arXiv subjects

Robert Sablatnig

Publications and source records attributed to Robert Sablatnig.

At least 19 recordsLinked to original sources

arXiv2026

Single-Annotation, Multi-Hypothesis Segmentation with Semantic-Spatial Residual Banks

Multi-rater segmentation datasets show that a single image can admit several valid masks, yet most training sets expose only one annotation per image. We study single-annotation multi-hypothesis segmentation: each training image exposes one fixed mask, while the model must return a finite bank that covers held-out human annotations at test time. Our experiments reveal a representation tradeoff. Banks learned directly from images recover variations in local boundaries and extent but lose structural hypotheses, whereas frozen semantic features preserve structural grouping but underrepresent spatial variation. We introduce the Semantic-Spatial Residual Bank (SSRB), which freezes a semantic bank trained with balanced assignments and learns a residual from the image for each hypothesis. Across five medical endpoints, SSRB improves coverage of held-out masks at $K=8$ over a Probabilistic U-Net under the same one-mask constraint. On LIDC and LIDC-hard, it also produces substantially more distinct useful masks. On BSDS, it preserves the semantic bank's performance in grouping regions. Its advantage grows as more masks are returned, showing that residuals learned for corresponding heads improve coverage of local annotation variation while preserving how regions are grouped.

cs.CV↗

arXiv2026

Grounding Image Composition with Label-Conditioned Visual Evidence

Image composition labels such as center, diagonal, or rule of thirds describe visual structure rather than object categories. KU-PCP provides image-level labels and class-specific geometric elements, but does not show which visible regions people associate with each of its nine classes. We introduce KU-PCP Elements (KU-PCPE), a label-conditioned region-evidence benchmark for photographic composition. Given an image and a label already judged applicable, the task is to segment the visible regions that explain why the label applies. KU-PCPE contains 4,093 single-annotator training masks and a 1,327-task expert test split with three masks per image-label task. The annotations also include exploratory segment-versus-line ratings that describe whether region or semantic-guideline evidence better explains the label. A held-out expert reaches .867 Dice against the other experts, while the strongest deployable model reaches .664, a proposal oracle .672, and the best vision-language model (VLM) proposal selector .395. KU-PCPE exposes the gap between recognizing a composition label and grounding the human-aligned visual evidence that makes it plausible in a particular image.

cs.CV↗

arXiv2026

PERSIST: Persistent-State Discrimination for Shot Boundary Detection

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.

cs.CV↗

arXiv2026

Semantically Stable Image Composition Analysis via Saliency and Gradient Vector Flow Fusion

The reliable computational assessment of photographic composition requires features that are discriminative of spatial layout yet robust to semantic content. This paper proposes a low-level representation grounded in the assumption that composition can be understood as the flow of visual attention across geometric structure. We introduce VFCNet, which fuses saliency and edge information into a gradient vector flow (GVF) field. The model computes dual-stream GVF representations, integrates them via attention, and extracts multi-scale flow features with a DINOv3 backbone. VFCNet achieves state-of-the-art performance on the PICD benchmark (CDA-1: 0.683, CDA-2: 0.629), improving by 33.1\% and 36.1\% over the previous best method. We also show that a simple classifier on self-supervised DINOv3 features substantially outperforms more sophisticated, composition-specialized models. Code is available at https://github.com/ADadras/VFCNet

cs.CV↗

arXiv2025

ClapperText: A Benchmark for Text Recognition in Low-Resource Archival Documents

This paper presents ClapperText, a benchmark dataset for handwritten and printed text recognition in visually degraded and low-resource settings. The dataset is derived from 127 World War II-era archival video segments containing clapperboards that record structured production metadata such as date, location, and camera-operator identity. ClapperText includes 9,813 annotated frames and 94,573 word-level text instances, 67% of which are handwritten and 1,566 are partially occluded. Each instance includes transcription, semantic category, text type, and occlusion status, with annotations available as rotated bounding boxes represented as 4-point polygons to support spatially precise OCR applications. Recognizing clapperboard text poses significant challenges, including motion blur, handwriting variation, exposure fluctuations, and cluttered backgrounds, mirroring broader challenges in historical document analysis where structured content appears in degraded, non-standard forms. We provide both full-frame annotations and cropped word images to support downstream tasks. Using a consistent per-video evaluation protocol, we benchmark six representative recognition and seven detection models under zero-shot and fine-tuned conditions. Despite the small training set (18 videos), fine-tuning leads to substantial performance gains, highlighting ClapperText's suitability for few-shot learning scenarios. The dataset offers a realistic and culturally grounded resource for advancing robust OCR and document understanding in low-resource archival contexts. The dataset and evaluation code are available at https://github.com/linty5/ClapperText.

cs.CV↗

arXiv2025

DGME-T: Directional Grid Motion Encoding for Transformer-Based Historical Camera Movement Classification

Camera movement classification (CMC) models trained on contemporary, high-quality footage often degrade when applied to archival film, where noise, missing frames, and low contrast obscure motion cues. We bridge this gap by assembling a unified benchmark that consolidates two modern corpora into four canonical classes and restructures the HISTORIAN collection into five balanced categories. Building on this benchmark, we introduce DGME-T, a lightweight extension to the Video Swin Transformer that injects directional grid motion encoding, derived from optical flow, via a learnable and normalised late-fusion layer. DGME-T raises the backbone's top-1 accuracy from 81.78% to 86.14% and its macro F1 from 82.08% to 87.81% on modern clips, while still improving the demanding World-War-II footage from 83.43% to 84.62% accuracy and from 81.72% to 82.63% macro F1. A cross-domain study further shows that an intermediate fine-tuning stage on modern data increases historical performance by more than five percentage points. These results demonstrate that structured motion priors and transformer representations are complementary and that even a small, carefully calibrated motion head can substantially enhance robustness in degraded film analysis. Related resources are available at https://github.com/linty5/DGME-T.

cs.CV↗

arXiv2025

Camera Movement Classification in Historical Footage: A Comparative Study of Deep Video Models

Camera movement conveys spatial and narrative information essential for understanding video content. While recent camera movement classification (CMC) methods perform well on modern datasets, their generalization to historical footage remains unexplored. This paper presents the first systematic evaluation of deep video CMC models on archival film material. We summarize representative methods and datasets, highlighting differences in model design and label definitions. Five standard video classification models are assessed on the HISTORIAN dataset, which includes expert-annotated World War II footage. The best-performing model, Video Swin Transformer, achieves 80.25% accuracy, showing strong convergence despite limited training data. Our findings highlight the challenges and potential of adapting existing models to low-quality video and motivate future work combining diverse input modalities and temporal architectures.

cs.CV↗

arXiv2025

Few-Shot Connectivity-Aware Text Line Segmentation in Historical Documents

A foundational task for the digital analysis of documents is text line segmentation. However, automating this process with deep learning models is challenging because it requires large, annotated datasets that are often unavailable for historical documents. Additionally, the annotation process is a labor- and cost-intensive task that requires expert knowledge, which makes few-shot learning a promising direction for reducing data requirements. In this work, we demonstrate that small and simple architectures, coupled with a topology-aware loss function, are more accurate and data-efficient than more complex alternatives. We pair a lightweight UNet++ with a connectivity-aware loss, initially developed for neuron morphology, which explicitly penalizes structural errors like line fragmentation and unintended line merges. To increase our limited data, we train on small patches extracted from a mere three annotated pages per manuscript. Our methodology significantly improves upon the current state-of-the-art on the U-DIADS-TL dataset, with a 200% increase in Recognition Accuracy and a 75% increase in Line Intersection over Union. Our method also achieves an F-Measure score on par with or even exceeding that of the competition winner of the DIVA-HisDB baseline detection task, all while requiring only three annotated pages, exemplifying the efficacy of our approach. Our implementation is publicly available at: https://github.com/RafaelSterzinger/acpr_few_shot_hist.

cs.CV↗

arXiv2025

Few-Shot Segmentation of Historical Maps via Linear Probing of Vision Foundation Models

As rich sources of history, maps provide crucial insights into historical changes, yet their diverse visual representations and limited annotated data pose significant challenges for automated processing. We propose a simple yet effective approach for few-shot segmentation of historical maps, leveraging the rich semantic embeddings of large vision foundation models combined with parameter-efficient fine-tuning. Our method outperforms the state-of-the-art on the Siegfried benchmark dataset in vineyard and railway segmentation, achieving +5% and +13% relative improvements in mIoU in 10-shot scenarios and around +20% in the more challenging 5-shot setting. Additionally, it demonstrates strong performance on the ICDAR 2021 competition dataset, attaining a mean PQ of 67.3% for building block segmentation, despite not being optimized for this shape-sensitive metric, underscoring its generalizability. Notably, our approach maintains high performance even in extremely low-data regimes (10- & 5-shot), while requiring only 689k trainable parameters - just 0.21% of the total model size. Our approach enables precise segmentation of diverse historical maps while drastically reducing the need for manual annotations, advancing automated processing and analysis in the field. Our implementation is publicly available at: https://github.com/RafaelSterzinger/few-shot-map-segmentation.

cs.CV↗

arXiv2025

Towards the Influence of Text Quantity on Writer Retrieval

This paper investigates the task of writer retrieval, which identifies documents authored by the same individual within a dataset based on handwriting similarities. While existing datasets and methodologies primarily focus on page level retrieval, we explore the impact of text quantity on writer retrieval performance by evaluating line- and word level retrieval. We examine three state-of-the-art writer retrieval systems, including both handcrafted and deep learning-based approaches, and analyze their performance using varying amounts of text. Our experiments on the CVL and IAM dataset demonstrate that while performance decreases by 20-30% when only one line of text is used as query and gallery, retrieval accuracy remains above 90% of full-page performance when at least four lines are included. We further show that text-dependent retrieval can maintain strong performance in low-text scenarios. Our findings also highlight the limitations of handcrafted features in low-text scenarios, with deep learning-based methods like NetVLAD outperforming traditional VLAD encoding.

cs.CV↗

arXiv2024

Fusing Forces: Deep-Human-Guided Refinement of Segmentation Masks

Etruscan mirrors constitute a significant category in Etruscan art, characterized by elaborate figurative illustrations featured on their backside. A laborious and costly aspect of their analysis and documentation is the task of manually tracing these illustrations. In previous work, a methodology has been proposed to automate this process, involving photometric-stereo scanning in combination with deep neural networks. While achieving quantitative performance akin to an expert annotator, some results still lack qualitative precision and, thus, require annotators for inspection and potential correction, maintaining resource intensity. In response, we propose a deep neural network trained to interactively refine existing annotations based on human guidance. Our human-in-the-loop approach streamlines annotation, achieving equal quality with up to 75% less manual input required. Moreover, during the refinement process, the relative improvement of our methodology over pure manual labeling reaches peak values of up to 26%, attaining drastically better quality quicker. By being tailored to the complex task of segmenting intricate lines, specifically distinguishing it from previous methods, our approach offers drastic improvements in efficacy, transferable to a broad spectrum of applications beyond Etruscan mirrors.

cs.CV↗

arXiv2024

KaiRacters: Character-level-based Writer Retrieval for Greek Papyri

This paper presents a character-based approach for enhancing writer retrieval performance in the context of Greek papyri. Our contribution lies in introducing character-level annotations for frequently used characters, in our case the trigram kai and four additional letters (epsilon, kappa, mu, omega), in Greek texts. We use a state-of-the-art writer retrieval approach based on NetVLAD and compare a character-level-based feature aggregation method against the current default baseline of using small patches located at SIFT keypoint locations for building the page descriptors. We demonstrate that by using only about 15 characters per page, we are able to boost the performance up to 4% mAP (a relative improvement of 11%) on the GRK-120 dataset. Additionally, our qualitative analysis offers insights into the similarity scores of SIFT patches and specific characters. We publish the dataset with character-level annotations, including a quality label and our binarized images for further research.

cs.CV↗

arXiv2024

SAGHOG: Self-Supervised Autoencoder for Generating HOG Features for Writer Retrieval

This paper introduces SAGHOG, a self-supervised pretraining strategy for writer retrieval using HOG features of the binarized input image. Our preprocessing involves the application of the Segment Anything technique to extract handwriting from various datasets, ending up with about 24k documents, followed by training a vision transformer on reconstructing masked patches of the handwriting. SAGHOG is then finetuned by appending NetRVLAD as an encoding layer to the pretrained encoder. Evaluation of our approach on three historical datasets, Historical-WI, HisFrag20, and GRK-Papyri, demonstrates the effectiveness of SAGHOG for writer retrieval. Additionally, we provide ablation studies on our architecture and evaluate un- and supervised finetuning. Notably, on HisFrag20, SAGHOG outperforms related work with a mAP of 57.2 % - a margin of 11.6 % to the current state of the art, showcasing its robustness on challenging data, and is competitive on even small datasets, e.g. GRK-Papyri, where we achieve a Top-1 accuracy of 58.0%.

cs.CV↗

arXiv2024

Drawing the Line: Deep Segmentation for Extracting Art from Ancient Etruscan Mirrors

Etruscan mirrors constitute a significant category within Etruscan art and, therefore, undergo systematic examinations to obtain insights into ancient times. A crucial aspect of their analysis involves the labor-intensive task of manually tracing engravings from the backside. Additionally, this task is inherently challenging due to the damage these mirrors have sustained, introducing subjectivity into the process. We address these challenges by automating the process through photometric-stereo scanning in conjunction with deep segmentation networks which, however, requires effective usage of the limited data at hand. We accomplish this by incorporating predictions on a per-patch level, and various data augmentations, as well as exploring self-supervised learning. Compared to our baseline, we improve predictive performance w.r.t. the pseudo-F-Measure by around 16%. When assessing performance on complete mirrors against a human baseline, our approach yields quantitative similar performance to a human annotator and significantly outperforms existing binarization methods. With our proposed methodology, we streamline the annotation process, enhance its objectivity, and reduce overall workload, offering a valuable contribution to the examination of these historical artifacts and other non-traditional documents.

cs.CV↗

arXiv2024

Enhancing Historical Image Retrieval with Compositional Cues

In analyzing vast amounts of digitally stored historical image data, existing content-based retrieval methods often overlook significant non-semantic information, limiting their effectiveness for flexible exploration across varied themes. To broaden the applicability of image retrieval methods for diverse purposes and uncover more general patterns, we innovatively introduce a crucial factor from computational aesthetics, namely image composition, into this topic. By explicitly integrating composition-related information extracted by CNN into the designed retrieval model, our method considers both the image's composition rules and semantic information. Qualitative and quantitative experiments demonstrate that the image retrieval network guided by composition information outperforms those relying solely on content information, facilitating the identification of images in databases closer to the target image in human perception. Please visit https://github.com/linty5/CCBIR to try our codes.

cs.CV↗

arXiv2023

ECSIC: Epipolar Cross Attention for Stereo Image Compression

In this paper, we present ECSIC, a novel learned method for stereo image compression. Our proposed method compresses the left and right images in a joint manner by exploiting the mutual information between the images of the stereo image pair using a novel stereo cross attention (SCA) module and two stereo context modules. The SCA module performs cross-attention restricted to the corresponding epipolar lines of the two images and processes them in parallel. The stereo context modules improve the entropy estimation of the second encoded image by using the first image as a context. We conduct an extensive ablation study demonstrating the effectiveness of the proposed modules and a comprehensive quantitative and qualitative comparison with existing methods. ECSIC achieves state-of-the-art performance in stereo image compression on the two popular stereo image datasets Cityscapes and InStereo2k while allowing for fast encoding and decoding.

eess.IV↗

arXiv2023

Feature Mixing for Writer Retrieval and Identification on Papyri Fragments

This paper proposes a deep-learning-based approach to writer retrieval and identification for papyri, with a focus on identifying fragments associated with a specific writer and those corresponding to the same image. We present a novel neural network architecture that combines a residual backbone with a feature mixing stage to improve retrieval performance, and the final descriptor is derived from a projection layer. The methodology is evaluated on two benchmarks: PapyRow, where we achieve a mAP of 26.6 % and 24.9 % on writer and page retrieval, and HisFragIR20, showing state-of-the-art performance (44.0 % and 29.3 % mAP). Furthermore, our network has an accuracy of 28.7 % for writer identification. Additionally, we conduct experiments on the influence of two binarization techniques on fragments and show that binarizing does not enhance performance. Our code and models are available to the community.

cs.CV↗

arXiv2023

Towards Writer Retrieval for Historical Datasets

This paper presents an unsupervised approach for writer retrieval based on clustering SIFT descriptors detected at keypoint locations resulting in pseudo-cluster labels. With those cluster labels, a residual network followed by our proposed NetRVLAD, an encoding layer with reduced complexity compared to NetVLAD, is trained on 32x32 patches at keypoint locations. Additionally, we suggest a graph-based reranking algorithm called SGR to exploit similarities of the page embeddings to boost the retrieval performance. Our approach is evaluated on two historical datasets (Historical-WI and HisIR19). We include an evaluation of different backbones and NetRVLAD. It competes with related work on historical datasets without using explicit encodings. We set a new State-of-the-art on both datasets by applying our reranking scheme and show that our approach achieves comparable performance on a modern dataset as well.

cs.CV↗