Emanuele Vivoli, Ali Furkan Biten, Andres Mafla, Dimosthenis Karatzas, & Lluis Gomez. (2022). MUST-VQA: MUltilingual Scene-text VQA. In Proceedings European Conference on Computer Vision Workshops (Vol. 13804, 345–358). LNCS.
Abstract: In this paper, we present a framework for Multilingual Scene Text Visual Question Answering that deals with new languages in a zero-shot fashion. Specifically, we consider the task of Scene Text Visual Question Answering (STVQA) in which the question can be asked in different languages and it is not necessarily aligned to the scene text language. Thus, we first introduce a natural step towards a more generalized version of STVQA: MUST-VQA. Accounting for this, we discuss two evaluation scenarios in the constrained setting, namely IID and zero-shot and we demonstrate that the models can perform on a par on a zero-shot setting. We further provide extensive experimentation and show the effectiveness of adapting multilingual language models into STVQA tasks.
Keywords: Visual question answering; Scene text; Translation robustness; Multilingual models; Zero-shot transfer; Power of language models
|
Sergi Garcia Bordils, Andres Mafla, Ali Furkan Biten, Oren Nuriel, Aviad Aberdam, Shai Mazor, et al. (2022). Out-of-Vocabulary Challenge Report. In Proceedings European Conference on Computer Vision Workshops (Vol. 13804, 359–375). LNCS.
Abstract: This paper presents final results of the Out-Of-Vocabulary 2022 (OOV) challenge. The OOV contest introduces an important aspect that is not commonly studied by Optical Character Recognition (OCR) models, namely, the recognition of unseen scene text instances at training time. The competition compiles a collection of public scene text datasets comprising of 326,385 images with 4,864,405 scene text instances, thus covering a wide range of data distributions. A new and independent validation and test set is formed with scene text instances that are out of vocabulary at training time. The competition was structured in two tasks, end-to-end and cropped scene text recognition respectively. A thorough analysis of results from baselines and different participants is presented. Interestingly, current state-of-the-art models show a significant performance gap under the newly studied setting. We conclude that the OOV dataset proposed in this challenge will be an essential area to be explored in order to develop scene text models that achieve more robust and generalized predictions.
|
Andrea Gemelli, Sanket Biswas, Enrico Civitelli, Josep Llados, & Simone Marinai. (2022). Doc2Graph: A Task Agnostic Document Understanding Framework Based on Graph Neural Networks. In 17th European Conference on Computer Vision Workshops (Vol. 13804, 329–344). LNCS.
Abstract: Geometric Deep Learning has recently attracted significant interest in a wide range of machine learning fields, including document analysis. The application of Graph Neural Networks (GNNs) has become crucial in various document-related tasks since they can unravel important structural patterns, fundamental in key information extraction processes. Previous works in the literature propose task-driven models and do not take into account the full power of graphs. We propose Doc2Graph, a task-agnostic document understanding framework based on a GNN model, to solve different tasks given different types of documents. We evaluated our approach on two challenging datasets for key information extraction in form understanding, invoice layout analysis and table detection.
|
Gabriel Villalonga, Sebastian Ramos, German Ros, David Vazquez, & Antonio Lopez. (2014). 3d Pedestrian Detection via Random Forest.
Abstract: Our demo focuses on showing the extraordinary performance of our novel 3D pedestrian detector along with its simplicity and real-time capabilities. This detector has been designed for autonomous driving applications, but it can also be applied in other scenarios that cover both outdoor and indoor applications.
Our pedestrian detector is based on the combination of a random forest classifier with HOG-LBP features and the inclusion of a preprocessing stage based on 3D scene information in order to precisely determinate the image regions where the detector should search for pedestrians. This approach ends up in a high accurate system that runs real-time as it is required by many computer vision and robotics applications.
Keywords: Pedestrian Detection
|
|
Eduard Vazquez, Joost Van de Weijer, & Ramon Baldrich. (2008). Image Segmentation in the Presence of Shadows and Highligts. In 10th European Conference on Computer Vision (Vol. 5305, 1–14). LNCS.
|
Marco Pedersoli, Jordi Gonzalez, Andrew Bagdanov, & Juan J. Villanueva. (2010). Recursive Coarse-to-Fine Localization for fast Object Recognition. In 11th European Conference on Computer Vision (Vol. 6313, 280–293). LNCS. Springer Berlin Heidelberg.
Abstract: Cascading techniques are commonly used to speed-up the scan of an image for object detection. However, cascades of detectors are slow to train due to the high number of detectors and corresponding thresholds to learn. Furthermore, they do not use any prior knowledge about the scene structure to decide where to focus the search. To handle these problems, we propose a new way to scan an image, where we couple a recursive coarse-to-fine refinement together with spatial constraints of the object location. For doing that we split an image into a set of uniformly distributed neighborhood regions, and for each of these we apply a local greedy search over feature resolutions. The neighborhood is defined as a scanning region that only one object can occupy. Therefore the best hypothesis is obtained as the location with maximum score and no thresholds are needed. We present an implementation of our method using a pyramid of HOG features and we evaluate it on two standard databases, VOC2007 and INRIA dataset. Results show that the Recursive Coarse-to-Fine Localization (RCFL) achieves a 12x speed-up compared to standard sliding windows. Compared with a cascade of multiple resolutions approach our method has slightly better performance in speed and Average-Precision. Furthermore, in contrast to cascading approach, the speed-up is independent of image conditions, the number of detected objects and clutter.
|
Carles Fernandez, Jordi Gonzalez, & Xavier Roca. (2010). Automatic Learning of Background Semantics in Generic Surveilled Scenes. In 11th European Conference on Computer Vision (Vol. 6313, 678–692). LNCS. Springer Berlin Heidelberg.
Abstract: Advanced surveillance systems for behavior recognition in outdoor traffic scenes depend strongly on the particular configuration of the scenario. Scene-independent trajectory analysis techniques statistically infer semantics in locations where motion occurs, and such inferences are typically limited to abnormality. Thus, it is interesting to design contributions that automatically categorize more specific semantic regions. State-of-the-art approaches for unsupervised scene labeling exploit trajectory data to segment areas like sources, sinks, or waiting zones. Our method, in addition, incorporates scene-independent knowledge to assign more meaningful labels like crosswalks, sidewalks, or parking spaces. First, a spatiotemporal scene model is obtained from trajectory analysis. Subsequently, a so-called GI-MRF inference process reinforces spatial coherence, and incorporates taxonomy-guided smoothness constraints. Our method achieves automatic and effective labeling of conceptual regions in urban scenarios, and is robust to tracking errors. Experimental validation on 5 surveillance databases has been conducted to assess the generality and accuracy of the segmentations. The resulting scene models are used for model-based behavior analysis.
|
Jose Manuel Alvarez, Theo Gevers, Y. LeCun, & Antonio Lopez. (2012). Road Scene Segmentation from a Single Image. In 12th European Conference on Computer Vision (Vol. 7578, pp. 376–389). LNCS. Springer Berlin Heidelberg.
Abstract: Road scene segmentation is important in computer vision for different applications such as autonomous driving and pedestrian detection. Recovering the 3D structure of road scenes provides relevant contextual information to improve their understanding.
In this paper, we use a convolutional neural network based algorithm to learn features from noisy labels to recover the 3D scene layout of a road image. The novelty of the algorithm relies on generating training labels by applying an algorithm trained on a general image dataset to classify on–board images. Further, we propose a novel texture descriptor based on a learned color plane fusion to obtain maximal uniformity in road areas. Finally, acquired (off–line) and current (on–line) information are combined to detect road areas in single images.
From quantitative and qualitative experiments, conducted on publicly available datasets, it is concluded that convolutional neural networks are suitable for learning 3D scene layout from noisy labels and provides a relative improvement of 7% compared to the baseline. Furthermore, combining color planes provides a statistical description of road areas that exhibits maximal uniformity and provides a relative improvement of 8% compared to the baseline. Finally, the improvement is even bigger when acquired and current information from a single image are combined
Keywords: road detection
|
Ivo Everts, Jan van Gemert, & Theo Gevers. (2012). Per-patch Descriptor Selection using Surface and Scene Properties. In 12th European Conference on Computer Vision (Vol. 7577, pp. 172–186). LNCS. Springer Berlin Heidelberg.
Abstract: Local image descriptors are generally designed for describing all possible image patches. Such patches may be subject to complex variations in appearance due to incidental object, scene and recording conditions. Because of this, a single-best descriptor for accurate image representation under all conditions does not exist. Therefore, we propose to automatically select from a pool of descriptors the one that is best suitable based on object surface and scene properties. These properties are measured on the fly from a single image patch through a set of attributes. Attributes are input to a classifier which selects the best descriptor. Our experiments on a large dataset of colored object patches show that the proposed selection method outperforms the best single descriptor and a-priori combinations of the descriptor pool.
|
Hamdi Dibeklioglu, Theo Gevers, & Albert Ali Salah. (2012). Are You Really Smiling at Me? Spontaneous versus Posed Enjoyment Smiles. In 12th European Conference on Computer Vision (Vol. 7574, pp. 525–538). LNCS. Springer Berlin Heidelberg.
Abstract: Smiling is an indispensable element of nonverbal social interaction. Besides, automatic distinction between spontaneous and posed expressions is important for visual analysis of social signals. Therefore, in this paper, we propose a method to distinguish between spontaneous and posed enjoyment smiles by using the dynamics of eyelid, cheek, and lip corner movements. The discriminative power of these movements, and the effect of different fusion levels are investigated on multiple databases. Our results improve the state-of-the-art. We also introduce the largest spontaneous/posed enjoyment smile database collected to date, and report new empirical and conceptual findings on smile dynamics. The collected database consists of 1240 samples of 400 subjects. Moreover, it has the unique property of having an age range from 8 to 76 years. Large scale experiments on the new database indicate that eyelid dynamics are highly relevant for smile classification, and there are age-related differences in smile dynamics.
|
Mohammad Rouhani, & Angel Sappa. (2012). Non-Rigid Shape Registration: A Single Linear Least Squares Framework. In 12th European Conference on Computer Vision (Vol. 7578, pp. 264–277). LNCS. Springer Berlin Heidelberg.
Abstract: This paper proposes a non-rigid registration formulation capturing both global and local deformations in a single framework. This formulation is based on a quadratic estimation of the registration distance together with a quadratic regularization term. Hence, the optimal transformation parameters are easily obtained by solving a liner system of equations, which guarantee a fast convergence. Experimental results with challenging 2D and 3D shapes are presented to show the validity of the proposed framework. Furthermore, comparisons with the most relevant approaches are provided.
|
Cesar de Souza, Adrien Gaidon, Eleonora Vig, & Antonio Lopez. (2016). Sympathy for the Details: Dense Trajectories and Hybrid Classification Architectures for Action Recognition. In 14th European Conference on Computer Vision (pp. 697–716). LNCS.
Abstract: Action recognition in videos is a challenging task due to the complexity of the spatio-temporal patterns to model and the difficulty to acquire and learn on large quantities of video data. Deep learning, although a breakthrough for image classification and showing promise for videos, has still not clearly superseded action recognition methods using hand-crafted features, even when training on massive datasets. In this paper, we introduce hybrid video classification architectures based on carefully designed unsupervised representations of hand-crafted spatio-temporal features classified by supervised deep networks. As we show in our experiments on five popular benchmarks for action recognition, our hybrid model combines the best of both worlds: it is data efficient (trained on 150 to 10000 short clips) and yet improves significantly on the state of the art, including recent deep models trained on millions of manually labelled images and videos.
|
Yaxing Wang, Chenshen Wu, Luis Herranz, Joost Van de Weijer, Abel Gonzalez-Garcia, & Bogdan Raducanu. (2018). Transferring GANs: generating images from limited data. In 15th European Conference on Computer Vision (Vol. 11210, pp. 220–236). LNCS.
Abstract: ransferring knowledge of pre-trained networks to new domains by means of fine-tuning is a widely used practice for applications based on discriminative models. To the best of our knowledge this practice has not been studied within the context of generative deep networks. Therefore, we study domain adaptation applied to image generation with generative adversarial networks. We evaluate several aspects of domain adaptation, including the impact of target domain size, the relative distance between source and target domain, and the initialization of conditional GANs. Our results show that using knowledge from pre-trained networks can shorten the convergence time and can significantly improve the quality of the generated images, especially when target data is limited. We show that these conclusions can also be drawn for conditional GANs even when the pre-trained model was trained without conditioning. Our results also suggest that density is more important than diversity and a dataset with one or few densely sampled classes is a better source model than more diverse datasets such as ImageNet or Places.
Keywords: Generative adversarial networks; Transfer learning; Domain adaptation; Image generation
|
Pau Rodriguez, Josep M. Gonfaus, Guillem Cucurull, Xavier Roca, & Jordi Gonzalez. (2018). Attend and Rectify: A Gated Attention Mechanism for Fine-Grained Recovery. In 15th European Conference on Computer Vision (Vol. 11212, pp. 357–372). LNCS.
Abstract: We propose a novel attention mechanism to enhance Convolutional Neural Networks for fine-grained recognition. It learns to attend to lower-level feature activations without requiring part annotations and uses these activations to update and rectify the output likelihood distribution. In contrast to other approaches, the proposed mechanism is modular, architecture-independent and efficient both in terms of parameters and computation required. Experiments show that networks augmented with our approach systematically improve their classification accuracy and become more robust to clutter. As a result, Wide Residual Networks augmented with our proposal surpasses the state of the art classification accuracies in CIFAR-10, the Adience gender recognition task, Stanford dogs, and UEC Food-100.
Keywords: Deep Learning; Convolutional Neural Networks; Attention
|
Lluis Gomez, Andres Mafla, Marçal Rusiñol, & Dimosthenis Karatzas. (2018). Single Shot Scene Text Retrieval. In 15th European Conference on Computer Vision (Vol. 11218, pp. 728–744). LNCS.
Abstract: Textual information found in scene images provides high level semantic information about the image and its context and it can be leveraged for better scene understanding. In this paper we address the problem of scene text retrieval: given a text query, the system must return all images containing the queried text. The novelty of the proposed model consists in the usage of a single shot CNN architecture that predicts at the same time bounding boxes and a compact text representation of the words in them. In this way, the text based image retrieval task can be casted as a simple nearest neighbor search of the query text representation over the outputs of the CNN over the entire image
database. Our experiments demonstrate that the proposed architecture
outperforms previous state-of-the-art while it offers a significant increase
in processing speed.
Keywords: Image retrieval; Scene text; Word spotting; Convolutional Neural Networks; Region Proposals Networks; PHOC
|
