Zobrazeno 1 - 10
of 181
pro vyhledávání: '"Yaghoubi, Ehsan"'
Autor:
Kelm, André, Hannemann, Niels, Heberle, Bruno, Schmidt, Lucas, Rolff, Tim, Wilms, Christian, Yaghoubi, Ehsan, Frintrop, Simone
This study introduces a novel expert generation method that dynamically reduces task and computational complexity without compromising predictive performance. It is based on a new hierarchical classification network topology that combines sequential
Externí odkaz:
http://arxiv.org/abs/2403.05601
Autor:
Kelm, André Peter, Hannemann, Niels, Heberle, Bruno, Schmidt, Lucas, Rolff, Tim, Wilms, Christian, Yaghoubi, Ehsan, Frintrop, Simone
This paper introduces a novel network topology that seamlessly integrates dynamic inference cost with a top-down attention mechanism, addressing two significant gaps in traditional deep learning models. Drawing inspiration from human perception, we c
Externí odkaz:
http://arxiv.org/abs/2308.05128
Synthesising the spatial and temporal dynamics of the human body skeleton remains a challenging task, not only in terms of the quality of the generated shapes, but also of their diversity, particularly to synthesise realistic body movements of a spec
Externí odkaz:
http://arxiv.org/abs/2110.11191
Autor:
Haigh, Robert, Sandanayake, Malindu, Sasi, Soorya, Yaghoubi, Ehsan, Joseph, Paul, Vrcelj, Zora
Publikováno v:
In Journal of Building Engineering 1 June 2024 86
Autor:
Yaghoubi, Ehsan, Ghorbani, Behnam, Saberian, Mohammad, van Staden, Rudi, Guerrieri, Maurice, Fragomeni, Sam
Publikováno v:
In Journal of Building Engineering 1 April 2024 82
In video-based person re-identification, both the spatial and temporal features are known to provide orthogonal cues to effective representations. Such representations are currently typically obtained by aggregating the frame-level features using max
Externí odkaz:
http://arxiv.org/abs/2006.11416
Over the last decades, the world has been witnessing growing threats to the security in urban spaces, which has augmented the relevance given to visual surveillance solutions able to detect, track and identify persons of interest in crowds. In partic
Externí odkaz:
http://arxiv.org/abs/2004.02782
The automatic characterization of pedestrians in surveillance footage is a tough challenge, particularly when the data is extremely diverse with cluttered backgrounds, and subjects are captured from varying distances, under multiple poses, with parti
Externí odkaz:
http://arxiv.org/abs/2004.01110
This paper describes one objective function for learning semantically coherent feature embeddings in multi-output classification problems, i.e., when the response variables have dimension higher than one. In particular, we consider the problems of id
Externí odkaz:
http://arxiv.org/abs/2002.11644
The \emph{receptive fields} of deep learning classification models determine the regions of the input data that have the most significance for providing correct decisions. The primary way to learn such receptive fields is to train the models upon mas
Externí odkaz:
http://arxiv.org/abs/2001.11267