Zobrazeno 1 - 10
of 32
pro vyhledávání: '"Gkalelis, Nikolaos"'
The development and adoption of Vision Transformers and other deep-learning architectures for image classification tasks has been rapid. However, the "black box" nature of neural networks is a barrier to adoption in applications where explainability
Externí odkaz:
http://arxiv.org/abs/2403.04523
In this paper, we introduce Masked Feature Modelling (MFM), a novel approach for the unsupervised pre-training of a Graph Attention Network (GAT) block. MFM utilizes a pretrained Visual Tokenizer to reconstruct masked features of objects within a vid
Externí odkaz:
http://arxiv.org/abs/2308.12673
In this paper, Gated-ViGAT, an efficient approach for video event recognition, utilizing bottom-up (object) information, a new frame sampling policy and a gating mechanism is proposed. Specifically, the frame sampling policy uses weighted in-degrees
Externí odkaz:
http://arxiv.org/abs/2301.07565
The apparent ``black box'' nature of neural networks is a barrier to adoption in applications where explainability is essential. This paper presents TAME (Trainable Attention Mechanism for Explanations), a method for generating explanation maps with
Externí odkaz:
http://arxiv.org/abs/2301.07407
In this paper two new learning-based eXplainable AI (XAI) methods for deep convolutional neural network (DCNN) image classifiers, called L-CAM-Fm and L-CAM-Img, are proposed. Both methods use an attention mechanism that is inserted in the original (f
Externí odkaz:
http://arxiv.org/abs/2209.11189
ViGAT: Bottom-up event recognition and explanation in video using factorized graph attention network
Publikováno v:
IEEE Access, vol. 10, pp. 108797-108816, 2022
In this paper a pure-attention bottom-up approach, called ViGAT, that utilizes an object detector together with a Vision Transformer (ViT) backbone network to derive object and frame features, and a head network to process these features for the task
Externí odkaz:
http://arxiv.org/abs/2207.09927
Autor:
Gkalelis, Nikolaos
The management of digital video has become a very challenging problem as the amount of video content continues to witness phenomenal growth. This trend necessitates the development of advanced techniques for the efficient and effective manipulation o
Externí odkaz:
http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.650661
Autor:
Gkalelis, Nikolaos, Mezaris, Vasileios
In this paper, using a novel matrix factorization and simultaneous reduction to diagonal form approach (or in short simultaneous reduction approach), Accelerated Kernel Discriminant Analysis (AKDA) and Accelerated Kernel Subclass Discriminant Analysi
Externí odkaz:
http://arxiv.org/abs/1504.07000
Publikováno v:
2022 IEEE International Symposium on Multimedia (ISM)
The apparent ``black box'' nature of neural networks is a barrier to adoption in applications where explainability is essential. This paper presents TAME (Trainable Attention Mechanism for Explanations), a method for generating explanation maps with
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d62407507e138c65ec9258d36a5c9a1b
https://doi.org/10.1109/ism55400.2022.00014
https://doi.org/10.1109/ism55400.2022.00014
This paper presents our team’s (IDT-ITI-CERTH) proposed method for the Visual Sentiment Analysis task of the Mediaeval 2021 benchmarking activity. Visual sentiment analysis is a challenging task as it involves a high level of subjectivity. The most
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::34f07ce5cefd505d2266eda9ea49f744