|
Records |
Links |
|
Author |
Mikkel Thogersen; Sergio Escalera; Jordi Gonzalez; Thomas B. Moeslund |
|
|
Title |
Segmentation of RGB-D Indoor scenes by Stacking Random Forests and Conditional Random Fields |
Type |
Journal Article |
|
Year |
2016 |
Publication |
Pattern Recognition Letters |
Abbreviated Journal |
PRL |
|
|
Volume |
80 |
Issue |
|
Pages |
208–215 |
|
|
Keywords |
|
|
|
Abstract |
This paper proposes a technique for RGB-D scene segmentation using Multi-class
Multi-scale Stacked Sequential Learning (MMSSL) paradigm. Following recent trends in state-of-the-art, a base classifier uses an initial SLIC segmentation to obtain superpixels which provide a diminution of data while retaining object boundaries. A series of color and depth features are extracted from the superpixels, and are used in a Conditional Random Field (CRF) to predict superpixel labels. Furthermore, a Random Forest (RF) classifier using random offset features is also used as an input to the CRF, acting as an initial prediction. As a stacked classifier, another Random Forest is used acting on a spatial multi-scale decomposition of the CRF confidence map to correct the erroneous labels assigned by the previous classifier. The model is tested on the popular NYU-v2 dataset.
The approach shows that simple multi-modal features with the power of the MMSSL
paradigm can achieve better performance than state of the art results on the same dataset. |
|
|
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 |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
|
|
|
Notes |
HuPBA; ISE;MILAB; 600.098; 600.119 |
Approved |
no |
|
|
Call Number |
Admin @ si @ TEG2016 |
Serial |
2843 |
|
Permanent link to this record |
|
|
|
|
Author |
Sergio Escalera |
|
|
Title |
Multi-Modal Human Behaviour Analysis from Visual Data Sources |
Type |
Journal |
|
Year |
2013 |
Publication |
ERCIM News journal |
Abbreviated Journal |
ERCIM |
|
|
Volume |
95 |
Issue |
|
Pages |
21-22 |
|
|
Keywords |
|
|
|
Abstract |
The Human Pose Recovery and Behaviour Analysis group (HuPBA), University of Barcelona, is developing a line of research on multi-modal analysis of humans in visual data. The novel technology is being applied in several scenarios with high social impact, including sign language recognition, assisted technology and supported diagnosis for the elderly and people with mental/physical disabilities, fitness conditioning, and Human Computer Interaction. |
|
|
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 |
0926-4981 |
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
|
|
|
Notes |
HuPBA;MILAB |
Approved |
no |
|
|
Call Number |
Admin @ si @ Esc2013 |
Serial |
2361 |
|
Permanent link to this record |
|
|
|
|
Author |
Bhalaji Nagarajan; Marc Bolaños; Eduardo Aguilar; Petia Radeva |
|
|
Title |
Deep ensemble-based hard sample mining for food recognition |
Type |
Journal Article |
|
Year |
2023 |
Publication |
Journal of Visual Communication and Image Representation |
Abbreviated Journal |
JVCIR |
|
|
Volume |
95 |
Issue |
|
Pages |
103905 |
|
|
Keywords |
|
|
|
Abstract |
Deep neural networks represent a compelling technique to tackle complex real-world problems, but are over-parameterized and often suffer from over- or under-confident estimates. Deep ensembles have shown better parameter estimations and often provide reliable uncertainty estimates that contribute to the robustness of the results. In this work, we propose a new metric to identify samples that are hard to classify. Our metric is defined as coincidence score for deep ensembles which measures the agreement of its individual models. The main hypothesis we rely on is that deep learning algorithms learn the low-loss samples better compared to large-loss samples. In order to compensate for this, we use controlled over-sampling on the identified ”hard” samples using proper data augmentation schemes to enable the models to learn those samples better. We validate the proposed metric using two public food datasets on different backbone architectures and show the improvements compared to the conventional deep neural network training using different performance metrics. |
|
|
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 |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
|
|
|
Notes |
MILAB |
Approved |
no |
|
|
Call Number |
Admin @ si @ NBA2023 |
Serial |
3844 |
|
Permanent link to this record |
|
|
|
|
Author |
Debora Gil; Petia Radeva |
|
|
Title |
Extending anisotropic operators to recover smooth shapes |
Type |
Journal Article |
|
Year |
2005 |
Publication |
Computer Vision and Image Understanding |
Abbreviated Journal |
|
|
|
Volume |
99 |
Issue |
1 |
Pages |
110-125 |
|
|
Keywords |
Contour completion; Functional extension; Differential operators; Riemmanian manifolds; Snake segmentation |
|
|
Abstract |
Anisotropic differential operators are widely used in image enhancement processes. Recently, their property of smoothly extending functions to the whole image domain has begun to be exploited. Strong ellipticity of differential operators is a requirement that ensures existence of a unique solution. This condition is too restrictive for operators designed to extend image level sets: their own functionality implies that they should restrict to some vector field. The diffusion tensor that defines the diffusion operator links anisotropic processes with Riemmanian manifolds. In this context, degeneracy implies restricting diffusion to the varieties generated by the vector fields of positive eigenvalues, provided that an integrability condition is satisfied. We will use that any smooth vector field fulfills this integrability requirement to design line connection algorithms for contour completion. As application we present a segmenting strategy that assures convergent snakes whatever the geometry of the object to be modelled is. |
|
|
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 |
1077-3142 |
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
|
|
|
Notes |
IAM;MILAB |
Approved |
no |
|
|
Call Number |
IAM @ iam @ GIR2005 |
Serial |
1530 |
|
Permanent link to this record |
|
|
|
|
Author |
Maria Salamo; Sergio Escalera |
|
|
Title |
Increasing Retrieval Quality in Conversational Recommenders |
Type |
Journal Article |
|
Year |
2011 |
Publication |
IEEE Transactions on Knowledge and Data Engineering |
Abbreviated Journal |
TKDE |
|
|
Volume |
99 |
Issue |
|
Pages |
1-1 |
|
|
Keywords |
|
|
|
Abstract |
IF JCR CCIA 2.286 2009 24/103
JCR Impact Factor 2010: 1.851
A major task of research in conversational recommender systems is personalization. Critiquing is a common and powerful form of feedback, where a user can express her feature preferences by applying a series of directional critiques over the recommendations instead of providing specific preference values. Incremental Critiquing is a conversational recommender system that uses critiquing as a feedback to efficiently personalize products. The expectation is that in each cycle the system retrieves the products that best satisfy the user’s soft product preferences from a minimal information input. In this paper, we present a novel technique that increases retrieval quality based on a combination of compatibility and similarity scores. Under the hypothesis that a user learns Turing the recommendation process, we propose two novel exponential reinforcement learning approaches for compatibility that take into account both the instant at which the user makes a critique and the number of satisfied critiques. Moreover, we consider that the impact of features on the similarity differs according to the preferences manifested by the user. We propose a global weighting approach that uses a common weight for nearest cases in order to focus on groups of relevant products. We show that our methodology significantly improves recommendation efficiency in four data sets of different sizes in terms of session length in comparison with state-of-the-art approaches. Moreover, our recommender shows higher robustness against noisy user data when compared to classical approaches |
|
|
Address |
|
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
IEEE |
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
1041-4347 |
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
|
|
|
Notes |
MILAB; HuPBA |
Approved |
no |
|
|
Call Number |
Admin @ si @ SaE2011 |
Serial |
1713 |
|
Permanent link to this record |