Records |
Author |
Matthias Eisenmann; Annika Reinke; Vivienn Weru; Minu D. Tizabi; Fabian Isensee; Tim J. Adler; Sharib Ali; Vincent Andrearczyk; Marc Aubreville; Ujjwal Baid; Spyridon Bakas; Niranjan Balu; Sophia Bano; Jorge Bernal; Sebastian Bodenstedt; Alessandro Casella; Veronika Cheplygina; Marie Daum; Marleen de Bruijne |
Title |
Why Is the Winner the Best? |
Type |
Conference Article |
Year |
2023 |
Publication |
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition |
Abbreviated Journal ![sorted by Abbreviated Journal field, ascending order (up)](img/sort_asc.gif) |
|
Volume |
|
Issue |
|
Pages |
19955-19966 |
Keywords |
|
Abstract |
International benchmarking competitions have become fundamental for the comparative performance assessment of image analysis methods. However, little attention has been given to investigating what can be learnt from these competitions. Do they really generate scientific progress? What are common and successful participation strategies? What makes a solution superior to a competing method? To address this gap in the literature, we performed a multi-center study with all 80 competitions that were conducted in the scope of IEEE ISBI 2021 and MICCAI 2021. Statistical analyses performed based on comprehensive descriptions of the submitted algorithms linked to their rank as well as the underlying participation strategies revealed common characteristics of winning solutions. These typically include the use of multi-task learning (63%) and/or multi-stage pipelines (61%), and a focus on augmentation (100%), image preprocessing (97%), data curation (79%), and postprocessing (66%). The “typical” lead of a winning team is a computer scientist with a doctoral degree, five years of experience in biomedical image analysis, and four years of experience in deep learning. Two core general development strategies stood out for highly-ranked teams: the reflection of the metrics in the method design and the focus on analyzing and handling failure cases. According to the organizers, 43% of the winning algorithms exceeded the state of the art but only 11% completely solved the respective domain problem. The insights of our study could help researchers (1) improve algorithm development strategies when approaching new problems, and (2) focus on open research questions revealed by this work. |
Address |
Vancouver; Canada; June 2023 |
Corporate Author |
|
Thesis |
|
Publisher |
|
Place of Publication |
|
Editor |
|
Language |
|
Summary Language |
|
Original Title |
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
Series Volume |
|
Series Issue |
|
Edition |
|
ISSN |
|
ISBN |
|
Medium |
|
Area |
|
Expedition |
|
Conference |
CVPR |
Notes |
ISE |
Approved |
no |
Call Number |
Admin @ si @ ERW2023 |
Serial |
3842 |
Permanent link to this record |
|
|
|
Author |
Eduardo Aguilar; Bogdan Raducanu; Petia Radeva; Joost Van de Weijer |
Title |
Continual Evidential Deep Learning for Out-of-Distribution Detection |
Type |
Conference Article |
Year |
2023 |
Publication |
IEEE/CVF International Conference on Computer Vision (ICCV) Workshops -Visual Continual Learning workshop |
Abbreviated Journal ![sorted by Abbreviated Journal field, ascending order (up)](img/sort_asc.gif) |
|
Volume |
|
Issue |
|
Pages |
3444-3454 |
Keywords |
|
Abstract |
Uncertainty-based deep learning models have attracted a great deal of interest for their ability to provide accurate and reliable predictions. Evidential deep learning stands out achieving remarkable performance in detecting out-of-distribution (OOD) data with a single deterministic neural network. Motivated by this fact, in this paper we propose the integration of an evidential deep learning method into a continual learning framework in order to perform simultaneously incremental object classification and OOD detection. Moreover, we analyze the ability of vacuity and dissonance to differentiate between in-distribution data belonging to old classes and OOD data. The proposed method, called CEDL, is evaluated on CIFAR-100 considering two settings consisting of 5 and 10 tasks, respectively. From the obtained results, we could appreciate that the proposed method, in addition to provide comparable results in object classification with respect to the baseline, largely outperforms OOD detection compared to several posthoc methods on three evaluation metrics: AUROC, AUPR and FPR95. |
Address |
Paris; France; October 2023 |
Corporate Author |
|
Thesis |
|
Publisher |
|
Place of Publication |
|
Editor |
|
Language |
|
Summary Language |
|
Original Title |
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
Series Volume |
|
Series Issue |
|
Edition |
|
ISSN |
|
ISBN |
|
Medium |
|
Area |
|
Expedition |
|
Conference |
ICCVW |
Notes |
LAMP; MILAB |
Approved |
no |
Call Number |
Admin @ si @ ARR2023 |
Serial |
3841 |
Permanent link to this record |
|
|
|
Author |
Roberto Morales; Juan Quispe; Eduardo Aguilar |
Title |
Exploring multi-food detection using deep learning-based algorithms |
Type |
Conference Article |
Year |
2023 |
Publication |
13th International Conference on Pattern Recognition Systems |
Abbreviated Journal ![sorted by Abbreviated Journal field, ascending order (up)](img/sort_asc.gif) |
|
Volume |
|
Issue |
|
Pages |
1-7 |
Keywords |
|
Abstract |
People are becoming increasingly concerned about their diet, whether for disease prevention, medical treatment or other purposes. In meals served in restaurants, schools or public canteens, it is not easy to identify the ingredients and/or the nutritional information they contain. Currently, technological solutions based on deep learning models have facilitated the recording and tracking of food consumed based on the recognition of the main dish present in an image. Considering that sometimes there may be multiple foods served on the same plate, food analysis should be treated as a multi-class object detection problem. EfficientDet and YOLOv5 are object detection algorithms that have demonstrated high mAP and real-time performance on general domain data. However, these models have not been evaluated and compared on public food datasets. Unlike general domain objects, foods have more challenging features inherent in their nature that increase the complexity of detection. In this work, we performed a performance evaluation of Efficient-Det and YOLOv5 on three public food datasets: UNIMIB2016, UECFood256 and ChileanFood64. From the results obtained, it can be seen that YOLOv5 provides a significant difference in terms of both mAP and response time compared to EfficientDet in all datasets. Furthermore, YOLOv5 outperforms the state-of-the-art on UECFood256, achieving an improvement of more than 4% in terms of mAP@.50 over the best reported. |
Address |
Guayaquil; Ecuador; July 2023 |
Corporate Author |
|
Thesis |
|
Publisher |
|
Place of Publication |
|
Editor |
|
Language |
|
Summary Language |
|
Original Title |
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
Series Volume |
|
Series Issue |
|
Edition |
|
ISSN |
|
ISBN |
|
Medium |
|
Area |
|
Expedition |
|
Conference |
ICPRS |
Notes |
MILAB |
Approved |
no |
Call Number |
Admin @ si @ MQA2023 |
Serial |
3843 |
Permanent link to this record |
|
|
|
Author |
Roger Max Calle Quispe; Maya Aghaei Gavari; Eduardo Aguilar Torres |
Title |
Towards real-time accurate safety helmets detection through a deep learning-based method |
Type |
Journal |
Year |
2023 |
Publication |
Ingeniare. Revista chilena de ingenieria |
Abbreviated Journal ![sorted by Abbreviated Journal field, ascending order (up)](img/sort_asc.gif) |
|
Volume |
31 |
Issue |
12 |
Pages |
|
Keywords |
|
Abstract |
Occupational safety is a fundamental activity in industries and revolves around the management of the necessary controls that must be present to mitigate occupational risks. These controls include verifying the use of Personal Protection Equipment (PPE). Within PPE, safety helmets are vital to reducing severe or fatal consequences caused by head injuries. This problem has been addressed recently by various research based on deep learning to detect the usage of safety helmets by the present people in the industrial field.
These works have achieved promising results for safety helmet detection using object detection methods from the YOLO family. In this work, we propose to analyze the performance of Scaled-YOLOv4, a novel model of the YOLO family that has yet to be previously studied for this problem. The performance of the Scaled-YOLOv4 is evaluated on two public databases, carefully selected among the previously proposed datasets for the occupational safety framework. We demonstrate the superiority of Scaled-YOLOv4 in terms of mAP and Fl-score concerning the previous works for both databases. Further, we summarize the currently available datasets for safety helmet detection purposes and discuss their suitability. |
Address |
|
Corporate Author |
|
Thesis |
|
Publisher |
|
Place of Publication |
|
Editor |
|
Language |
|
Summary Language |
|
Original Title |
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
Series Volume |
|
Series Issue |
|
Edition |
|
ISSN |
|
ISBN |
|
Medium |
|
Area |
|
Expedition |
|
Conference |
|
Notes |
MILAB |
Approved |
no |
Call Number |
Admin @ si @ CAA2023 |
Serial |
3846 |
Permanent link to this record |
|
|
|
Author |
G. Gasbarri; Matias Bilkis; E. Roda Salichs; J. Calsamiglia |
Title |
Sequential hypothesis testing for continuously-monitored quantum systems |
Type |
Journal Article |
Year |
2024 |
Publication |
Quantum |
Abbreviated Journal ![sorted by Abbreviated Journal field, ascending order (up)](img/sort_asc.gif) |
|
Volume |
8 |
Issue |
1289 |
Pages |
|
Keywords |
|
Abstract |
We consider a quantum system that is being continuously monitored, giving rise to a measurement signal. From such a stream of data, information needs to be inferred about the underlying system's dynamics. Here we focus on hypothesis testing problems and put forward the usage of sequential strategies where the signal is analyzed in real time, allowing the experiment to be concluded as soon as the underlying hypothesis can be identified with a certified prescribed success probability. We analyze the performance of sequential tests by studying the stopping-time behavior, showing a considerable advantage over currently-used strategies based on a fixed predetermined measurement time. |
Address |
|
Corporate Author |
|
Thesis |
|
Publisher |
|
Place of Publication |
|
Editor |
|
Language |
|
Summary Language |
|
Original Title |
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
Series Volume |
|
Series Issue |
|
Edition |
|
ISSN |
|
ISBN |
|
Medium |
|
Area |
|
Expedition |
|
Conference |
|
Notes |
xxxx |
Approved |
no |
Call Number |
Admin @ si @ GBR2024 |
Serial |
3847 |
Permanent link to this record |
|
|
|
Author |
Mohamed Ali Souibgui; Sanket Biswas; Andres Mafla; Ali Furkan Biten; Alicia Fornes; Yousri Kessentini; Josep Llados; Lluis Gomez; Dimosthenis Karatzas |
Title |
Text-DIAE: a self-supervised degradation invariant autoencoder for text recognition and document enhancement |
Type |
Conference Article |
Year |
2023 |
Publication |
Proceedings of the 37th AAAI Conference on Artificial Intelligence |
Abbreviated Journal ![sorted by Abbreviated Journal field, ascending order (up)](img/sort_asc.gif) |
|
Volume |
37 |
Issue |
2 |
Pages |
|
Keywords |
Representation Learning for Vision; CV Applications; CV Language and Vision; ML Unsupervised; Self-Supervised Learning |
Abstract |
In this paper, we propose a Text-Degradation Invariant Auto Encoder (Text-DIAE), a self-supervised model designed to tackle two tasks, text recognition (handwritten or scene-text) and document image enhancement. We start by employing a transformer-based architecture that incorporates three pretext tasks as learning objectives to be optimized during pre-training without the usage of labelled data. Each of the pretext objectives is specifically tailored for the final downstream tasks. We conduct several ablation experiments that confirm the design choice of the selected pretext tasks. Importantly, the proposed model does not exhibit limitations of previous state-of-the-art methods based on contrastive losses, while at the same time requiring substantially fewer data samples to converge. Finally, we demonstrate that our method surpasses the state-of-the-art in existing supervised and self-supervised settings in handwritten and scene text recognition and document image enhancement. Our code and trained models will be made publicly available at https://github.com/dali92002/SSL-OCR |
Address |
|
Corporate Author |
|
Thesis |
|
Publisher |
|
Place of Publication |
|
Editor |
|
Language |
|
Summary Language |
|
Original Title |
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
Series Volume |
|
Series Issue |
|
Edition |
|
ISSN |
|
ISBN |
|
Medium |
|
Area |
|
Expedition |
|
Conference |
AAAI |
Notes |
DAG |
Approved |
no |
Call Number |
Admin @ si @ SBM2023 |
Serial |
3848 |
Permanent link to this record |
|
|
|
Author |
Mohamed Ali Souibgui; Pau Torras; Jialuo Chen; Alicia Fornes |
Title |
An Evaluation of Handwritten Text Recognition Methods for Historical Ciphered Manuscripts |
Type |
Conference Article |
Year |
2023 |
Publication |
7th International Workshop on Historical Document Imaging and Processing |
Abbreviated Journal ![sorted by Abbreviated Journal field, ascending order (up)](img/sort_asc.gif) |
|
Volume |
|
Issue |
|
Pages |
7-12 |
Keywords |
|
Abstract |
This paper investigates the effectiveness of different deep learning HTR families, including LSTM, Seq2Seq, and transformer-based approaches with self-supervised pretraining, in recognizing ciphered manuscripts from different historical periods and cultures. The goal is to identify the most suitable method or training techniques for recognizing ciphered manuscripts and to provide insights into the challenges and opportunities in this field of research. We evaluate the performance of these models on several datasets of ciphered manuscripts and discuss their results. This study contributes to the development of more accurate and efficient methods for recognizing historical manuscripts for the preservation and dissemination of our cultural heritage. |
Address |
|
Corporate Author |
|
Thesis |
|
Publisher |
|
Place of Publication |
|
Editor |
|
Language |
|
Summary Language |
|
Original Title |
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
Series Volume |
|
Series Issue |
|
Edition |
|
ISSN |
|
ISBN |
|
Medium |
|
Area |
|
Expedition |
|
Conference |
HIP |
Notes |
DAG |
Approved |
no |
Call Number |
Admin @ si @ STC2023 |
Serial |
3849 |
Permanent link to this record |
|
|
|
Author |
Pau Torras; Mohamed Ali Souibgui; Sanket Biswas; Alicia Fornes |
Title |
Segmentation-Free Alignment of Arbitrary Symbol Transcripts to Images |
Type |
Conference Article |
Year |
2023 |
Publication |
Document Analysis and Recognition – ICDAR 2023 Workshops |
Abbreviated Journal ![sorted by Abbreviated Journal field, ascending order (up)](img/sort_asc.gif) |
|
Volume |
14193 |
Issue |
|
Pages |
83-93 |
Keywords |
Historical Manuscripts; Symbol Alignment |
Abstract |
Developing arbitrary symbol recognition systems is a challenging endeavour. Even using content-agnostic architectures such as few-shot models, performance can be substantially improved by providing a number of well-annotated examples into training. In some contexts, transcripts of the symbols are available without any position information associated to them, which enables using line-level recognition architectures. A way of providing this position information to detection-based architectures is finding systems that can align the input symbols with the transcription. In this paper we discuss some symbol alignment techniques that are suitable for low-data scenarios and provide an insight on their perceived strengths and weaknesses. In particular, we study the usage of Connectionist Temporal Classification models, Attention-Based Sequence to Sequence models and we compare them with the results obtained on a few-shot recognition system. |
Address |
|
Corporate Author |
|
Thesis |
|
Publisher |
|
Place of Publication |
|
Editor |
|
Language |
|
Summary Language |
|
Original Title |
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
LNCS |
Series Volume |
|
Series Issue |
|
Edition |
|
ISSN |
|
ISBN |
|
Medium |
|
Area |
|
Expedition |
|
Conference |
ICDAR |
Notes |
DAG |
Approved |
no |
Call Number |
Admin @ si @ TSS2023 |
Serial |
3850 |
Permanent link to this record |
|
|
|
Author |
Marwa Dhiaf; Mohamed Ali Souibgui; Kai Wang; Yuyang Liu; Yousri Kessentini; Alicia Fornes; Ahmed Cheikh Rouhou |
Title |
CSSL-MHTR: Continual Self-Supervised Learning for Scalable Multi-script Handwritten Text Recognition |
Type |
Miscellaneous |
Year |
2023 |
Publication |
Arxiv |
Abbreviated Journal ![sorted by Abbreviated Journal field, ascending order (up)](img/sort_asc.gif) |
|
Volume |
|
Issue |
|
Pages |
|
Keywords |
|
Abstract |
Self-supervised learning has recently emerged as a strong alternative in document analysis. These approaches are now capable of learning high-quality image representations and overcoming the limitations of supervised methods, which require a large amount of labeled data. However, these methods are unable to capture new knowledge in an incremental fashion, where data is presented to the model sequentially, which is closer to the realistic scenario. In this paper, we explore the potential of continual self-supervised learning to alleviate the catastrophic forgetting problem in handwritten text recognition, as an example of sequence recognition. Our method consists in adding intermediate layers called adapters for each task, and efficiently distilling knowledge from the previous model while learning the current task. Our proposed framework is efficient in both computation and memory complexity. To demonstrate its effectiveness, we evaluate our method by transferring the learned model to diverse text recognition downstream tasks, including Latin and non-Latin scripts. As far as we know, this is the first application of continual self-supervised learning for handwritten text recognition. We attain state-of-the-art performance on English, Italian and Russian scripts, whilst adding only a few parameters per task. The code and trained models will be publicly available. |
Address |
|
Corporate Author |
|
Thesis |
|
Publisher |
|
Place of Publication |
|
Editor |
|
Language |
|
Summary Language |
|
Original Title |
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
Series Volume |
|
Series Issue |
|
Edition |
|
ISSN |
|
ISBN |
|
Medium |
|
Area |
|
Expedition |
|
Conference |
|
Notes |
DAG |
Approved |
no |
Call Number |
Admin @ si @ DSW2023 |
Serial |
3851 |
Permanent link to this record |
|
|
|
Author |
Mickael Coustaty; Alicia Fornes |
Title |
Document Analysis and Recognition – ICDAR 2023 Workshops |
Type |
Book Whole |
Year |
2023 |
Publication |
Document Analysis and Recognition – ICDAR 2023 Workshops |
Abbreviated Journal ![sorted by Abbreviated Journal field, ascending order (up)](img/sort_asc.gif) |
|
Volume |
14194 |
Issue |
2 |
Pages |
|
Keywords |
|
Abstract |
|
Address |
San Jose; USA; August 2023 |
Corporate Author |
|
Thesis |
|
Publisher |
|
Place of Publication |
|
Editor |
|
Language |
|
Summary Language |
|
Original Title |
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
LNCS |
Series Volume |
|
Series Issue |
|
Edition |
|
ISSN |
|
ISBN |
|
Medium |
|
Area |
|
Expedition |
|
Conference |
ICDAR |
Notes |
DAG |
Approved |
no |
Call Number |
Admin @ si @ CoF2023 |
Serial |
3852 |
Permanent link to this record |
|
|
|
Author |
JW Xiao; CB Zhang; J. Feng; Xialei Liu; Joost Van de Weijer; MM Cheng |
Title |
Endpoints Weight Fusion for Class Incremental Semantic Segmentation |
Type |
Conference Article |
Year |
2023 |
Publication |
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition |
Abbreviated Journal ![sorted by Abbreviated Journal field, ascending order (up)](img/sort_asc.gif) |
|
Volume |
|
Issue |
|
Pages |
7204-7213 |
Keywords |
|
Abstract |
Class incremental semantic segmentation (CISS) focuses on alleviating catastrophic forgetting to improve discrimination. Previous work mainly exploit regularization (e.g., knowledge distillation) to maintain previous knowledge in the current model. However, distillation alone often yields limited gain to the model since only the representations of old and new models are restricted to be consistent. In this paper, we propose a simple yet effective method to obtain a model with strong memory of old knowledge, named Endpoints Weight Fusion (EWF). In our method, the model containing old knowledge is fused with the model retaining new knowledge in a dynamic fusion manner, strengthening the memory of old classes in ever-changing distributions. In addition, we analyze the relation between our fusion strategy and a popular moving average technique EMA, which reveals why our method is more suitable for class-incremental learning. To facilitate parameter fusion with closer distance in the parameter space, we use distillation to enhance the optimization process. Furthermore, we conduct experiments on two widely used datasets, achieving the state-of-the-art performance. |
Address |
Vancouver; Canada; June 2023 |
Corporate Author |
|
Thesis |
|
Publisher |
|
Place of Publication |
|
Editor |
|
Language |
|
Summary Language |
|
Original Title |
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
Series Volume |
|
Series Issue |
|
Edition |
|
ISSN |
|
ISBN |
|
Medium |
|
Area |
|
Expedition |
|
Conference |
CVPR |
Notes |
LAMP |
Approved |
no |
Call Number |
Admin @ si @ XZF2023 |
Serial |
3854 |
Permanent link to this record |
|
|
|
Author |
Patricia Suarez; Dario Carpio; Angel Sappa |
Title |
A Deep Learning Based Approach for Synthesizing Realistic Depth Maps |
Type |
Conference Article |
Year |
2023 |
Publication |
22nd International Conference on Image Analysis and Processing |
Abbreviated Journal ![sorted by Abbreviated Journal field, ascending order (up)](img/sort_asc.gif) |
|
Volume |
14234 |
Issue |
|
Pages |
369–380 |
Keywords |
|
Abstract |
This paper presents a novel cycle generative adversarial network (CycleGAN) architecture for synthesizing high-quality depth maps from a given monocular image. The proposed architecture uses multiple loss functions, including cycle consistency, contrastive, identity, and least square losses, to enable the generation of realistic and high-fidelity depth maps. The proposed approach addresses this challenge by synthesizing depth maps from RGB images without requiring paired training data. Comparisons with several state-of-the-art approaches are provided showing the proposed approach overcome other approaches both in terms of quantitative metrics and visual quality. |
Address |
Udine; Italia; Setember 2023 |
Corporate Author |
|
Thesis |
|
Publisher |
|
Place of Publication |
|
Editor |
|
Language |
|
Summary Language |
|
Original Title |
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
LNCS |
Series Volume |
|
Series Issue |
|
Edition |
|
ISSN |
|
ISBN |
|
Medium |
|
Area |
|
Expedition |
|
Conference |
ICIAP |
Notes |
MSIAU |
Approved |
no |
Call Number |
Admin @ si @ SCS2023a |
Serial |
3968 |
Permanent link to this record |
|
|
|
Author |
Francesc Net; Marc Folia; Pep Casals; Lluis Gomez |
Title |
Transductive Learning for Near-Duplicate Image Detection in Scanned Photo Collections |
Type |
Conference Article |
Year |
2023 |
Publication |
17th International Conference on Document Analysis and Recognition |
Abbreviated Journal ![sorted by Abbreviated Journal field, ascending order (up)](img/sort_asc.gif) |
|
Volume |
14191 |
Issue |
|
Pages |
3-17 |
Keywords |
Image deduplication; Near-duplicate images detection; Transductive Learning; Photographic Archives; Deep Learning |
Abstract |
This paper presents a comparative study of near-duplicate image detection techniques in a real-world use case scenario, where a document management company is commissioned to manually annotate a collection of scanned photographs. Detecting duplicate and near-duplicate photographs can reduce the time spent on manual annotation by archivists. This real use case differs from laboratory settings as the deployment dataset is available in advance, allowing the use of transductive learning. We propose a transductive learning approach that leverages state-of-the-art deep learning architectures such as convolutional neural networks (CNNs) and Vision Transformers (ViTs). Our approach involves pre-training a deep neural network on a large dataset and then fine-tuning the network on the unlabeled target collection with self-supervised learning. The results show that the proposed approach outperforms the baseline methods in the task of near-duplicate image detection in the UKBench and an in-house private dataset. |
Address |
San Jose; CA; USA; August 2023 |
Corporate Author |
|
Thesis |
|
Publisher |
|
Place of Publication |
|
Editor |
|
Language |
|
Summary Language |
|
Original Title |
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
LNCS |
Series Volume |
|
Series Issue |
|
Edition |
|
ISSN |
|
ISBN |
|
Medium |
|
Area |
|
Expedition |
|
Conference |
ICDAR |
Notes |
DAG |
Approved |
no |
Call Number |
Admin @ si @ NFC2023 |
Serial |
3859 |
Permanent link to this record |
|
|
|
Author |
Khanh Nguyen; Ali Furkan Biten; Andres Mafla; Lluis Gomez; Dimosthenis Karatzas |
Title |
Show, Interpret and Tell: Entity-Aware Contextualised Image Captioning in Wikipedia |
Type |
Conference Article |
Year |
2023 |
Publication |
Proceedings of the 37th AAAI Conference on Artificial Intelligence |
Abbreviated Journal ![sorted by Abbreviated Journal field, ascending order (up)](img/sort_asc.gif) |
|
Volume |
37 |
Issue |
2 |
Pages |
1940-1948 |
Keywords |
|
Abstract |
Humans exploit prior knowledge to describe images, and are able to adapt their explanation to specific contextual information given, even to the extent of inventing plausible explanations when contextual information and images do not match. In this work, we propose the novel task of captioning Wikipedia images by integrating contextual knowledge. Specifically, we produce models that jointly reason over Wikipedia articles, Wikimedia images and their associated descriptions to produce contextualized captions. The same Wikimedia image can be used to illustrate different articles, and the produced caption needs to be adapted to the specific context allowing us to explore the limits of the model to adjust captions to different contextual information. Dealing with out-of-dictionary words and Named Entities is a challenging task in this domain. To address this, we propose a pre-training objective, Masked Named Entity Modeling (MNEM), and show that this pretext task results to significantly improved models. Furthermore, we verify that a model pre-trained in Wikipedia generalizes well to News Captioning datasets. We further define two different test splits according to the difficulty of the captioning task. We offer insights on the role and the importance of each modality and highlight the limitations of our model. |
Address |
Washington; USA; February 2023 |
Corporate Author |
|
Thesis |
|
Publisher |
|
Place of Publication |
|
Editor |
|
Language |
|
Summary Language |
|
Original Title |
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
Series Volume |
|
Series Issue |
|
Edition |
|
ISSN |
|
ISBN |
|
Medium |
|
Area |
|
Expedition |
|
Conference |
AAAI |
Notes |
DAG |
Approved |
no |
Call Number |
Admin @ si @ NBM2023 |
Serial |
3860 |
Permanent link to this record |
|
|
|
Author |
Bonifaz Stuhr; Jurgen Brauer; Bernhard Schick; Jordi Gonzalez |
Title |
Masked Discriminators for Content-Consistent Unpaired Image-to-Image Translation |
Type |
Miscellaneous |
Year |
2023 |
Publication |
Arxiv |
Abbreviated Journal ![sorted by Abbreviated Journal field, ascending order (up)](img/sort_asc.gif) |
|
Volume |
|
Issue |
|
Pages |
|
Keywords |
|
Abstract |
A common goal of unpaired image-to-image translation is to preserve content consistency between source images and translated images while mimicking the style of the target domain. Due to biases between the datasets of both domains, many methods suffer from inconsistencies caused by the translation process. Most approaches introduced to mitigate these inconsistencies do not constrain the discriminator, leading to an even more ill-posed training setup. Moreover, none of these approaches is designed for larger crop sizes. In this work, we show that masking the inputs of a global discriminator for both domains with a content-based mask is sufficient to reduce content inconsistencies significantly. However, this strategy leads to artifacts that can be traced back to the masking process. To reduce these artifacts, we introduce a local discriminator that operates on pairs of small crops selected with a similarity sampling strategy. Furthermore, we apply this sampling strategy to sample global input crops from the source and target dataset. In addition, we propose feature-attentive denormalization to selectively incorporate content-based statistics into the generator stream. In our experiments, we show that our method achieves state-of-the-art performance in photorealistic sim-to-real translation and weather translation and also performs well in day-to-night translation. Additionally, we propose the cKVD metric, which builds on the sKVD metric and enables the examination of translation quality at the class or category level. |
Address |
|
Corporate Author |
|
Thesis |
|
Publisher |
|
Place of Publication |
|
Editor |
|
Language |
|
Summary Language |
|
Original Title |
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
Series Volume |
|
Series Issue |
|
Edition |
|
ISSN |
|
ISBN |
|
Medium |
|
Area |
|
Expedition |
|
Conference |
|
Notes |
ISE |
Approved |
no |
Call Number |
Admin @ si @ SBS2023 |
Serial |
3863 |
Permanent link to this record |