Home << 1 2 3 4 5 6 7 8 9 10 >>
List View
 | 
Citations
 | 
Details
   web
Records
Author Hugo Jair Escalante; Heysem Kaya; Albert Ali Salah; Sergio Escalera; Yagmur Gucluturk; Umut Guçlu; Xavier Baro; Isabelle Guyon; Julio C. S. Jacques Junior; Meysam Madadi; Stephane Ayache; Evelyne Viegas; Furkan Gurpinar; Achmadnoer Sukma Wicaksana; Cynthia Liem; Marcel A. J. Van Gerven; Rob Van Lier
Title Modeling, Recognizing, and Explaining Apparent Personality from Videos Type Journal Article
Year 2022 Publication IEEE Transactions on Affective Computing Abbreviated Journal TAC
Volume 13 Issue 2 Pages 894-911
Keywords
Abstract Explainability and interpretability are two critical aspects of decision support systems. Despite their importance, it is only recently that researchers are starting to explore these aspects. This paper provides an introduction to explainability and interpretability in the context of apparent personality recognition. To the best of our knowledge, this is the first effort in this direction. We describe a challenge we organized on explainability in first impressions analysis from video. We analyze in detail the newly introduced data set, evaluation protocol, proposed solutions and summarize the results of the challenge. We investigate the issue of bias in detail. Finally, derived from our study, we outline research opportunities that we foresee will be relevant in this area in the near future.
Address 1 April-June 2022
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 HuPBA; no menciona Approved no
Call Number Admin @ si @ EKS2022 Serial (up) 3406
Permanent link to this record
 
 
Author Mohamed Ali Souibgui; Y.Kessentini
Title DE-GAN: A Conditional Generative Adversarial Network for Document Enhancement Type Journal Article
Year 2022 Publication IEEE Transactions on Pattern Analysis and Machine Intelligence Abbreviated Journal TPAMI
Volume 44 Issue 3 Pages 1180-1191
Keywords
Abstract Documents often exhibit various forms of degradation, which make it hard to be read and substantially deteriorate the performance of an OCR system. In this paper, we propose an effective end-to-end framework named Document Enhancement Generative Adversarial Networks (DE-GAN) that uses the conditional GANs (cGANs) to restore severely degraded document images. To the best of our knowledge, this practice has not been studied within the context of generative adversarial deep networks. We demonstrate that, in different tasks (document clean up, binarization, deblurring and watermark removal), DE-GAN can produce an enhanced version of the degraded document with a high quality. In addition, our approach provides consistent improvements compared to state-of-the-art methods over the widely used DIBCO 2013, DIBCO 2017 and H-DIBCO 2018 datasets, proving its ability to restore a degraded document image to its ideal condition. The obtained results on a wide variety of degradation reveal the flexibility of the proposed model to be exploited in other document enhancement problems.
Address 1 March 2022
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; 602.230; 600.121; 600.140 Approved no
Call Number Admin @ si @ SoK2022 Serial (up) 3454
Permanent link to this record
 
 
Author Saad Minhas; Aura Hernandez-Sabate; Shoaib Ehsan; Klaus McDonald Maier
Title Effects of Non-Driving Related Tasks during Self-Driving mode Type Journal Article
Year 2022 Publication IEEE Transactions on Intelligent Transportation Systems Abbreviated Journal TITS
Volume 23 Issue 2 Pages 1391-1399
Keywords
Abstract Perception reaction time and mental workload have proven to be crucial in manual driving. Moreover, in highly automated cars, where most of the research is focusing on Level 4 Autonomous driving, take-over performance is also a key factor when taking road safety into account. This study aims to investigate how the immersion in non-driving related tasks affects the take-over performance of drivers in given scenarios. The paper also highlights the use of virtual simulators to gather efficient data that can be crucial in easing the transition between manual and autonomous driving scenarios. The use of Computer Aided Simulations is of absolute importance in this day and age since the automotive industry is rapidly moving towards Autonomous technology. An experiment comprising of 40 subjects was performed to examine the reaction times of driver and the influence of other variables in the success of take-over performance in highly automated driving under different circumstances within a highway virtual environment. The results reflect the relationship between reaction times under different scenarios that the drivers might face under the circumstances stated above as well as the importance of variables such as velocity in the success on regaining car control after automated driving. The implications of the results acquired are important for understanding the criteria needed for designing Human Machine Interfaces specifically aimed towards automated driving conditions. Understanding the need to keep drivers in the loop during automation, whilst allowing drivers to safely engage in other non-driving related tasks is an important research area which can be aided by the proposed study.
Address Feb. 2022
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 IAM; 600.139; 600.145 Approved no
Call Number Admin @ si @ MHE2022 Serial (up) 3468
Permanent link to this record
 
 
Author Jun Wan; Chi Lin; Longyin Wen; Yunan Li; Qiguang Miao; Sergio Escalera; Gholamreza Anbarjafari; Isabelle Guyon; Guodong Guo; Stan Z. Li
Title ChaLearn Looking at People: IsoGD and ConGD Large-scale RGB-D Gesture Recognition Type Journal Article
Year 2022 Publication IEEE Transactions on Cybernetics Abbreviated Journal TCIBERN
Volume 52 Issue 5 Pages 3422-3433
Keywords
Abstract The ChaLearn large-scale gesture recognition challenge has been run twice in two workshops in conjunction with the International Conference on Pattern Recognition (ICPR) 2016 and International Conference on Computer Vision (ICCV) 2017, attracting more than 200 teams round the world. This challenge has two tracks, focusing on isolated and continuous gesture recognition, respectively. This paper describes the creation of both benchmark datasets and analyzes the advances in large-scale gesture recognition based on these two datasets. We discuss the challenges of collecting large-scale ground-truth annotations of gesture recognition, and provide a detailed analysis of the current state-of-the-art methods for large-scale isolated and continuous gesture recognition based on RGB-D video sequences. In addition to recognition rate and mean jaccard index (MJI) as evaluation metrics used in our previous challenges, we also introduce the corrected segmentation rate (CSR) metric to evaluate the performance of temporal segmentation for continuous gesture recognition. Furthermore, we propose a bidirectional long short-term memory (Bi-LSTM) baseline method, determining the video division points based on the skeleton points extracted by convolutional pose machine (CPM). Experiments demonstrate that the proposed Bi-LSTM outperforms the state-of-the-art methods with an absolute improvement of 8.1% (from 0.8917 to 0.9639) of CSR.
Address May 2022
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 HUPBA; no menciona Approved no
Call Number Admin @ si @ WLW2022 Serial (up) 3522
Permanent link to this record
 
 
Author Marc Masana; Xialei Liu; Bartlomiej Twardowski; Mikel Menta; Andrew Bagdanov; Joost Van de Weijer
Title Class-incremental learning: survey and performance evaluation Type Journal Article
Year 2022 Publication IEEE Transactions on Pattern Analysis and Machine Intelligence Abbreviated Journal TPAMI
Volume Issue Pages
Keywords
Abstract For future learning systems incremental learning is desirable, because it allows for: efficient resource usage by eliminating the need to retrain from scratch at the arrival of new data; reduced memory usage by preventing or limiting the amount of data required to be stored -- also important when privacy limitations are imposed; and learning that more closely resembles human learning. The main challenge for incremental learning is catastrophic forgetting, which refers to the precipitous drop in performance on previously learned tasks after learning a new one. Incremental learning of deep neural networks has seen explosive growth in recent years. Initial work focused on task incremental learning, where a task-ID is provided at inference time. Recently we have seen a shift towards class-incremental learning where the learner must classify at inference time between all classes seen in previous tasks without recourse to a task-ID. In this paper, we provide a complete survey of existing methods for incremental learning, and in particular we perform an extensive experimental evaluation on twelve class-incremental methods. We consider several new experimental scenarios, including a comparison of class-incremental methods on multiple large-scale datasets, investigation into small and large domain shifts, and comparison on various network architectures.
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 LAMP; 600.120 Approved no
Call Number Admin @ si @ MLT2022 Serial (up) 3538
Permanent link to this record
 
 
Author Lei Kang; Pau Riba; Marçal Rusiñol; Alicia Fornes; Mauricio Villegas
Title Pay Attention to What You Read: Non-recurrent Handwritten Text-Line Recognition Type Journal Article
Year 2022 Publication Pattern Recognition Abbreviated Journal PR
Volume 129 Issue Pages 108766
Keywords
Abstract The advent of recurrent neural networks for handwriting recognition marked an important milestone reaching impressive recognition accuracies despite the great variability that we observe across different writing styles. Sequential architectures are a perfect fit to model text lines, not only because of the inherent temporal aspect of text, but also to learn probability distributions over sequences of characters and words. However, using such recurrent paradigms comes at a cost at training stage, since their sequential pipelines prevent parallelization. In this work, we introduce a non-recurrent approach to recognize handwritten text by the use of transformer models. We propose a novel method that bypasses any recurrence. By using multi-head self-attention layers both at the visual and textual stages, we are able to tackle character recognition as well as to learn language-related dependencies of the character sequences to be decoded. Our model is unconstrained to any predefined vocabulary, being able to recognize out-of-vocabulary words, i.e. words that do not appear in the training vocabulary. We significantly advance over prior art and demonstrate that satisfactory recognition accuracies are yielded even in few-shot learning scenarios.
Address Sept. 2022
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; 600.121; 600.162 Approved no
Call Number Admin @ si @ KRR2022 Serial (up) 3556
Permanent link to this record
 
 
Author S.K. Jemni; Mohamed Ali Souibgui; Yousri Kessentini; Alicia Fornes
Title Enhance to Read Better: A Multi-Task Adversarial Network for Handwritten Document Image Enhancement Type Journal Article
Year 2022 Publication Pattern Recognition Abbreviated Journal PR
Volume 123 Issue Pages 108370
Keywords
Abstract Handwritten document images can be highly affected by degradation for different reasons: Paper ageing, daily-life scenarios (wrinkles, dust, etc.), bad scanning process and so on. These artifacts raise many readability issues for current Handwritten Text Recognition (HTR) algorithms and severely devalue their efficiency. In this paper, we propose an end to end architecture based on Generative Adversarial Networks (GANs) to recover the degraded documents into a and form. Unlike the most well-known document binarization methods, which try to improve the visual quality of the degraded document, the proposed architecture integrates a handwritten text recognizer that promotes the generated document image to be more readable. To the best of our knowledge, this is the first work to use the text information while binarizing handwritten documents. Extensive experiments conducted on degraded Arabic and Latin handwritten documents demonstrate the usefulness of integrating the recognizer within the GAN architecture, which improves both the visual quality and the readability of the degraded document images. Moreover, we outperform the state of the art in H-DIBCO challenges, after fine tuning our pre-trained model with synthetically degraded Latin handwritten images, on this task.
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; 600.124; 600.121; 602.230 Approved no
Call Number Admin @ si @ JSK2022 Serial (up) 3613
Permanent link to this record
 
 
Author Mohamed Ali Souibgui; Ali Furkan Biten; Sounak Dey; Alicia Fornes; Yousri Kessentini; Lluis Gomez; Dimosthenis Karatzas; Josep Llados
Title One-shot Compositional Data Generation for Low Resource Handwritten Text Recognition Type Conference Article
Year 2022 Publication Winter Conference on Applications of Computer Vision Abbreviated Journal
Volume Issue Pages
Keywords Document Analysis
Abstract Low resource Handwritten Text Recognition (HTR) is a hard problem due to the scarce annotated data and the very limited linguistic information (dictionaries and language models). This appears, for example, in the case of historical ciphered manuscripts, which are usually written with invented alphabets to hide the content. Thus, in this paper we address this problem through a data generation technique based on Bayesian Program Learning (BPL). Contrary to traditional generation approaches, which require a huge amount of annotated images, our method is able to generate human-like handwriting using only one sample of each symbol from the desired alphabet. After generating symbols, we create synthetic lines to train state-of-the-art HTR architectures in a segmentation free fashion. Quantitative and qualitative analyses were carried out and confirm the effectiveness of the proposed method, achieving competitive results compared to the usage of real annotated data.
Address Virtual; January 2022
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 WACV
Notes DAG; 602.230; 600.140 Approved no
Call Number Admin @ si @ SBD2022 Serial (up) 3615
Permanent link to this record
 
 
Author Minesh Mathew; Viraj Bagal; Ruben Tito; Dimosthenis Karatzas; Ernest Valveny; C.V. Jawahar
Title InfographicVQA Type Conference Article
Year 2022 Publication Winter Conference on Applications of Computer Vision Abbreviated Journal
Volume Issue Pages 1697-1706
Keywords Document Analysis Datasets; Evaluation and Comparison of Vision Algorithms; Vision and Languages
Abstract Infographics communicate information using a combination of textual, graphical and visual elements. This work explores the automatic understanding of infographic images by using a Visual Question Answering technique. To this end, we present InfographicVQA, a new dataset comprising a diverse collection of infographics and question-answer annotations. The questions require methods that jointly reason over the document layout, textual content, graphical elements, and data visualizations. We curate the dataset with an emphasis on questions that require elementary reasoning and basic arithmetic skills. For VQA on the dataset, we evaluate two Transformer-based strong baselines. Both the baselines yield unsatisfactory results compared to near perfect human performance on the dataset. The results suggest that VQA on infographics--images that are designed to communicate information quickly and clearly to human brain--is ideal for benchmarking machine understanding of complex document images. The dataset is available for download at docvqa. org
Address Virtual; Waikoloa; Hawai; USA; January 2022
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 WACV
Notes DAG; 600.155 Approved no
Call Number MBT2022 Serial (up) 3625
Permanent link to this record
 
 
Author Vacit Oguz Yazici
Title Towards Smart Fashion: Visual Recognition of Products and Attributes Type Book Whole
Year 2022 Publication PhD Thesis, Universitat Autonoma de Barcelona-CVC Abbreviated Journal
Volume Issue Pages
Keywords
Abstract Artificial intelligence is innovating the fashion industry by proposing new applications and solutions to the problems encountered by researchers and engineers working in the industry. In this thesis, we address three of these problems. In the first part of the thesis, we tackle the problem of multi-label image classification which is very related to fashion attribute recognition. In the second part of the thesis, we address two problems that are specific to fashion. Firstly, we address the problem of main product detection which is the task of associating correct image parts (e.g. bounding boxes) with the fashion product being sold. Secondly, we address the problem of color naming for multicolored fashion items. The task of multi-label image classification consists in assigning various concepts such as objects or attributes to images. Usually, there are dependencies that can be learned between the concepts to capture label correlations (chair and table classes are more likely to co-exist than chair and giraffe).
If we treat the multi-label image classification problem as an orderless set prediction problem, we can exploit recurrent neural networks (RNN) to capture label correlations. However, RNNs are trained to predict ordered sequences of tokens, so if the order of the predicted sequence is different than the order of the ground truth sequence, there will be penalization although the predictions are correct. Therefore, in the first part of the thesis, we propose an orderless loss function which will order the labels in the ground truth sequence dynamically in a way that the minimum loss is achieved. This results in a significant improvement of RNN models on multi-label image classification over the previous methods.
However, RNNs suffer from long term dependencies when the cardinality of set grows bigger. The decoding process might stop early if the current hidden state cannot find any object and outputs the termination token. This would cause the remaining classes not to be predicted and lower recall metric. Transformers can be used to avoid the long term dependency problem exploiting their selfattention modules that process sequential data simultaneously. Consequently, we propose a novel transformer model for multi-label image classification which surpasses the state-of-the-art results by a large margin.
In the second part of thesis, we focus on two fashion-specific problems. Main product detection is the task of associating image parts with the fashion product that is being sold, generally using associated textual metadata (product title or description). Normally, in fashion e-commerces, products are represented by multiple images where a person wears the product along with other fashion items. If all the fashion items in the images are marked with bounding boxes, we can use the textual metadata to decide which item is the main product. The initial work treated each of these images independently, discarding the fact that they all belong to the same product. In this thesis, we represent the bounding boxes from all the images as nodes in a fully connected graph. This allows the algorithm to learn relations between the nodes during training and take the entire context into account for the final decision. Our algorithm results in a significant improvement of the state-ofthe-art.
Moreover, we address the problem of color naming for multicolored fashion items, which is a challenging task due to the external factors such as illumination changes or objects that act as clutter. In the context of multi-label classification, the vaguely defined lines between the classes in the color space cause ambiguity. For example, a shade of blue which is very close to green might cause the model to incorrectly predict the color blue and green at the same time. Based on this, models trained for color naming are expected to recognize the colors and their quantities in both single colored and multicolored fashion items. Therefore, in this thesis, we propose a novel architecture with an additional head that explicitly estimates the number of colors in fashion items. This removes the ambiguity problem and results in better color naming performance.
Address January 2022
Corporate Author Thesis Ph.D. thesis
Publisher IMPRIMA Place of Publication Editor Joost Van de Weijer;Arnau Ramisa
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN 978-84-122714-6-1 Medium
Area Expedition Conference
Notes LAMP Approved no
Call Number Admin @ si @ Ogu2022 Serial (up) 3631
Permanent link to this record
 
 
Author Joakim Bruslund Haurum; Meysam Madadi; Sergio Escalera; Thomas B. Moeslund
Title Multi-Task Classification of Sewer Pipe Defects and Properties Using a Cross-Task Graph Neural Network Decoder Type Conference Article
Year 2022 Publication Winter Conference on Applications of Computer Vision Abbreviated Journal
Volume Issue Pages 2806-2817
Keywords Vision Systems; Applications Multi-Task Classification
Abstract The sewerage infrastructure is one of the most important and expensive infrastructures in modern society. In order to efficiently manage the sewerage infrastructure, automated sewer inspection has to be utilized. However, while sewer
defect classification has been investigated for decades, little attention has been given to classifying sewer pipe properties such as water level, pipe material, and pipe shape, which are needed to evaluate the level of sewer pipe deterioration.
In this work we classify sewer pipe defects and properties concurrently and present a novel decoder-focused multi-task classification architecture Cross-Task Graph Neural Network (CT-GNN), which refines the disjointed per-task predictions using cross-task information. The CT-GNN architecture extends the traditional disjointed task-heads decoder, by utilizing a cross-task graph and unique class node embeddings. The cross-task graph can either be determined a priori based on the conditional probability between the task classes or determined dynamically using self-attention.
CT-GNN can be added to any backbone and trained end-toend at a small increase in the parameter count. We achieve state-of-the-art performance on all four classification tasks in the Sewer-ML dataset, improving defect classification and
water level classification by 5.3 and 8.0 percentage points, respectively. We also outperform the single task methods as well as other multi-task classification approaches while introducing 50 times fewer parameters than previous modelfocused approaches.
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 WACV
Notes HUPBA; no proj Approved no
Call Number Admin @ si @ BME2022 Serial (up) 3638
Permanent link to this record
 
 
Author Meysam Madadi; Sergio Escalera; Xavier Baro; Jordi Gonzalez
Title End-to-end Global to Local CNN Learning for Hand Pose Recovery in Depth data Type Journal Article
Year 2022 Publication IET Computer Vision Abbreviated Journal IETCV
Volume 16 Issue 1 Pages 50-66
Keywords Computer vision; data acquisition; human computer interaction; learning (artificial intelligence); pose estimation
Abstract Despite recent advances in 3D pose estimation of human hands, especially thanks to the advent of CNNs and depth cameras, this task is still far from being solved. This is mainly due to the highly non-linear dynamics of fingers, which make hand model training a challenging task. In this paper, we exploit a novel hierarchical tree-like structured CNN, in which branches are trained to become specialized in predefined subsets of hand joints, called local poses. We further fuse local pose features, extracted from hierarchical CNN branches, to learn higher order dependencies among joints in the final pose by end-to-end training. Lastly, the loss function used is also defined to incorporate appearance and physical constraints about doable hand motion and deformation. Finally, we introduce a non-rigid data augmentation approach to increase the amount of training depth data. Experimental results suggest that feeding a tree-shaped CNN, specialized in local poses, into a fusion network for modeling joints correlations and dependencies, helps to increase the precision of final estimations, outperforming state-of-the-art results on NYU and SyntheticHand datasets.
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 HUPBA; ISE; 600.098; 600.119 Approved no
Call Number Admin @ si @ MEB2022 Serial (up) 3652
Permanent link to this record
 
 
Author Razieh Rastgoo; Kourosh Kiani; Sergio Escalera
Title Real-time Isolated Hand Sign Language RecognitioN Using Deep Networks and SVD Type Journal
Year 2022 Publication Journal of Ambient Intelligence and Humanized Computing Abbreviated Journal
Volume 13 Issue Pages 591–611
Keywords
Abstract One of the challenges in computer vision models, especially sign language, is real-time recognition. In this work, we present a simple yet low-complex and efficient model, comprising single shot detector, 2D convolutional neural network, singular value decomposition (SVD), and long short term memory, to real-time isolated hand sign language recognition (IHSLR) from RGB video. We employ the SVD method as an efficient, compact, and discriminative feature extractor from the estimated 3D hand keypoints coordinators. Despite the previous works that employ the estimated 3D hand keypoints coordinates as raw features, we propose a novel and revolutionary way to apply the SVD to the estimated 3D hand keypoints coordinates to get more discriminative features. SVD method is also applied to the geometric relations between the consecutive segments of each finger in each hand and also the angles between these sections. We perform a detailed analysis of recognition time and accuracy. One of our contributions is that this is the first time that the SVD method is applied to the hand pose parameters. Results on four datasets, RKS-PERSIANSIGN (99.5±0.04), First-Person (91±0.06), ASVID (93±0.05), and isoGD (86.1±0.04), confirm the efficiency of our method in both accuracy (mean+std) and time recognition. Furthermore, our model outperforms or gets competitive results with the state-of-the-art alternatives in IHSLR and hand action recognition.
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 HUPBA; no proj Approved no
Call Number Admin @ si @ RKE2022a Serial (up) 3660
Permanent link to this record
 
 
Author Ali Furkan Biten; Lluis Gomez; Dimosthenis Karatzas
Title Let there be a clock on the beach: Reducing Object Hallucination in Image Captioning Type Conference Article
Year 2022 Publication Winter Conference on Applications of Computer Vision Abbreviated Journal
Volume Issue Pages 1381-1390
Keywords Measurement; Training; Visualization; Analytical models; Computer vision; Computational modeling; Training data
Abstract Explaining an image with missing or non-existent objects is known as object bias (hallucination) in image captioning. This behaviour is quite common in the state-of-the-art captioning models which is not desirable by humans. To decrease the object hallucination in captioning, we propose three simple yet efficient training augmentation method for sentences which requires no new training data or increase
in the model size. By extensive analysis, we show that the proposed methods can significantly diminish our models’ object bias on hallucination metrics. Moreover, we experimentally demonstrate that our methods decrease the dependency on the visual features. All of our code, configuration files and model weights are available online.
Address Virtual; Waikoloa; Hawai; USA; January 2022
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 WACV
Notes DAG; 600.155; 302.105 Approved no
Call Number Admin @ si @ BGK2022 Serial (up) 3662
Permanent link to this record
 
 
Author Ali Furkan Biten; Andres Mafla; Lluis Gomez; Dimosthenis Karatzas
Title Is An Image Worth Five Sentences? A New Look into Semantics for Image-Text Matching Type Conference Article
Year 2022 Publication Winter Conference on Applications of Computer Vision Abbreviated Journal
Volume Issue Pages 1391-1400
Keywords Measurement; Training; Integrated circuits; Annotations; Semantics; Training data; Semisupervised learning
Abstract The task of image-text matching aims to map representations from different modalities into a common joint visual-textual embedding. However, the most widely used datasets for this task, MSCOCO and Flickr30K, are actually image captioning datasets that offer a very limited set of relationships between images and sentences in their ground-truth annotations. This limited ground truth information forces us to use evaluation metrics based on binary relevance: given a sentence query we consider only one image as relevant. However, many other relevant images or captions may be present in the dataset. In this work, we propose two metrics that evaluate the degree of semantic relevance of retrieved items, independently of their annotated binary relevance. Additionally, we incorporate a novel strategy that uses an image captioning metric, CIDEr, to define a Semantic Adaptive Margin (SAM) to be optimized in a standard triplet loss. By incorporating our formulation to existing models, a large improvement is obtained in scenarios where available training data is limited. We also demonstrate that the performance on the annotated image-caption pairs is maintained while improving on other non-annotated relevant items when employing the full training set. The code for our new metric can be found at github. com/furkanbiten/ncsmetric and the model implementation at github. com/andrespmd/semanticadaptive_margin.
Address Virtual; Waikoloa; Hawai; USA; January 2022
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 WACV
Notes DAG; 600.155; 302.105; Approved no
Call Number Admin @ si @ BMG2022 Serial (up) 3663
Permanent link to this record