from cs.LG
Efficient Test-Time Scaling for Small Vision-Language Models
Small Vision-Language Models (VLMs) provide a computationally efficient alternative to larger models, at the cost of weaker generalization abilities and downstream task performance. These shortcomings could be addressed by test-time scaling techniques, but existing methods are typically computationally demanding, contradicting the resource-efficient design goals of small models. To address these limitations, we propose two novel and efficient test-time scaling strategies that leverage the model-internal features rather than external supervision: (i) Test-Time Augmentation (TTAug), which generates multiple augmented inputs and aggregates outputs at the token level without parameter updates, and (ii) Test-Time Adaptation (TTAdapt), which adapts model parameters during inference using consensus-based pseudolabels from TTAug. Through extensive experiments across nine benchmarks, we demonstrate consistent performance improvements while maintaining computational efficiency suitable for resource-constrained environments. The generality of our approach is demonstrated both within models at different scales and across different VLMs without additional tuning.
Read the full abstract
Computer Vision
Evaluating OCR performance on food packaging labels in South Africa
This study evaluates four open-source Optical Character Recognition (OCR) systems which are Tesseract, EasyOCR, PaddleOCR, and TrOCR on real world food packaging images. The aim is to assess their ability to extract ingredient lists and nutrition facts panels. Accurate OCR for packaging is important for compliance and nutrition monitoring but is challenging due to multilingual text, dense layouts, varied fonts, glare, and curved surfaces. A dataset of 231 products (1,628 images) was processed by all four models to assess speed and coverage, and a ground truth subset of 113 images (60 products) was created for accuracy evaluation. Metrics include Character Error Rate (CER), Word Error Rate (WER), BLEU, ROUGE-L, F1, coverage, and execution time. On the ground truth subset, Tesseract achieved the lowest CER (0.912) and the highest BLEU (0.245). EasyOCR provided a good balance between accuracy and multilingual support. PaddleOCR achieved near complete coverage but was slower because it ran on CPU only due to GPU incompatibility, and TrOCR produced the weakest results despite GPU acceleration. These results provide a packaging-specific benchmark, establish a baseline, and highlight directions for layout-aware methods and text localization.
Read the full abstract
Computer Vision · Cross-listed from cs.LG
Longitudinal Flow Matching for Trajectory Modeling
Generative models for sequential data often struggle with sparsely sampled and high-dimensional trajectories, typically reducing the learning of dynamics to pairwise transitions. We propose Interpolative Multi-Marginal Flow Matching (IMMFM), a framework that learns continuous stochastic dynamics jointly consistent with multiple observed time points. IMMFM employs a piecewise-quadratic interpolation path as a smooth target for flow matching and jointly optimizes drift and a data-driven diffusion coefficient, supported by a theoretical condition for stable learning. This design captures intrinsic stochasticity, handles irregular sparse sampling, and yields subject-specific trajectories. Experiments on synthetic benchmarks and real-world longitudinal neuroimaging datasets show that IMMFM outperforms existing methods in both forecasting accuracy and further downstream tasks.
Read the full abstract
Computer Vision · Cross-listed from eess.IV
How We Won BraTS-SSA 2025: Brain Tumor Segmentation in the Sub-Saharan African Population Using Segmentation-Aware Data Augmentation and Model Ensembling
Brain tumors, particularly gliomas, pose significant chall-enges due to their complex growth patterns, infiltrative nature, and the variability in brain structure across individuals, which makes accurate diagnosis and monitoring difficult. Deep learning models have been developed to accurately delineate these tumors. However, most of these models were trained on relatively homogenous high-resource datasets, limiting their robustness when deployed in underserved regions. In this study, we performed segmentation-aware offline data augmentation on the BraTS-Africa dataset to increase the data sample size and diversity to enhance generalization. We further constructed an ensemble of three distinct architectures, MedNeXt, SegMamba, and Residual-Encoder U-Net, to leverage their complementary strengths. Our best-performing model, MedNeXt, was trained on 1000 epochs and achieved the highest average lesion-wise dice and normalized surface distance scores of 0.86 and 0.81 respectively. However, the ensemble model trained for 500 epochs produced the most balanced segmentation performance across the tumour subregions. This work demonstrates that a combination of advanced augmentation and model ensembling can improve segmentation accuracy and robustness on diverse and underrepresented datasets. Code available at: https://github.com/SPARK-Academy-2025/SPARK-2025/tree/main/SPARK2025_BraTs_MODELS/SPARK_NeuroAshanti
Read the full abstract
Computer Vision
Real-Time Assessment of Bystander Situation Awareness in Drone-Assisted First Aid
Rapid naloxone delivery via drones offers a promising solution for responding to opioid overdose emergencies (OOEs), by extending lifesaving interventions to medically untrained bystanders before emergency medical services (EMS) arrive. Recognizing the critical role of bystander situational awareness (SA) in human-autonomy teaming (HAT), we address a key research gap in real-time SA assessment by introducing the Drone-Assisted Naloxone Delivery Simulation Dataset (DANDSD). This pioneering dataset captures HAT during simulated OOEs, where college students without medical training act as bystanders tasked with administering intranasal naloxone to a mock overdose victim. Leveraging this dataset, we propose a video-based real-time SA assessment framework that utilizes graph embeddings and transformer models to assess bystander SA in real time. Our approach integrates visual perception and comprehension cues–such as geometric, kinematic, and interaction graph features–and achieves high-performance SA prediction. It also demonstrates strong temporal segmentation accuracy, outperforming the FINCH baseline by 9% in Mean over Frames (MoF) and 5% in Intersection over Union (IoU). This work supports the development of adaptive drone systems capable of guiding bystanders effectively, ultimately improving emergency response outcomes and saving lives.
Read the full abstract
Computer Vision
GAS-MIL: Group-Aggregative Selection Multi-Instance Learning for Ensemble of Foundation Models in Digital Pathology Image Analysis
Foundation models (FMs) have transformed computational pathology by providing powerful, general-purpose feature extractors. However, adapting and benchmarking individual FMs for specific diagnostic tasks is often time-consuming and resource-intensive, especially given their scale and diversity. To address this challenge, we introduce Group-Aggregative Selection Multi-Instance Learning (GAS-MIL), a flexible ensemble framework that seamlessly integrates features from multiple FMs, preserving their complementary strengths without requiring manual feature selection or extensive task-specific fine-tuning. Across classification tasks in three cancer datasets-prostate (PANDA), ovarian (UBC-OCEAN), and breast (TCGA-BrCa)-GAS-MIL consistently achieves superior or on-par performance relative to individual FMs and established MIL methods, demonstrating its robustness and generalizability. By enabling efficient integration of heterogeneous FMs, GAS-MIL streamlines model deployment for pathology and provides a scalable foundation for future multimodal and precision oncology applications.
Read the full abstract
Computer Vision
Streaming Drag-Oriented Interactive Video Manipulation: Drag Anything, Anytime!
Achieving streaming, fine-grained control over the outputs of autoregressive video diffusion models remains challenging, making it difficult to ensure that they consistently align with user expectations. To bridge this gap, we propose stReaming drag-oriEnted interactiVe vidEo manipuLation (REVEL), a new task that enables users to modify generated videos anytime on anything via fine-grained, interactive drag. Beyond DragVideo and SG-I2V, REVEL unifies drag-style video manipulation as editing and animating video frames with both supporting user-specified translation, deformation, and rotation effects, making drag operations versatile. In resolving REVEL, we observe: i) drag-induced perturbations accumulate in latent space, causing severe latent distribution drift that halts the drag process; ii) streaming drag is easily disturbed by context frames, thereby yielding visually unnatural outcomes. We thus propose a training-free approach, DragStream, comprising: i) an adaptive distribution self-rectification strategy that leverages neighboring frames' statistics to effectively constrain the drift of latent embeddings; ii) a spatial-frequency selective optimization mechanism, allowing the model to fully exploit contextual information while mitigating its interference via selectively propagating visual cues along generation. Our method can be seamlessly integrated into existing autoregressive video diffusion models, and extensive experiments firmly demonstrate the effectiveness of our DragStream.
Read the full abstract
Computer Vision
Unmasking Puppeteers: Leveraging Biometric Leakage to Expose Impersonation in AI-Based Videoconferencing
AI-based talking-head videoconferencing systems reduce bandwidth by sending a compact pose-expression latent and re-synthesizing RGB at the receiver, but this latent can be puppeteered, letting an attacker hijack a victim's likeness in real time. Because every frame is synthetic, deepfake and synthetic video detectors fail outright. To address this security problem, we exploit a key observation: the pose-expression latent inherently contains biometric information of the driving identity. Therefore, we introduce the first biometric leakage defense without ever looking at the reconstructed RGB video: a pose-conditioned, large-margin contrastive encoder that isolates persistent identity cues inside the transmitted latent while cancelling transient pose and expression. A simple cosine test on this disentangled embedding flags illicit identity swaps as the video is rendered. Our experiments on multiple talking-head generation models show that our method consistently outperforms existing puppeteering defenses, operates in real-time, and shows strong generalization to out-of-distribution scenarios.
Read the full abstract
Computer Vision
SketchPlan: Diffusion Based Drone Planning From Human Sketches
We propose SketchPlan, a diffusion-based planner that interprets 2D hand-drawn sketches over depth images to generate 3D flight paths for drone navigation. SketchPlan comprises two components: a SketchAdapter that learns to map the human sketches to projected 2D paths, and DiffPath, a diffusion model that infers 3D trajectories from 2D projections and a first person view depth image. Our model achieves zero-shot sim-to-real transfer, generating accurate and safe flight paths in previously unseen real-world environments. To train the model, we build a synthetic dataset of 32k flight paths using a diverse set of photorealistic 3D Gaussian Splatting scenes. We automatically label the data by computing 2D projections of the 3D flight paths onto the camera plane, and use this to train the DiffPath diffusion model. However, since real human 2D sketches differ significantly from ideal 2D projections, we additionally label 872 of the 3D flight paths with real human sketches and use this to train the SketchAdapter to infer the 2D projection from the human sketch. We demonstrate SketchPlan's effectiveness in both simulated and real-world experiments, and show through ablations that training on a mix of human labeled and auto-labeled data together with a modular design significantly boosts its capabilities to correctly interpret human intent and infer 3D paths. In real-world drone tests, SketchPlan achieved 100% success in low/medium clutter and 40% in unseen high-clutter environments, outperforming key ablations by 20-60% in task completion.