10 papers
PERSIST: Persistent-State Discrimination for Shot Boundary Detection
Tingyu Lin, Christian Stippel, Armin Dadras +4
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…
DGME-T: Directional Grid Motion Encoding for Transformer-Based Historical Camera Movement Classification
Tingyu Lin, Armin Dadras, Florian Kleber +1
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…
ClapperText: A Benchmark for Text Recognition in Low-Resource Archival Documents
Tingyu Lin, Marco Peer, Florian Kleber +1
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 Wo…
Camera Movement Classification in Historical Footage: A Comparative Study of Deep Video Models
Tingyu Lin, Armin Dadras, Florian Kleber +1
Camera movement conveys spatial and narrative information essential for understanding video content. While recent camera movement classification (CMC) methods perform well on moder…
Towards the Influence of Text Quantity on Writer Retrieval
Marco Peer, Robert Sablatnig, Florian Kleber
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…
SAGHOG: Self-Supervised Autoencoder for Generating HOG Features for Writer Retrieval
Marco Peer, Florian Kleber, Robert Sablatnig
This paper introduces SAGHOG, a self-supervised pretraining strategy for writer retrieval using HOG features of the binarized input image. Our preprocessing involves the applicatio…
Explainable Techniques for Analyzing Flow Cytometry Cell Transformers
Florian Kowarsch, Lisa Weijler, FLorian Kleber +4
Explainability for Deep Learning Models is especially important for clinical applications, where decisions of automated systems have far-reaching consequences. While various post-h…
Towards Writer Retrieval for Historical Datasets
Marco Peer, Florian Kleber, Robert Sablatnig
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…
Comparing Machine Learning Approaches for Table Recognition in Historical Register Books
Stéphane Clinchant, Hervé Déjean, Jean-Luc Meunier +2
We present in this paper experiments on Table Recognition in hand-written registry books. We first explain how the problem of row and column detection is modeled, and then compare…
READ-BAD: A New Dataset and Evaluation Scheme for Baseline Detection in Archival Documents
Tobias Grüning, Roger Labahn, Markus Diem +2
Text line detection is crucial for any application associated with Automatic Text Recognition or Keyword Spotting. Modern algorithms perform good on well-established datasets since…