|
Records |
Links |
|
Author |
Abel Gonzalez-Garcia; Joost Van de Weijer; Yoshua Bengio |
|
|
Title |
Image-to-image translation for cross-domain disentanglement |
Type |
Conference Article |
|
Year |
2018 |
Publication |
32nd Annual Conference on Neural Information Processing Systems |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract |
|
|
|
Address |
Montreal; Canada; December 2018 |
|
|
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 |
NIPS |
|
|
Notes |
LAMP; 600.120 |
Approved |
no |
|
|
Call Number |
Admin @ si @ GWB2018 |
Serial |
3155 |
|
Permanent link to this record |
|
|
|
|
Author |
Chenshen Wu; Luis Herranz; Xialei Liu; Joost Van de Weijer; Bogdan Raducanu |
|
|
Title |
Memory Replay GANs: Learning to Generate New Categories without Forgetting |
Type |
Conference Article |
|
Year |
2018 |
Publication |
32nd Annual Conference on Neural Information Processing Systems |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
5966-5976 |
|
|
Keywords |
|
|
|
Abstract |
Previous works on sequential learning address the problem of forgetting in discriminative models. In this paper we consider the case of generative models. In particular, we investigate generative adversarial networks (GANs) in the task of learning new categories in a sequential fashion. We first show that sequential fine tuning renders the network unable to properly generate images from previous categories (ie forgetting). Addressing this problem, we propose Memory Replay GANs (MeRGANs), a conditional GAN framework that integrates a memory replay generator. We study two methods to prevent forgetting by leveraging these replays, namely joint training with replay and replay alignment. Qualitative and quantitative experimental results in MNIST, SVHN and LSUN datasets show that our memory replay approach can generate competitive images while significantly mitigating the forgetting of previous categories. |
|
|
Address |
Montreal; Canada; December 2018 |
|
|
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 |
NIPS |
|
|
Notes |
LAMP; 600.106; 600.109; 602.200; 600.120 |
Approved |
no |
|
|
Call Number |
Admin @ si @ WHL2018 |
Serial |
3249 |
|
Permanent link to this record |
|
|
|
|
Author |
Raul Gomez; Lluis Gomez; Jaume Gibert; Dimosthenis Karatzas |
|
|
Title |
Learning to Learn from Web Data through Deep Semantic Embeddings |
Type |
Conference Article |
|
Year |
2018 |
Publication |
15th European Conference on Computer Vision Workshops |
Abbreviated Journal |
|
|
|
Volume |
11134 |
Issue |
|
Pages |
514-529 |
|
|
Keywords |
|
|
|
Abstract |
In this paper we propose to learn a multimodal image and text embedding from Web and Social Media data, aiming to leverage the semantic knowledge learnt in the text domain and transfer it to a visual model for semantic image retrieval. We demonstrate that the pipeline can learn from images with associated text without supervision and perform a thourough analysis of five different text embeddings in three different benchmarks. We show that the embeddings learnt with Web and Social Media data have competitive performances over supervised methods in the text based image retrieval task, and we clearly outperform state of the art in the MIRFlickr dataset when training in the target data. Further we demonstrate how semantic multimodal image retrieval can be performed using the learnt embeddings, going beyond classical instance-level retrieval problems. Finally, we present a new dataset, InstaCities1M, composed by Instagram images and their associated texts that can be used for fair comparison of image-text embeddings. |
|
|
Address |
Munich; Alemanya; September 2018 |
|
|
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 |
ECCVW |
|
|
Notes |
DAG; 600.129; 601.338; 600.121 |
Approved |
no |
|
|
Call Number |
Admin @ si @ GGG2018a |
Serial |
3175 |
|
Permanent link to this record |
|
|
|
|
Author |
Dena Bazazian; Dimosthenis Karatzas; Andrew Bagdanov |
|
|
Title |
Soft-PHOC Descriptor for End-to-End Word Spotting in Egocentric Scene Images |
Type |
Conference Article |
|
Year |
2018 |
Publication |
International Workshop on Egocentric Perception, Interaction and Computing at ECCV |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract |
Word spotting in natural scene images has many applications in scene understanding and visual assistance. We propose Soft-PHOC, an intermediate representation of images based on character probability maps. Our representation extends the concept of the Pyramidal Histogram Of Characters (PHOC) by exploiting Fully Convolutional Networks to derive a pixel-wise mapping of the character distribution within candidate word regions. We show how to use our descriptors for word spotting tasks in egocentric camera streams through an efficient text line proposal algorithm. This is based on the Hough Transform over character attribute maps followed by scoring using Dynamic Time Warping (DTW). We evaluate our results on ICDAR 2015 Challenge 4 dataset of incidental scene text captured by an egocentric camera. |
|
|
Address |
Munich; Alemanya; September 2018 |
|
|
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 |
ECCVW |
|
|
Notes |
DAG; 600.129; 600.121; |
Approved |
no |
|
|
Call Number |
Admin @ si @ BKB2018b |
Serial |
3174 |
|
Permanent link to this record |
|
|
|
|
Author |
Raul Gomez; Lluis Gomez; Jaume Gibert; Dimosthenis Karatzas |
|
|
Title |
Learning from# Barcelona Instagram data what Locals and Tourists post about its Neighbourhoods |
Type |
Conference Article |
|
Year |
2018 |
Publication |
15th European Conference on Computer Vision Workshops |
Abbreviated Journal |
|
|
|
Volume |
11134 |
Issue |
|
Pages |
530-544 |
|
|
Keywords |
|
|
|
Abstract |
Massive tourism is becoming a big problem for some cities, such as Barcelona, due to its concentration in some neighborhoods. In this work we gather Instagram data related to Barcelona consisting on images-captions pairs and, using the text as a supervisory signal, we learn relations between images, words and neighborhoods. Our goal is to learn which visual elements appear in photos when people is posting about each neighborhood. We perform a language separate treatment of the data and show that it can be extrapolated to a tourists and locals separate analysis, and that tourism is reflected in Social Media at a neighborhood level. The presented pipeline allows analyzing the differences between the images that tourists and locals associate to the different neighborhoods. The proposed method, which can be extended to other cities or subjects, proves that Instagram data can be used to train multi-modal (image and text) machine learning models that are useful to analyze publications about a city at a neighborhood level. We publish the collected dataset, InstaBarcelona and the code used in the analysis. |
|
|
Address |
Munich; Alemanya; September 2018 |
|
|
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 |
ECCVW |
|
|
Notes |
DAG; 600.129; 601.338; 600.121 |
Approved |
no |
|
|
Call Number |
Admin @ si @ GGG2018b |
Serial |
3176 |
|
Permanent link to this record |
|
|
|
|
Author |
Yaxing Wang; Chenshen Wu; Luis Herranz; Joost Van de Weijer; Abel Gonzalez-Garcia; Bogdan Raducanu |
|
|
Title |
Transferring GANs: generating images from limited data |
Type |
Conference Article |
|
Year |
2018 |
Publication |
15th European Conference on Computer Vision |
Abbreviated Journal |
|
|
|
Volume |
11210 |
Issue |
|
Pages |
220-236 |
|
|
Keywords |
Generative adversarial networks; Transfer learning; Domain adaptation; Image generation |
|
|
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. |
|
|
Address |
Munich; September 2018 |
|
|
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 |
ECCV |
|
|
Notes |
LAMP; 600.109; 600.106; 600.120 |
Approved |
no |
|
|
Call Number |
Admin @ si @ WWH2018a |
Serial |
3130 |
|
Permanent link to this record |
|
|
|
|
Author |
Pau Rodriguez; Josep M. Gonfaus; Guillem Cucurull; Xavier Roca; Jordi Gonzalez |
|
|
Title |
Attend and Rectify: A Gated Attention Mechanism for Fine-Grained Recovery |
Type |
Conference Article |
|
Year |
2018 |
Publication |
15th European Conference on Computer Vision |
Abbreviated Journal |
|
|
|
Volume |
11212 |
Issue |
|
Pages |
357-372 |
|
|
Keywords |
Deep Learning; Convolutional Neural Networks; Attention |
|
|
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. |
|
|
Address |
Munich; September 2018 |
|
|
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 |
ECCV |
|
|
Notes |
ISE; 600.098; 602.121; 600.119 |
Approved |
no |
|
|
Call Number |
Admin @ si @ RGC2018 |
Serial |
3139 |
|
Permanent link to this record |
|
|
|
|
Author |
Lluis Gomez; Andres Mafla; Marçal Rusiñol; Dimosthenis Karatzas |
|
|
Title |
Single Shot Scene Text Retrieval |
Type |
Conference Article |
|
Year |
2018 |
Publication |
15th European Conference on Computer Vision |
Abbreviated Journal |
|
|
|
Volume |
11218 |
Issue |
|
Pages |
728-744 |
|
|
Keywords |
Image retrieval; Scene text; Word spotting; Convolutional Neural Networks; Region Proposals Networks; PHOC |
|
|
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. |
|
|
Address |
Munich; September 2018 |
|
|
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 |
ECCV |
|
|
Notes |
DAG; 600.084; 601.338; 600.121; 600.129 |
Approved |
no |
|
|
Call Number |
Admin @ si @ GMR2018 |
Serial |
3143 |
|
Permanent link to this record |
|
|
|
|
Author |
Felipe Codevilla; Antonio Lopez; Vladlen Koltun; Alexey Dosovitskiy |
|
|
Title |
On Offline Evaluation of Vision-based Driving Models |
Type |
Conference Article |
|
Year |
2018 |
Publication |
15th European Conference on Computer Vision |
Abbreviated Journal |
|
|
|
Volume |
11219 |
Issue |
|
Pages |
246-262 |
|
|
Keywords |
Autonomous driving; deep learning |
|
|
Abstract |
Autonomous driving models should ideally be evaluated by deploying
them on a fleet of physical vehicles in the real world. Unfortunately, this approach is not practical for the vast majority of researchers. An attractive alternative is to evaluate models offline, on a pre-collected validation dataset with ground truth annotation. In this paper, we investigate the relation between various online and offline metrics for evaluation of autonomous driving models. We find that offline prediction error is not necessarily correlated with driving quality, and two models with identical prediction error can differ dramatically in their driving performance. We show that the correlation of offline evaluation with driving quality can be significantly improved by selecting an appropriate validation dataset and
suitable offline metrics. |
|
|
Address |
Munich; September 2018 |
|
|
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 |
ECCV |
|
|
Notes |
ADAS; 600.124; 600.118 |
Approved |
no |
|
|
Call Number |
Admin @ si @ CLK2018 |
Serial |
3162 |
|
Permanent link to this record |
|
|
|
|
Author |
Marc Oliu; Javier Selva; Sergio Escalera |
|
|
Title |
Folded Recurrent Neural Networks for Future Video Prediction |
Type |
Conference Article |
|
Year |
2018 |
Publication |
15th European Conference on Computer Vision |
Abbreviated Journal |
|
|
|
Volume |
11218 |
Issue |
|
Pages |
745-761 |
|
|
Keywords |
|
|
|
Abstract |
Future video prediction is an ill-posed Computer Vision problem that recently received much attention. Its main challenges are the high variability in video content, the propagation of errors through time, and the non-specificity of the future frames: given a sequence of past frames there is a continuous distribution of possible futures. This work introduces bijective Gated Recurrent Units, a double mapping between the input and output of a GRU layer. This allows for recurrent auto-encoders with state sharing between encoder and decoder, stratifying the sequence representation and helping to prevent capacity problems. We show how with this topology only the encoder or decoder needs to be applied for input encoding and prediction, respectively. This reduces the computational cost and avoids re-encoding the predictions when generating a sequence of frames, mitigating the propagation of errors. Furthermore, it is possible to remove layers from an already trained model, giving an insight to the role performed by each layer and making the model more explainable. We evaluate our approach on three video datasets, outperforming state of the art prediction results on MMNIST and UCF101, and obtaining competitive results on KTH with 2 and 3 times less memory usage and computational cost than the best scored approach. |
|
|
Address |
Munich; September 2018 |
|
|
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 |
ECCV |
|
|
Notes |
HUPBA; no menciona |
Approved |
no |
|
|
Call Number |
Admin @ si @ OSE2018 |
Serial |
3204 |
|
Permanent link to this record |
|
|
|
|
Author |
Ciprian Corneanu; Meysam Madadi; Sergio Escalera |
|
|
Title |
Deep Structure Inference Network for Facial Action Unit Recognition |
Type |
Conference Article |
|
Year |
2018 |
Publication |
15th European Conference on Computer Vision |
Abbreviated Journal |
|
|
|
Volume |
11216 |
Issue |
|
Pages |
309-324 |
|
|
Keywords |
Computer Vision; Machine Learning; Deep Learning; Facial Expression Analysis; Facial Action Units; Structure Inference |
|
|
Abstract |
Facial expressions are combinations of basic components called Action Units (AU). Recognizing AUs is key for general facial expression analysis. Recently, efforts in automatic AU recognition have been dedicated to learning combinations of local features and to exploiting correlations between AUs. We propose a deep neural architecture that tackles both problems by combining learned local and global features in its initial stages and replicating a message passing algorithm between classes similar to a graphical model inference approach in later stages. We show that by training the model end-to-end with increased supervision we improve state-of-the-art by 5.3% and 8.2% performance on BP4D and DISFA datasets, respectively. |
|
|
Address |
Munich; September 2018 |
|
|
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 |
ECCV |
|
|
Notes |
HUPBA; no proj |
Approved |
no |
|
|
Call Number |
Admin @ si @ CME2018 |
Serial |
3205 |
|
Permanent link to this record |
|
|
|
|
Author |
Mohamed Ilyes Lakhal; Albert Clapes; Sergio Escalera; Oswald Lanz; Andrea Cavallaro |
|
|
Title |
Residual Stacked RNNs for Action Recognition |
Type |
Conference Article |
|
Year |
2018 |
Publication |
9th International Workshop on Human Behavior Understanding |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
534-548 |
|
|
Keywords |
Action recognition; Deep residual learning; Two-stream RNN |
|
|
Abstract |
Action recognition pipelines that use Recurrent Neural Networks (RNN) are currently 5–10% less accurate than Convolutional Neural Networks (CNN). While most works that use RNNs employ a 2D CNN on each frame to extract descriptors for action recognition, we extract spatiotemporal features from a 3D CNN and then learn the temporal relationship of these descriptors through a stacked residual recurrent neural network (Res-RNN). We introduce for the first time residual learning to counter the degradation problem in multi-layer RNNs, which have been successful for temporal aggregation in two-stream action recognition pipelines. Finally, we use a late fusion strategy to combine RGB and optical flow data of the two-stream Res-RNN. Experimental results show that the proposed pipeline achieves competitive results on UCF-101 and state of-the-art results for RNN-like architectures on the challenging HMDB-51 dataset. |
|
|
Address |
Munich; September 2018 |
|
|
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 |
ECCVW |
|
|
Notes |
HUPBA; no proj |
Approved |
no |
|
|
Call Number |
Admin @ si @ LCE2018b |
Serial |
3206 |
|
Permanent link to this record |
|
|
|
|
Author |
Vacit Oguz Yazici; Joost Van de Weijer; Arnau Ramisa |
|
|
Title |
Color Naming for Multi-Color Fashion Items |
Type |
Conference Article |
|
Year |
2018 |
Publication |
6th World Conference on Information Systems and Technologies |
Abbreviated Journal |
|
|
|
Volume |
747 |
Issue |
|
Pages |
64-73 |
|
|
Keywords |
Deep learning; Color; Multi-label |
|
|
Abstract |
There exists a significant amount of research on color naming of single colored objects. However in reality many fashion objects consist of multiple colors. Currently, searching in fashion datasets for multi-colored objects can be a laborious task. Therefore, in this paper we focus on color naming for images with multi-color fashion items. We collect a dataset, which consists of images which may have from one up to four colors. We annotate the images with the 11 basic colors of the English language. We experiment with several designs for deep neural networks with different losses. We show that explicitly estimating the number of colors in the fashion item leads to improved results. |
|
|
Address |
Naples; March 2018 |
|
|
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 |
WORLDCIST |
|
|
Notes |
LAMP; 600.109; 601.309; 600.120 |
Approved |
no |
|
|
Call Number |
Admin @ si @ YWR2018 |
Serial |
3161 |
|
Permanent link to this record |
|
|
|
|
Author |
Marc Masana; Idoia Ruiz; Joan Serrat; Joost Van de Weijer; Antonio Lopez |
|
|
Title |
Metric Learning for Novelty and Anomaly Detection |
Type |
Conference Article |
|
Year |
2018 |
Publication |
29th British Machine Vision Conference |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract |
When neural networks process images which do not resemble the distribution seen during training, so called out-of-distribution images, they often make wrong predictions, and do so too confidently. The capability to detect out-of-distribution images is therefore crucial for many real-world applications. We divide out-of-distribution detection between novelty detection ---images of classes which are not in the training set but are related to those---, and anomaly detection ---images with classes which are unrelated to the training set. By related we mean they contain the same type of objects, like digits in MNIST and SVHN. Most existing work has focused on anomaly detection, and has addressed this problem considering networks trained with the cross-entropy loss. Differently from them, we propose to use metric learning which does not have the drawback of the softmax layer (inherent to cross-entropy methods), which forces the network to divide its prediction power over the learned classes. We perform extensive experiments and evaluate both novelty and anomaly detection, even in a relevant application such as traffic sign recognition, obtaining comparable or better results than previous works. |
|
|
Address |
Newcastle; uk; September 2018 |
|
|
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 |
BMVC |
|
|
Notes |
LAMP; ADAS; 601.305; 600.124; 600.106; 602.200; 600.120; 600.118 |
Approved |
no |
|
|
Call Number |
Admin @ si @ MRS2018 |
Serial |
3156 |
|
Permanent link to this record |
|
|
|
|
Author |
Cristina Palmero; Javier Selva; Mohammad Ali Bagheri; Sergio Escalera |
|
|
Title |
Recurrent CNN for 3D Gaze Estimation using Appearance and Shape Cues |
Type |
Conference Article |
|
Year |
2018 |
Publication |
29th British Machine Vision Conference |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract |
Gaze behavior is an important non-verbal cue in social signal processing and humancomputer interaction. In this paper, we tackle the problem of person- and head poseindependent 3D gaze estimation from remote cameras, using a multi-modal recurrent convolutional neural network (CNN). We propose to combine face, eyes region, and face landmarks as individual streams in a CNN to estimate gaze in still images. Then, we exploit the dynamic nature of gaze by feeding the learned features of all the frames in a sequence to a many-to-one recurrent module that predicts the 3D gaze vector of the last frame. Our multi-modal static solution is evaluated on a wide range of head poses and gaze directions, achieving a significant improvement of 14.6% over the state of the art on
EYEDIAP dataset, further improved by 4% when the temporal modality is included. |
|
|
Address |
Newcastle; UK; September 2018 |
|
|
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 |
BMVC |
|
|
Notes |
HUPBA; no proj |
Approved |
no |
|
|
Call Number |
Admin @ si @ PSB2018 |
Serial |
3208 |
|
Permanent link to this record |