toggle visibility Search & Display Options

Select All    Deselect All
 |   | 
Details
  Records Links
Author Swathikiran Sudhakaran; Sergio Escalera; Oswald Lanz edit   pdf
doi  openurl
  Title Gate-Shift-Fuse for Video Action Recognition Type Journal Article
  Year (down) 2023 Publication IEEE Transactions on Pattern Analysis and Machine Intelligence Abbreviated Journal TPAMI  
  Volume 45 Issue 9 Pages 10913-10928  
  Keywords Action Recognition; Video Classification; Spatial Gating; Channel Fusion  
  Abstract Convolutional Neural Networks are the de facto models for image recognition. However 3D CNNs, the straight forward extension of 2D CNNs for video recognition, have not achieved the same success on standard action recognition benchmarks. One of the main reasons for this reduced performance of 3D CNNs is the increased computational complexity requiring large scale annotated datasets to train them in scale. 3D kernel factorization approaches have been proposed to reduce the complexity of 3D CNNs. Existing kernel factorization approaches follow hand-designed and hard-wired techniques. In this paper we propose Gate-Shift-Fuse (GSF), a novel spatio-temporal feature extraction module which controls interactions in spatio-temporal decomposition and learns to adaptively route features through time and combine them in a data dependent manner. GSF leverages grouped spatial gating to decompose input tensor and channel weighting to fuse the decomposed tensors. GSF can be inserted into existing 2D CNNs to convert them into an efficient and high performing spatio-temporal feature extractor, with negligible parameter and compute overhead. We perform an extensive analysis of GSF using two popular 2D CNN families and achieve state-of-the-art or competitive performance on five standard action recognition benchmarks.  
  Address 1 Sept. 2023  
  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; no menciona;MILAB Approved no  
  Call Number Admin @ si @ SEL2023 Serial 3814  
Permanent link to this record
 

 
Author Zahra Raisi-Estabragh; Carlos Martin-Isla; Louise Nissen; Liliana Szabo; Victor M. Campello; Sergio Escalera; Simon Winther; Morten Bottcher; Karim Lekadir; and Steffen E. Petersen edit  url
openurl 
  Title Radiomics analysis enhances the diagnostic performance of CMR stress perfusion: a proof-of-concept study using the Dan-NICAD dataset Type Journal Article
  Year (down) 2023 Publication Frontiers in Cardiovascular Medicine Abbreviated Journal FCM  
  Volume Issue Pages  
  Keywords  
  Abstract  
  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;MILAB Approved no  
  Call Number Admin @ si @ RMN2023 Serial 3937  
Permanent link to this record
 

 
Author Ajian Liu; Chenxu Zhao; Zitong Yu; Jun Wan; Anyang Su; Xing Liu; Zichang Tan; Sergio Escalera; Junliang Xing; Yanyan Liang; Guodong Guo; Zhen Lei; Stan Z. Li; Shenshen Du edit  doi
openurl 
  Title Contrastive Context-Aware Learning for 3D High-Fidelity Mask Face Presentation Attack Detection Type Journal Article
  Year (down) 2022 Publication IEEE Transactions on Information Forensics and Security Abbreviated Journal TIForensicSEC  
  Volume 17 Issue Pages 2497 - 2507  
  Keywords  
  Abstract Face presentation attack detection (PAD) is essential to secure face recognition systems primarily from high-fidelity mask attacks. Most existing 3D mask PAD benchmarks suffer from several drawbacks: 1) a limited number of mask identities, types of sensors, and a total number of videos; 2) low-fidelity quality of facial masks. Basic deep models and remote photoplethysmography (rPPG) methods achieved acceptable performance on these benchmarks but still far from the needs of practical scenarios. To bridge the gap to real-world applications, we introduce a large-scale Hi gh- Fi delity Mask dataset, namely HiFiMask . Specifically, a total amount of 54,600 videos are recorded from 75 subjects with 225 realistic masks by 7 new kinds of sensors. Along with the dataset, we propose a novel C ontrastive C ontext-aware L earning (CCL) framework. CCL is a new training methodology for supervised PAD tasks, which is able to learn by leveraging rich contexts accurately (e.g., subjects, mask material and lighting) among pairs of live faces and high-fidelity mask attacks. Extensive experimental evaluations on HiFiMask and three additional 3D mask datasets demonstrate the effectiveness of our method. The codes and dataset will be released soon.  
  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 ISBN Medium  
  Area Expedition Conference  
  Notes HuPBA;MILAB Approved no  
  Call Number Admin @ si @ LZY2022 Serial 3778  
Permanent link to this record
 

 
Author Hugo Jair Escalante; Heysem Kaya; Albert Ali Salah; Sergio Escalera; Yagmur Gucluturk; Umut Guçlu; Xavier Baro; Isabelle Guyon; Julio C. S. Jacques Junior; Meysam Madadi; Stephane Ayache; Evelyne Viegas; Furkan Gurpinar; Achmadnoer Sukma Wicaksana; Cynthia Liem; Marcel A. J. Van Gerven; Rob Van Lier edit   pdf
url  doi
openurl 
  Title Modeling, Recognizing, and Explaining Apparent Personality from Videos Type Journal Article
  Year (down) 2022 Publication IEEE Transactions on Affective Computing Abbreviated Journal TAC  
  Volume 13 Issue 2 Pages 894-911  
  Keywords  
  Abstract Explainability and interpretability are two critical aspects of decision support systems. Despite their importance, it is only recently that researchers are starting to explore these aspects. This paper provides an introduction to explainability and interpretability in the context of apparent personality recognition. To the best of our knowledge, this is the first effort in this direction. We describe a challenge we organized on explainability in first impressions analysis from video. We analyze in detail the newly introduced data set, evaluation protocol, proposed solutions and summarize the results of the challenge. We investigate the issue of bias in detail. Finally, derived from our study, we outline research opportunities that we foresee will be relevant in this area in the near future.  
  Address 1 April-June 2022  
  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; no menciona;MV;OR;MILAB Approved no  
  Call Number Admin @ si @ EKS2022 Serial 3406  
Permanent link to this record
 

 
Author Joakim Bruslund Haurum; Meysam Madadi; Sergio Escalera; Thomas B. Moeslund edit  doi
openurl 
  Title Multi-scale hybrid vision transformer and Sinkhorn tokenizer for sewer defect classification Type Journal Article
  Year (down) 2022 Publication Automation in Construction Abbreviated Journal AC  
  Volume 144 Issue Pages 104614  
  Keywords Sewer Defect Classification; Vision Transformers; Sinkhorn-Knopp; Convolutional Neural Networks; Closed-Circuit Television; Sewer Inspection  
  Abstract A crucial part of image classification consists of capturing non-local spatial semantics of image content. This paper describes the multi-scale hybrid vision transformer (MSHViT), an extension of the classical convolutional neural network (CNN) backbone, for multi-label sewer defect classification. To better model spatial semantics in the images, features are aggregated at different scales non-locally through the use of a lightweight vision transformer, and a smaller set of tokens was produced through a novel Sinkhorn clustering-based tokenizer using distinct cluster centers. The proposed MSHViT and Sinkhorn tokenizer were evaluated on the Sewer-ML multi-label sewer defect classification dataset, showing consistent performance improvements of up to 2.53 percentage points.  
  Address Dec 2022  
  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;MILAB Approved no  
  Call Number Admin @ si @ BME2022c Serial 3780  
Permanent link to this record
Select All    Deselect All
 |   | 
Details

Save Citations:
Export Records: