|
Records |
Links |
|
Author |
Jaime Moreno; Xavier Otazu |
|
|
Title |
Image compression algorithm based on Hilbert scanning of embedded quadTrees: an introduction of the Hi-SET coder |
Type |
Conference Article |
|
Year |
2011 |
Publication |
IEEE International Conference on Multimedia and Expo |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
1-6 |
|
|
Keywords |
|
|
|
Abstract |
In this work we present an effective and computationally simple algorithm for image compression based on Hilbert Scanning of Embedded quadTrees (Hi-SET). It allows to represent an image as an embedded bitstream along a fractal function. Embedding is an important feature of modern image compression algorithms, in this way Salomon in [1, pg. 614] cite that another feature and perhaps a unique one is the fact of achieving the best quality for the number of bits input by the decoder at any point during the decoding. Hi-SET possesses also this latter feature. Furthermore, the coder is based on a quadtree partition strategy, that applied to image transformation structures such as discrete cosine or wavelet transform allows to obtain an energy clustering both in frequency and space. The coding algorithm is composed of three general steps, using just a list of significant pixels. The implementation of the proposed coder is developed for gray-scale and color image compression. Hi-SET compressed images are, on average, 6.20dB better than the ones obtained by other compression techniques based on the Hilbert scanning. Moreover, Hi-SET improves the image quality in 1.39dB and 1.00dB in gray-scale and color compression, respectively, when compared with JPEG2000 coder. |
|
|
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 |
1945-7871 |
ISBN |
978-1-61284-348-3 |
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
ICME |
|
|
Notes |
CIC |
Approved |
no |
|
|
Call Number |
Admin @ si @ MoO2011a |
Serial |
2176 |
|
Permanent link to this record |
|
|
|
|
Author |
Marc Bolaños; R. Mestre; Estefania Talavera; Xavier Giro; Petia Radeva |
|
|
Title |
Visual Summary of Egocentric Photostreams by Representative Keyframes |
Type |
Conference Article |
|
Year |
2015 |
Publication |
IEEE International Conference on Multimedia and Expo ICMEW2015 |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
1-6 |
|
|
Keywords |
egocentric; lifelogging; summarization; keyframes |
|
|
Abstract |
Building a visual summary from an egocentric photostream captured by a lifelogging wearable camera is of high interest for different applications (e.g. memory reinforcement). In this paper, we propose a new summarization method based on keyframes selection that uses visual features extracted bymeans of a convolutional neural network. Our method applies an unsupervised clustering for dividing the photostreams into events, and finally extracts the most relevant keyframe for each event. We assess the results by applying a blind-taste test on a group of 20 people who assessed the quality of the
summaries. |
|
|
Address |
Torino; italy; July 2015 |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
978-1-4799-7079-7 |
Edition |
|
|
|
ISSN |
|
ISBN |
978-1-4799-7079-7 |
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
ICME |
|
|
Notes |
MILAB |
Approved |
no |
|
|
Call Number |
Admin @ si @ BMT2015 |
Serial |
2638 |
|
Permanent link to this record |
|
|
|
|
Author |
Sergio Escalera; Jordi Gonzalez; Xavier Baro; Miguel Reyes; Oscar Lopes; Isabelle Guyon; V. Athitsos; Hugo Jair Escalante |
|
|
Title |
Multi-modal Gesture Recognition Challenge 2013: Dataset and Results |
Type |
Conference Article |
|
Year |
2013 |
Publication |
15th ACM International Conference on Multimodal Interaction |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
445-452 |
|
|
Keywords |
|
|
|
Abstract |
The recognition of continuous natural gestures is a complex and challenging problem due to the multi-modal nature of involved visual cues (e.g. fingers and lips movements, subtle facial expressions, body pose, etc.), as well as technical limitations such as spatial and temporal resolution and unreliable
depth cues. In order to promote the research advance on this field, we organized a challenge on multi-modal gesture recognition. We made available a large video database of 13; 858 gestures from a lexicon of 20 Italian gesture categories recorded with a KinectTM camera, providing the audio, skeletal model, user mask, RGB and depth images. The focus of the challenge was on user independent multiple gesture learning. There are no resting positions and the gestures are performed in continuous sequences lasting 1-2 minutes, containing between 8 and 20 gesture instances in each sequence. As a result, the dataset contains around 1:720:800 frames. In addition to the 20 main gesture categories, ‘distracter’ gestures are included, meaning that additional audio
and gestures out of the vocabulary are included. The final evaluation of the challenge was defined in terms of the Levenshtein edit distance, where the goal was to indicate the real order of gestures within the sequence. 54 international teams participated in the challenge, and outstanding results
were obtained by the first ranked participants. |
|
|
Address |
Sidney; Australia; December 2013 |
|
|
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 |
978-1-4503-2129-7 |
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
ICMI |
|
|
Notes |
HUPBA; ISE; 600.063;MV |
Approved |
no |
|
|
Call Number |
Admin @ si @ EGB2013 |
Serial |
2373 |
|
Permanent link to this record |
|
|
|
|
Author |
David Vazquez; Antonio Lopez; Daniel Ponsa; Javier Marin |
|
|
Title |
Virtual Worlds and Active Learning for Human Detection |
Type |
Conference Article |
|
Year |
2011 |
Publication |
13th International Conference on Multimodal Interaction |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
393-400 |
|
|
Keywords |
Pedestrian Detection; Human detection; Virtual; Domain Adaptation; Active Learning |
|
|
Abstract |
Image based human detection is of paramount interest due to its potential applications in fields such as advanced driving assistance, surveillance and media analysis. However, even detecting non-occluded standing humans remains a challenge of intensive research. The most promising human detectors rely on classifiers developed in the discriminative paradigm, i.e., trained with labelled samples. However, labeling is a manual intensive step, especially in cases like human detection where it is necessary to provide at least bounding boxes framing the humans for training. To overcome such problem, some authors have proposed the use of a virtual world where the labels of the different objects are obtained automatically. This means that the human models (classifiers) are learnt using the appearance of rendered images, i.e., using realistic computer graphics. Later, these models are used for human detection in images of the real world. The results of this technique are surprisingly good. However, these are not always as good as the classical approach of training and testing with data coming from the same camera, or similar ones. Accordingly, in this paper we address the challenge of using a virtual world for gathering (while playing a videogame) a large amount of automatically labelled samples (virtual humans and background) and then training a classifier that performs equal, in real-world images, than the one obtained by equally training from manually labelled real-world samples. For doing that, we cast the problem as one of domain adaptation. In doing so, we assume that a small amount of manually labelled samples from real-world images is required. To collect these labelled samples we propose a non-standard active learning technique. Therefore, ultimately our human model is learnt by the combination of virtual and real world labelled samples (Fig. 1), which has not been done before. We present quantitative results showing that this approach is valid. |
|
|
Address |
Alicante, Spain |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
ACM DL |
Place of Publication |
New York, NY, USA, USA |
Editor |
|
|
|
Language |
English |
Summary Language |
English |
Original Title |
Virtual Worlds and Active Learning for Human Detection |
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
978-1-4503-0641-6 |
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
ICMI |
|
|
Notes |
ADAS |
Approved |
yes |
|
|
Call Number |
ADAS @ adas @ VLP2011a |
Serial |
1683 |
|
Permanent link to this record |
|
|
|
|
Author |
Victor Ponce; Sergio Escalera; Xavier Baro |
|
|
Title |
Multi-modal Social Signal Analysis for Predicting Agreement in Conversation Settings |
Type |
Conference Article |
|
Year |
2013 |
Publication |
15th ACM International Conference on Multimodal Interaction |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
495-502 |
|
|
Keywords |
|
|
|
Abstract |
In this paper we present a non-invasive ambient intelligence framework for the analysis of non-verbal communication applied to conversational settings. In particular, we apply feature extraction techniques to multi-modal audio-RGB-depth data. We compute a set of behavioral indicators that define communicative cues coming from the fields of psychology and observational methodology. We test our methodology over data captured in victim-offender mediation scenarios. Using different state-of-the-art classification approaches, our system achieve upon 75% of recognition predicting agreement among the parts involved in the conversations, using as ground truth the experts opinions. |
|
|
Address |
Sidney; Australia; December 2013 |
|
|
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 |
978-1-4503-2129-7 |
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
ICMI |
|
|
Notes |
HuPBA;MV |
Approved |
no |
|
|
Call Number |
Admin @ si @ PEB2013 |
Serial |
2488 |
|
Permanent link to this record |
|
|
|
|
Author |
Ruth Aylett; Ginevra Castellano; Bogdan Raducanu; Ana Paiva; Marc Hanheide |
|
|
Title |
Long-term socially perceptive and interactive robot companions: challenges and future perspectives |
Type |
Conference Article |
|
Year |
2011 |
Publication |
13th International Conference on Multimodal Interaction |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
323-326 |
|
|
Keywords |
human-robot interaction, multimodal interaction, social robotics |
|
|
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. |
|
|
Address |
Alicante |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
ACM |
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
978-1-4503-0641-6 |
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
ICMI |
|
|
Notes |
OR;MV |
Approved |
no |
|
|
Call Number |
Admin @ si @ ACR2011 |
Serial |
1888 |
|
Permanent link to this record |
|
|
|
|
Author |
Javier M. Olaso; Alain Vazquez; Leila Ben Letaifa; Mikel de Velasco; Aymen Mtibaa; Mohamed Amine Hmani; Dijana Petrovska-Delacretaz; Gerard Chollet; Cesar Montenegro; Asier Lopez-Zorrilla; Raquel Justo; Roberto Santana; Jofre Tenorio-Laranga; Eduardo Gonzalez-Fraile; Begoña Fernandez-Ruanova; Gennaro Cordasco; Anna Esposito; Kristin Beck Gjellesvik; Anna Torp Johansen; Maria Stylianou Kornes; Colin Pickard; Cornelius Glackin; Gary Cahalane; Pau Buch; Cristina Palmero; Sergio Escalera; Olga Gordeeva; Olivier Deroo; Anaïs Fernandez; Daria Kyslitska; Jose Antonio Lozano; Maria Ines Torres; Stephan Schlogl |
|
|
Title |
The EMPATHIC Virtual Coach: a demo |
Type |
Conference Article |
|
Year |
2021 |
Publication |
23rd ACM International Conference on Multimodal Interaction |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
848-851 |
|
|
Keywords |
|
|
|
Abstract |
The main objective of the EMPATHIC project has been the design and development of a virtual coach to engage the healthy-senior user and to enhance well-being through awareness of personal status. The EMPATHIC approach addresses this objective through multimodal interactions supported by the GROW coaching model. The paper summarizes the main components of the EMPATHIC Virtual Coach (EMPATHIC-VC) and introduces a demonstration of the coaching sessions in selected scenarios. |
|
|
Address |
Virtual; October 2021 |
|
|
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 |
ICMI |
|
|
Notes |
HUPBA; no proj |
Approved |
no |
|
|
Call Number |
Admin @ si @ OVB2021 |
Serial |
3644 |
|
Permanent link to this record |
|
|
|
|
Author |
Sergio Escalera; Petia Radeva; Jordi Vitria; Xavier Baro; Bogdan Raducanu |
|
|
Title |
Modelling and Analyzing Multimodal Dyadic Interactions Using Social Networks |
Type |
Conference Article |
|
Year |
2010 |
Publication |
12th International Conference on Multimodal Interfaces and 7th Workshop on Machine Learning for Multimodal Interaction. |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
Social interaction; Multimodal fusion, Influence model; Social network analysis |
|
|
Abstract |
Social network analysis became a common technique used to model and quantify the properties of social interactions. In this paper, we propose an integrated framework to explore the characteristics of a social network extracted from
multimodal dyadic interactions. First, speech detection is performed through an audio/visual fusion scheme based on stacked sequential learning. In the audio domain, speech is detected through clusterization of audio features. Clusters
are modelled by means of an One-state Hidden Markov Model containing a diagonal covariance Gaussian Mixture Model. In the visual domain, speech detection is performed through differential-based feature extraction from the segmented
mouth region, and a dynamic programming matching procedure. Second, in order to model the dyadic interactions, we employed the Influence Model whose states
encode the previous integrated audio/visual data. Third, the social network is extracted based on the estimated influences. For our study, we used a set of videos belonging to New York Times’ Blogging Heads opinion blog. The results
are reported both in terms of accuracy of the audio/visual data fusion and centrality measures used to characterize the social network. |
|
|
Address |
Beijing (China) |
|
|
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 |
ICMI-MLI |
|
|
Notes |
OR;MILAB;HUPBA;MV |
Approved |
no |
|
|
Call Number |
BCNPCL @ bcnpcl @ ERV2010 |
Serial |
1427 |
|
Permanent link to this record |
|
|
|
|
Author |
Isabelle Guyon; Kristin Bennett; Gavin Cawley; Hugo Jair Escalante; Sergio Escalera; Tin Kam Ho; Nuria Macia; Bisakha Ray; Mehreen Saeed; Alexander Statnikov; Evelyne Viegas |
|
|
Title |
AutoML Challenge 2015: Design and First Results |
Type |
Conference Article |
|
Year |
2015 |
Publication |
32nd International Conference on Machine Learning, ICML workshop, JMLR proceedings ICML15 |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
1-8 |
|
|
Keywords |
AutoML Challenge; machine learning; model selection; meta-learning; repre- sentation learning; active learning |
|
|
Abstract |
ChaLearn is organizing the Automatic Machine Learning (AutoML) contest 2015, which challenges participants to solve classication and regression problems without any human intervention. Participants' code is automatically run on the contest servers to train and test learning machines. However, there is no obligation to submit code; half of the prizes can be won by submitting prediction results only. Datasets of progressively increasing diculty are introduced throughout the six rounds of the challenge. (Participants can
enter the competition in any round.) The rounds alternate phases in which learners are tested on datasets participants have not seen (AutoML), and phases in which participants have limited time to tweak their algorithms on those datasets to improve performance (Tweakathon). This challenge will push the state of the art in fully automatic machine learning on a wide range of real-world problems. The platform will remain available beyond the termination of the challenge: http://codalab.org/AutoML. |
|
|
Address |
Lille; France; July 2015 |
|
|
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 |
ICML |
|
|
Notes |
HuPBA;MILAB |
Approved |
no |
|
|
Call Number |
Admin @ si @ GBC2015c |
Serial |
2656 |
|
Permanent link to this record |
|
|
|
|
Author |
Isabelle Guyon; Imad Chaabane; Hugo Jair Escalante; Sergio Escalera; Damir Jajetic; James Robert Lloyd; Nuria Macia; Bisakha Ray; Lukasz Romaszko; Michele Sebag; Alexander Statnikov; Sebastien Treguer; Evelyne Viegas |
|
|
Title |
A brief Review of the ChaLearn AutoML Challenge: Any-time Any-dataset Learning without Human Intervention |
Type |
Conference Article |
|
Year |
2016 |
Publication |
AutoML Workshop |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
1 |
Pages |
1-8 |
|
|
Keywords |
AutoML Challenge; machine learning; model selection; meta-learning; repre- sentation learning; active learning |
|
|
Abstract |
The ChaLearn AutoML Challenge team conducted a large scale evaluation of fully automatic, black-box learning machines for feature-based classification and regression problems. The test bed was composed of 30 data sets from a wide variety of application domains and ranged across different types of complexity. Over six rounds, participants succeeded in delivering AutoML software capable of being trained and tested without human intervention. Although improvements can still be made to close the gap between human-tweaked and AutoML models, this competition contributes to the development of fully automated environments by challenging practitioners to solve problems under specific constraints and sharing their approaches; the platform will remain available for post-challenge submissions at http://codalab.org/AutoML. |
|
|
Address |
New York; USA; June 2016 |
|
|
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 |
ICML |
|
|
Notes |
HuPBA;MILAB |
Approved |
no |
|
|
Call Number |
Admin @ si @ GCE2016 |
Serial |
2769 |
|
Permanent link to this record |
|
|
|
|
Author |
Zhengying Liu; Adrien Pavao; Zhen Xu; Sergio Escalera; Isabelle Guyon; Julio C. S. Jacques Junior; Meysam Madadi; Sebastien Treguer |
|
|
Title |
How far are we from true AutoML: reflection from winning solutions and results of AutoDL challenge |
Type |
Conference Article |
|
Year |
2020 |
Publication |
7th ICML Workshop on Automated Machine Learning |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract |
Following the completion of the AutoDL challenge (the final challenge in the ChaLearn
AutoDL challenge series 2019), we investigate winning solutions and challenge results to
answer an important motivational question: how far are we from achieving true AutoML?
On one hand, the winning solutions achieve good (accurate and fast) classification performance on unseen datasets. On the other hand, all winning solutions still contain a
considerable amount of hard-coded knowledge on the domain (or modality) such as image,
video, text, speech and tabular. This form of ad-hoc meta-learning could be replaced by
more automated forms of meta-learning in the future. Organizing a meta-learning challenge could help forging AutoML solutions that generalize to new unseen domains (e.g.
new types of sensor data) as well as gaining insights on the AutoML problem from a more
fundamental point of view. The datasets of the AutoDL challenge are a resource that can
be used for further benchmarks and the code of the winners has been outsourced, which is
a big step towards “democratizing” Deep Learning. |
|
|
Address |
Virtual; July 2020 |
|
|
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 |
ICML |
|
|
Notes |
HUPBA |
Approved |
no |
|
|
Call Number |
Admin @ si @ LPX2020 |
Serial |
3502 |
|
Permanent link to this record |
|
|
|
|
Author |
Marc Masana; Bartlomiej Twardowski; Joost Van de Weijer |
|
|
Title |
On Class Orderings for Incremental Learning |
Type |
Conference Article |
|
Year |
2020 |
Publication |
ICML Workshop on Continual Learning |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract |
The influence of class orderings in the evaluation of incremental learning has received very little attention. In this paper, we investigate the impact of class orderings for incrementally learned classifiers. We propose a method to compute various orderings for a dataset. The orderings are derived by simulated annealing optimization from the confusion matrix and reflect different incremental learning scenarios, including maximally and minimally confusing tasks. We evaluate a wide range of state-of-the-art incremental learning methods on the proposed orderings. Results show that orderings can have a significant impact on performance and the ranking of the methods. |
|
|
Address |
Virtual; July 2020 |
|
|
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 |
ICMLW |
|
|
Notes |
LAMP; 600.120 |
Approved |
no |
|
|
Call Number |
Admin @ si @ MTW2020 |
Serial |
3505 |
|
Permanent link to this record |
|
|
|
|
Author |
David Berga; Marc Masana; Joost Van de Weijer |
|
|
Title |
Disentanglement of Color and Shape Representations for Continual Learning |
Type |
Conference Article |
|
Year |
2020 |
Publication |
ICML Workshop on Continual Learning |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract |
We hypothesize that disentangled feature representations suffer less from catastrophic forgetting. As a case study we perform explicit disentanglement of color and shape, by adjusting the network architecture. We tested classification accuracy and forgetting in a task-incremental setting with Oxford-102 Flowers dataset. We combine our method with Elastic Weight Consolidation, Learning without Forgetting, Synaptic Intelligence and Memory Aware Synapses, and show that feature disentanglement positively impacts continual learning performance. |
|
|
Address |
Virtual; July 2020 |
|
|
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 |
ICMLW |
|
|
Notes |
LAMP; 600.120 |
Approved |
no |
|
|
Call Number |
Admin @ si @ BMW2020 |
Serial |
3506 |
|
Permanent link to this record |
|
|
|
|
Author |
Albin Soutif; Marc Masana; Joost Van de Weijer; Bartlomiej Twardowski |
|
|
Title |
On the importance of cross-task features for class-incremental learning |
Type |
Conference Article |
|
Year |
2021 |
Publication |
Theory and Foundation of continual learning workshop of ICML |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract |
In class-incremental learning, an agent with limited resources needs to learn a sequence of classification tasks, forming an ever growing classification problem, with the constraint of not being able to access data from previous tasks. The main difference with task-incremental learning, where a task-ID is available at inference time, is that the learner also needs to perform crosstask discrimination, i.e. distinguish between classes that have not been seen together. Approaches to tackle this problem are numerous and mostly make use of an external memory (buffer) of non-negligible size. In this paper, we ablate the learning of crosstask features and study its influence on the performance of basic replay strategies used for class-IL. We also define a new forgetting measure for class-incremental learning, and see that forgetting is not the principal cause of low performance. Our experimental results show that future algorithms for class-incremental learning should not only prevent forgetting, but also aim to improve the quality of the cross-task features. This is especially important when the number of classes per task is small. |
|
|
Address |
Virtual; July 2021 |
|
|
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 |
ICMLW |
|
|
Notes |
LAMP |
Approved |
no |
|
|
Call Number |
Admin @ si @ SMW2021 |
Serial |
3588 |
|
Permanent link to this record |
|
|
|
|
Author |
Muhammad Anwer Rao; Fahad Shahbaz Khan; Joost Van de Weijer; Jorma Laaksonen |
|
|
Title |
Combining Holistic and Part-based Deep Representations for Computational Painting Categorization |
Type |
Conference Article |
|
Year |
2016 |
Publication |
6th International Conference on Multimedia Retrieval |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract |
Automatic analysis of visual art, such as paintings, is a challenging inter-disciplinary research problem. Conventional approaches only rely on global scene characteristics by encoding holistic information for computational painting categorization.We argue that such approaches are sub-optimal and that discriminative common visual structures provide complementary information for painting classification. We present an approach that encodes both the global scene layout and discriminative latent common structures for computational painting categorization. The region of interests are automatically extracted, without any manual part labeling, by training class-specific deformable part-based models. Both holistic and region-of-interests are then described using multi-scale dense convolutional features. These features are pooled separately using Fisher vector encoding and concatenated afterwards in a single image representation. Experiments are performed on a challenging dataset with 91 different painters and 13 diverse painting styles. Our approach outperforms the standard method, which only employs the global scene characteristics. Furthermore, our method achieves state-of-the-art results outperforming a recent multi-scale deep features based approach [11] by 6.4% and 3.8% respectively on artist and style classification. |
|
|
Address |
New York; USA; June 2016 |
|
|
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 |
ICMR |
|
|
Notes |
LAMP; 600.068; 600.079;ADAS |
Approved |
no |
|
|
Call Number |
Admin @ si @ RKW2016 |
Serial |
2763 |
|
Permanent link to this record |