Ozan Caglayan, Walid Aransa, Adrien Bardet, Mercedes Garcia-Martinez, Fethi Bougares, Loic Barrault, et al. (2017). LIUM-CVC Submissions for WMT17 Multimodal Translation Task. In 2nd Conference on Machine Translation.
Abstract: This paper describes the monomodal and multimodal Neural Machine Translation systems developed by LIUM and CVC for WMT17 Shared Task on Multimodal Translation. We mainly explored two multimodal architectures where either global visual features or convolutional feature maps are integrated in order to benefit from visual context. Our final systems ranked first for both En-De and En-Fr language pairs according to the automatic evaluation metrics METEOR and BLEU.
|
Ozan Caglayan, Adrien Bardet, Fethi Bougares, Loic Barrault, Kai Wang, Marc Masana, et al. (2018). LIUM-CVC Submissions for WMT18 Multimodal Translation Task. In 3rd Conference on Machine Translation.
Abstract: This paper describes the multimodal Neural Machine Translation systems developed by LIUM and CVC for WMT18 Shared Task on Multimodal Translation. This year we propose several modifications to our previou multimodal attention architecture in order to better integrate convolutional features and refine them using encoder-side information. Our final constrained submissions
ranked first for English→French and second for English→German language pairs among the constrained submissions according to the automatic evaluation metric METEOR.
|
Spencer Low, Oliver Nina, Angel Sappa, Erik Blasch, & Nathan Inkawhich. (2022). Multi-Modal Aerial View Object Classification Challenge Results – PBVS 2022. In IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (pp. 350–358).
Abstract: This paper details the results and main findings of the second iteration of the Multi-modal Aerial View Object Classification (MAVOC) challenge. The primary goal of both MAVOC challenges is to inspire research into methods for building recognition models that utilize both synthetic aperture radar (SAR) and electro-optical (EO) imagery. Teams are encouraged to develop multi-modal approaches that incorporate complementary information from both domains. While the 2021 challenge showed a proof of concept that both modalities could be used together, the 2022 challenge focuses on the detailed multi-modal methods. The 2022 challenge uses the same UNIfied Coincident Optical and Radar for recognitioN (UNICORN) dataset and competition format that was used in 2021. Specifically, the challenge focuses on two tasks, (1) SAR classification and (2) SAR + EO classification. The bulk of this document is dedicated to discussing the top performing methods and describing their performance on our blind test set. Notably, all of the top ten teams outperform a Resnet-18 baseline. For SAR classification, the top team showed a 129% improvement over baseline and an 8% average improvement from the 2021 winner. The top team for SAR + EO classification shows a 165% improvement with a 32% average improvement over 2021.
|
Ole Larsen, Petia Radeva, & Enric Marti. (1995). Bounds on the optimal elasticity parameters for a snake. Image Analysis and Processing, , 37–42.
Abstract: This paper develops a formalism by which an estimate for the upper and lower bounds for the elasticity parameters for a snake can be obtained. Objects different in size and shape give rise to different bounds. The bounds can be obtained based on an analysis of the shape of the object of interest. Experiments on synthetic images show a good correlation between the estimated behaviour of the snake and the one actually observed. Experiments on real X-ray images show that the parameters for optimal segmentation lie within the estimated bounds.
|
Angel Sappa, P. Carvajal, Cristhian A. Aguilera-Carrasco, Miguel Oliveira, Dennis Romero, & Boris X. Vintimilla. (2016). Wavelet based visible and infrared image fusion: a comparative study. SENS - Sensors, 16(6), 1–15.
Abstract: This paper evaluates different wavelet-based cross-spectral image fusion strategies adopted to merge visible and infrared images. The objective is to find the best setup independently of the evaluation metric used to measure the performance. Quantitative performance results are obtained with state of the art approaches together with adaptations proposed in the current work. The options evaluated in the current work result from the combination of different setups in the wavelet image decomposition stage together with different fusion strategies for the final merging stage that generates the resulting representation. Most of the approaches evaluate results according to the application for which they are intended for. Sometimes a human observer is selected to judge the quality of the obtained results. In the current work, quantitative values are considered in order to find correlations between setups and performance of obtained results; these correlations can be used to define a criteria for selecting the best fusion strategy for a given pair of cross-spectral images. The whole procedure is evaluated with a large set of correctly registered visible and infrared image pairs, including both Near InfraRed (NIR) and Long Wave InfraRed (LWIR).
Keywords: Image fusion; fusion evaluation metrics; visible and infrared imaging; discrete wavelet transform
|
Raul Gomez, Ali Furkan Biten, Lluis Gomez, Jaume Gibert, Marçal Rusiñol, & Dimosthenis Karatzas. (2019). Selective Style Transfer for Text. In 15th International Conference on Document Analysis and Recognition (pp. 805–812).
Abstract: This paper explores the possibilities of image style transfer applied to text maintaining the original transcriptions. Results on different text domains (scene text, machine printed text and handwritten text) and cross-modal results demonstrate that this is feasible, and open different research lines. Furthermore, two architectures for selective style transfer, which means
transferring style to only desired image pixels, are proposed. Finally, scene text selective style transfer is evaluated as a data augmentation technique to expand scene text detection datasets, resulting in a boost of text detectors performance. Our implementation of the described models is publicly available.
Keywords: transfer; text style transfer; data augmentation; scene text detection
|
Anjan Dutta, Jaume Gibert, Josep Llados, Horst Bunke, & Umapada Pal. (2012). Combination of Product Graph and Random Walk Kernel for Symbol Spotting in Graphical Documents. In 21st International Conference on Pattern Recognition (pp. 1663–1666).
Abstract: This paper explores the utilization of product graph for spotting symbols on graphical documents. Product graph is intended to find the candidate subgraphs or components in the input graph containing the paths similar to the query graph. The acute angle between two edges and their length ratio are considered as the node labels. In a second step, each of the candidate subgraphs in the input graph is assigned with a distance measure computed by a random walk kernel. Actually it is the minimum of the distances of the component to all the components of the model graph. This distance measure is then used to eliminate dissimilar components. The remaining neighboring components are grouped and the grouped zone is considered as a retrieval zone of a symbol similar to the queried one. The entire method works online, i.e., it doesn't need any preprocessing step. The present paper reports the initial results of the method, which are very encouraging.
|
Patricia Suarez, Angel Sappa, & Boris X. Vintimilla. (2017). Colorizing Infrared Images through a Triplet Conditional DCGAN Architecture. In 19th international conference on image analysis and processing.
Abstract: This paper focuses on near infrared (NIR) image colorization by using a Conditional Deep Convolutional Generative Adversarial Network (CDCGAN) architecture model. The proposed architecture is based on the usage of a conditional probabilistic generative model. Firstly, it learns to colorize the given input image, by using a triplet model architecture that tackle every channel in an independent way. In the proposed model, the nal layer of red channel consider the infrared image to enhance the details, resulting in a sharp RGB image. Then, in the second stage, a discriminative model is used to estimate the probability that the generated image came from the training dataset, rather than the image automatically generated. Experimental results with a large set of real images are provided showing the validity of the proposed approach. Additionally, the proposed approach is compared with a state of the art approach showing better results.
Keywords: CNN in Multispectral Imaging; Image Colorization
|
Patricia Suarez, Angel Sappa, & Boris X. Vintimilla. (2017). Learning to Colorize Infrared Images. In 15th International Conference on Practical Applications of Agents and Multi-Agent System.
Abstract: This paper focuses on near infrared (NIR) image colorization by using a Generative Adversarial Network (GAN) architecture model. The proposed architecture consists of two stages. Firstly, it learns to colorize the given input, resulting in a RGB image. Then, in the second stage, a discriminative model is used to estimate the probability that the generated image came from the training dataset, rather than the image automatically generated. The proposed model starts the learning process from scratch, because our set of images is very di erent from the dataset used in existing pre-trained models, so transfer learning strategies cannot be used. Infrared image colorization is an important problem when human perception need to be considered, e.g, in remote sensing applications. Experimental results with a large set of real images are provided showing the validity of the proposed approach.
Keywords: CNN in multispectral imaging; Image colorization
|
Lluis Gomez, & Dimosthenis Karatzas. (2016). A fine-grained approach to scene text script identification. In 12th IAPR Workshop on Document Analysis Systems (pp. 192–197).
Abstract: This paper focuses on the problem of script identification in unconstrained scenarios. Script identification is an important prerequisite to recognition, and an indispensable condition for automatic text understanding systems designed for multi-language environments. Although widely studied for document images and handwritten documents, it remains an almost unexplored territory for scene text images. We detail a novel method for script identification in natural images that combines convolutional features and the Naive-Bayes Nearest Neighbor classifier. The proposed framework efficiently exploits the discriminative power of small stroke-parts, in a fine-grained classification framework. In addition, we propose a new public benchmark dataset for the evaluation of joint text detection and script identification in natural scenes. Experiments done in this new dataset demonstrate that the proposed method yields state of the art results, while it generalizes well to different datasets and variable number of scripts. The evidence provided shows that multi-lingual scene text recognition in the wild is a viable proposition. Source code of the proposed method is made available online.
|
Ruth Aylett, Ginevra Castellano, Bogdan Raducanu, Ana Paiva, & Marc Hanheide. (2011). Long-term socially perceptive and interactive robot companions: challenges and future perspectives. In 13th International Conference on Multimodal Interaction (pp. 323–326). ACM.
Abstract: This paper gives a brief overview of the challenges for multi-model perception and generation applied to robot companions located in human social environments. It reviews the current position in both perception and generation and the immediate technical challenges and goes on to consider the extra issues raised by embodiment and social context. Finally, it briefly discusses the impact of systems that must function continually over months rather than just for a few hours.
Keywords: human-robot interaction, multimodal interaction, social robotics
|
Francesco Brughi, Debora Gil, Llorenç Badiella, Eva Jove Casabella, & Oriol Ramos Terrades. (2014). Exploring the impact of inter-query variability on the performance of retrieval systems. In 11th International Conference on Image Analysis and Recognition (Vol. 8814, 413–420). LNCS. Springer International Publishing.
Abstract: This paper introduces a framework for evaluating the performance of information retrieval systems. Current evaluation metrics provide an average score that does not consider performance variability across the query set. In this manner, conclusions lack of any statistical significance, yielding poor inference to cases outside the query set and possibly unfair comparisons. We propose to apply statistical methods in order to obtain a more informative measure for problems in which different query classes can be identified. In this context, we assess the performance variability on two levels: overall variability across the whole query set and specific query class-related variability. To this end, we estimate confidence bands for precision-recall curves, and we apply ANOVA in order to assess the significance of the performance across different query classes.
|
Victor Ponce, Hugo Jair Escalante, Sergio Escalera, & Xavier Baro. (2015). Gesture and Action Recognition by Evolved Dynamic Subgestures. In 26th British Machine Vision Conference (129.pp. 1–129.13).
Abstract: This paper introduces a framework for gesture and action recognition based on the evolution of temporal gesture primitives, or subgestures. Our work is inspired on the principle of producing genetic variations within a population of gesture subsequences, with the goal of obtaining a set of gesture units that enhance the generalization capability of standard gesture recognition approaches. In our context, gesture primitives are evolved over time using dynamic programming and generative models in order to recognize complex actions. In few generations, the proposed subgesture-based representation
of actions and gestures outperforms the state of the art results on the MSRDaily3D and MSRAction3D datasets.
|
Gemma Rotger, Francesc Moreno-Noguer, Felipe Lumbreras, & Antonio Agudo. (2019). Detailed 3D face reconstruction from a single RGB image. JWSCG - Journal of WSCG, 103–112.
Abstract: This paper introduces a method to obtain a detailed 3D reconstruction of facial skin from a single RGB image.
To this end, we propose the exclusive use of an input image without requiring any information about the observed material nor training data to model the wrinkle properties. They are detected and characterized directly from the image via a simple and effective parametric model, determining several features such as location, orientation, width, and height. With these ingredients, we propose to minimize a photometric error to retrieve the final detailed 3D map, which is initialized by current techniques based on deep learning. In contrast with other approaches, we only require estimating a depth parameter, making our approach fast and intuitive. Extensive experimental evaluation is presented in a wide variety of synthetic and real images, including different skin properties and facial
expressions. In all cases, our method outperforms the current approaches regarding 3D reconstruction accuracy, providing striking results for both large and fine wrinkles.
Keywords: 3D Wrinkle Reconstruction; Face Analysis, Optimization.
|
Egils Avots, M. Daneshmanda, Andres Traumann, Sergio Escalera, & G. Anbarjafaria. (2016). Automatic garment retexturing based on infrared information. CG - Computers & Graphics, 59, 28–38.
Abstract: This paper introduces a new automatic technique for garment retexturing using a single static image along with the depth and infrared information obtained using the Microsoft Kinect II as the RGB-D acquisition device. First, the garment is segmented out from the image using either the Breadth-First Search algorithm or the semi-automatic procedure provided by the GrabCut method. Then texture domain coordinates are computed for each pixel belonging to the garment using normalised 3D information. Afterwards, shading is applied to the new colours from the texture image. As the main contribution of the proposed method, the latter information is obtained based on extracting a linear map transforming the colour present on the infrared image to that of the RGB colour channels. One of the most important impacts of this strategy is that the resulting retexturing algorithm is colour-, pattern- and lighting-invariant. The experimental results show that it can be used to produce realistic representations, which is substantiated through implementing it under various experimentation scenarios, involving varying lighting intensities and directions. Successful results are accomplished also on video sequences, as well as on images of subjects taking different poses. Based on the Mean Opinion Score analysis conducted on many randomly chosen users, it has been shown to produce more realistic-looking results compared to the existing state-of-the-art methods suggested in the literature. From a wide perspective, the proposed method can be used for retexturing all sorts of segmented surfaces, although the focus of this study is on garment retexturing, and the investigation of the configurations is steered accordingly, since the experiments target an application in the context of virtual fitting rooms.
Keywords: Garment Retexturing; Texture Mapping; Infrared Images; RGB-D Acquisition Devices; Shading
|
