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
|
Roberto Morales, Juan Quispe, & Eduardo Aguilar. (2023). Exploring multi-food detection using deep learning-based algorithms. In 13th International Conference on Pattern Recognition Systems (pp. 1–7).
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.
|
Gisel Bastidas-Guacho, Patricio Moreno, Boris X. Vintimilla, & Angel Sappa. (2023). Application on the Loop of Multimodal Image Fusion: Trends on Deep-Learning Based Approaches. In 13th International Conference on Pattern Recognition Systems (Vol. 14234, 25–36).
Abstract: Multimodal image fusion allows the combination of information from different modalities, which is useful for tasks such as object detection, edge detection, and tracking, to name a few. Using the fused representation for applications results in better task performance. There are several image fusion approaches, which have been summarized in surveys. However, the existing surveys focus on image fusion approaches where the application on the loop of multimodal image fusion is not considered. On the contrary, this study summarizes deep learning-based multimodal image fusion for computer vision (e.g., object detection) and image processing applications (e.g., semantic segmentation), that is, approaches where the application module leverages the multimodal fusion process to enhance the final result. Firstly, we introduce image fusion and the existing general frameworks for image fusion tasks such as multifocus, multiexposure and multimodal. Then, we describe the multimodal image fusion approaches. Next, we review the state-of-the-art deep learning multimodal image fusion approaches for vision applications. Finally, we conclude our survey with the trends of task-driven multimodal image fusion.
|
M. Ivasic-Kos, M. Pobar, & Jordi Gonzalez. (2019). Active Player Detection in Handball Videos Using Optical Flow and STIPs Based Measures. In 13th International Conference on Signal Processing and Communication Systems.
Abstract: In handball videos recorded during the training, multiple players are present in the scene at the same time. Although they all might move and interact, not all players contribute to the currently relevant exercise nor practice the given handball techniques. The goal of this experiment is to automatically determine players on training footage that perform given handball techniques and are therefore considered active. It is a very challenging task for which a precise object detector is needed that can handle cluttered scenes with poor illumination, with many players present in different sizes and distances from the camera, partially occluded, moving fast. To determine which of the detected players are active, additional information is needed about the level of player activity. Since many handball actions are characterized by considerable changes in speed, position, and variations in the player's appearance, we propose using spatio-temporal interest points (STIPs) and optical flow (OF). Therefore, we propose an active player detection method combining the YOLO object detector and two activity measures based on STIPs and OF. The performance of the proposed method and activity measures are evaluated on a custom handball video dataset acquired during handball training lessons.
|
Diego Alejandro Cheda, Daniel Ponsa, & Antonio Lopez. (2010). Camera Egomotion Estimation in the ADAS Context. In 13th International IEEE Annual Conference on Intelligent Transportation Systems (1415–1420).
Abstract: Camera-based Advanced Driver Assistance Systems (ADAS) have concentrated many research efforts in the last decades. Proposals based on monocular cameras require the knowledge of the camera pose with respect to the environment, in order to reach an efficient and robust performance. A common assumption in such systems is considering the road as planar, and the camera pose with respect to it as approximately known. However, in real situations, the camera pose varies along time due to the vehicle movement, the road slope, and irregularities on the road surface. Thus, the changes in the camera position and orientation (i.e., the egomotion) are critical information that must be estimated at every frame to avoid poor performances. This work focuses on egomotion estimation from a monocular camera under the ADAS context. We review and compare egomotion methods with simulated and real ADAS-like sequences. Basing on the results of our experiments, we show which of the considered nonlinear and linear algorithms have the best performance in this domain.
|
Eduardo Aguilar, Bhalaji Nagarajan, Rupali Khatun, Marc Bolaños, & Petia Radeva. (2020). Uncertainty Modeling and Deep Learning Applied to Food Image Analysis. In 13th International Joint Conference on Biomedical Engineering Systems and Technologies.
Abstract: Recently, computer vision approaches specially assisted by deep learning techniques have shown unexpected advancements that practically solve problems that never have been imagined to be automatized like face recognition or automated driving. However, food image recognition has received a little effort in the Computer Vision community. In this project, we review the field of food image analysis and focus on how to combine with two challenging research lines: deep learning and uncertainty modeling. After discussing our methodology to advance in this direction, we comment potential research, social and economic impact of the research on food image analysis.
|
Mohamed Ilyes Lakhal, Hakan Cevikalp, & Sergio Escalera. (2018). CRN: End-to-end Convolutional Recurrent Network Structure Applied to Vehicle Classification. In 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (Vol. 5, pp. 137–144).
Abstract: Vehicle type classification is considered to be a central part of Intelligent Traffic Systems. In the recent years, deep learning methods have emerged in as being the state-of-the-art in many computer vision tasks. In this paper, we present a novel yet simple deep learning framework for the vehicle type classification problem. We propose an end-to-end trainable system, that combines convolution neural network for feature extraction and recurrent neural network as a classifier. The recurrent network structure is used to handle various types of feature inputs, and at the same time allows to produce a single or a set of class predictions. In order to assess the effectiveness of our solution, we have conducted a set of experiments in two public datasets, obtaining state of the art results. In addition, we also report results on the newly released MIO-TCD dataset.
Keywords: Vehicle Classification; Deep Learning; End-to-end Learning
|
Jaume Gibert, & Ernest Valveny. (2010). Graph Embedding based on Nodes Attributes Representatives and a Graph of Words Representation. In I. Ulusoy and F. Escolano T. Windeatt R. C. W. In E.R. Hancock (Ed.), 13th International worshop on structural and syntactic pattern recognition and 8th international worshop on statistical pattern recognition (Vol. 6218, 223–232). LNCS. Springer Berlin Heidelberg.
Abstract: Although graph embedding has recently been used to extend statistical pattern recognition techniques to the graph domain, some existing embeddings are usually computationally expensive as they rely on classical graph-based operations. In this paper we present a new way to embed graphs into vector spaces by first encapsulating the information stored in the original graph under another graph representation by clustering the attributes of the graphs to be processed. This new representation makes the association of graphs to vectors an easy step by just arranging both node attributes and the adjacency matrix in the form of vectors. To test our method, we use two different databases of graphs whose nodes attributes are of different nature. A comparison with a reference method permits to show that this new embedding is better in terms of classification rates, while being much more faster.
|
Hugo Bertiche, Meysam Madadi, & Sergio Escalera. (2021). PBNS: Physically Based Neural Simulation for Unsupervised Garment Pose Space Deformation. In 14th ACM Siggraph Conference and exhibition on Computer Graphics and Interactive Techniques in Asia.
Abstract: We present a methodology to automatically obtain Pose Space Deformation (PSD) basis for rigged garments through deep learning. Classical approaches rely on Physically Based Simulations (PBS) to animate clothes. These are general solutions that, given a sufficiently fine-grained discretization of space and time, can achieve highly realistic results. However, they are computationally expensive and any scene modification prompts the need of re-simulation. Linear Blend Skinning (LBS) with PSD offers a lightweight alternative to PBS, though, it needs huge volumes of data to learn proper PSD. We propose using deep learning, formulated as an implicit PBS, to unsupervisedly learn realistic cloth Pose Space Deformations in a constrained scenario: dressed humans. Furthermore, we show it is possible to train these models in an amount of time comparable to a PBS of a few sequences. To the best of our knowledge, we are the first to propose a neural simulator for cloth.
While deep-based approaches in the domain are becoming a trend, these are data-hungry models. Moreover, authors often propose complex formulations to better learn wrinkles from PBS data. Supervised learning leads to physically inconsistent predictions that require collision solving to be used. Also, dependency on PBS data limits the scalability of these solutions, while their formulation hinders its applicability and compatibility. By proposing an unsupervised methodology to learn PSD for LBS models (3D animation standard), we overcome both of these drawbacks. Results obtained show cloth-consistency in the animated garments and meaningful pose-dependant folds and wrinkles. Our solution is extremely efficient, handles multiple layers of cloth, allows unsupervised outfit resizing and can be easily applied to any custom 3D avatar.
|
Sounak Dey, Anjan Dutta, Suman Ghosh, Ernest Valveny, & Josep Llados. (2018). Aligning Salient Objects to Queries: A Multi-modal and Multi-object Image Retrieval Framework. In 14th Asian Conference on Computer Vision.
Abstract: In this paper we propose an approach for multi-modal image retrieval in multi-labelled images. A multi-modal deep network architecture is formulated to jointly model sketches and text as input query modalities into a common embedding space, which is then further aligned with the image feature space. Our architecture also relies on a salient object detection through a supervised LSTM-based visual attention model learned from convolutional features. Both the alignment between the queries and the image and the supervision of the attention on the images are obtained by generalizing the Hungarian Algorithm using different loss functions. This permits encoding the object-based features and its alignment with the query irrespective of the availability of the co-occurrence of different objects in the training set. We validate the performance of our approach on standard single/multi-object datasets, showing state-of-the art performance in every dataset.
|
David Roche, Debora Gil, & Jesus Giraldo. (2011). An inference model for analyzing termination conditions of Evolutionary Algorithms. In 14th Congrès Català en Intel·ligencia Artificial (pp. 216–225).
Abstract: In real-world problems, it is mandatory to design a termination condition for Evolutionary Algorithms (EAs) ensuring stabilization close to the unknown optimum. Distribution-based quantities are good candidates as far as suitable parameters are used. A main limitation for application to real-world problems is that such parameters strongly depend on the topology of the objective function, as well as, the EA paradigm used.
We claim that the termination problem would be fully solved if we had a model measuring to what extent a distribution-based quantity asymptotically behaves like the solution accuracy. We present a regression-prediction model that relates any two given quantities and reports if they can be statistically swapped as termination conditions. Our framework is applied to two issues. First, exploring if the parameters involved in the computation of distribution-based quantities influence their asymptotic behavior. Second, to what extent existing distribution-based quantities can be asymptotically exchanged for the accuracy of the EA solution.
Keywords: Evolutionary Computation Convergence, Termination Conditions, Statistical Inference
|
Jorge Bernal, F. Javier Sanchez, & Fernando Vilariño. (2011). Depth of Valleys Accumulation Algorithm for Object Detection. In 14th Congrès Català en Intel·ligencia Artificial (Vol. 1, pp. 71–80).
Abstract: This work aims at detecting in which regions the objects in the image are by using information about the intensity of valleys, which appear to surround ob- jects in images where the source of light is in the line of direction than the camera. We present our depth of valleys accumulation method, which consists of two stages: first, the definition of the depth of valleys image which combines the output of a ridges and valleys detector with the morphological gradient to measure how deep is a point inside a valley and second, an algorithm that denotes points of the image as interior to objects those which are inside complete or incomplete boundaries in the depth of valleys image. To evaluate the performance of our method we have tested it on several application domains. Our results on object region identification are promising, specially in the field of polyp detection in colonoscopy videos, and we also show its applicability in different areas.
Keywords: Object Recognition, Object Region Identification, Image Analysis, Image Processing
|
Xavier Perez Sala, Cecilio Angulo, & Sergio Escalera. (2011). Biologically Inspired Turn Control in Robot Navigation. In 14th Congrès Català en Intel·ligencia Artificial (pp. 187–196).
Abstract: An exportable and robust system for turn control using only camera images is proposed for path execution in robot navigation. Robot motion information is extracted in the form of optical flow from SURF robust descriptors of consecutive frames in the image sequence. This information is used to compute the instantaneous rotation angle. Finally, control loop is closed correcting robot displacements when it is requested for a turn command. The proposed system has been successfully tested on the four-legged Sony Aibo robot.
|
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.
|
Y. Patel, Lluis Gomez, Marçal Rusiñol, & Dimosthenis Karatzas. (2016). Dynamic Lexicon Generation for Natural Scene Images. In 14th European Conference on Computer Vision Workshops (pp. 395–410).
Abstract: Many scene text understanding methods approach the endtoend recognition problem from a word-spotting perspective and take huge bene t from using small per-image lexicons. Such customized lexicons are normally assumed as given and their source is rarely discussed.
In this paper we propose a method that generates contextualized lexicons
for scene images using only visual information. For this, we exploit
the correlation between visual and textual information in a dataset consisting
of images and textual content associated with them. Using the topic modeling framework to discover a set of latent topics in such a dataset allows us to re-rank a xed dictionary in a way that prioritizes the words that are more likely to appear in a given image. Moreover, we train a CNN that is able to reproduce those word rankings but using only the image raw pixels as input. We demonstrate that the quality of the automatically obtained custom lexicons is superior to a generic frequency-based baseline.
Keywords: scene text; photo OCR; scene understanding; lexicon generation; topic modeling; CNN
|
