Zobrazeno 1 - 10
of 3 150
pro vyhledávání: '"Melo, A M"'
Active Learning (AL) aims to enhance the performance of deep models by selecting the most informative samples for annotation from a pool of unlabeled data. Despite impressive performance in closed-set settings, most AL methods fail in real-world scen
Externí odkaz:
http://arxiv.org/abs/2312.14126
In this work, we tackle the problem of unsupervised domain adaptation (UDA) for video action recognition. Our approach, which we call UNITE, uses an image teacher model to adapt a video student model to the target domain. UNITE first employs self-sup
Externí odkaz:
http://arxiv.org/abs/2312.02914
Self-supervised Learning (SSL) aims to learn transferable feature representations for downstream applications without relying on labeled data. The Barlow Twins algorithm, renowned for its widespread adoption and straightforward implementation compare
Externí odkaz:
http://arxiv.org/abs/2312.02151
Autor:
Finardi, Paulo, Melo, Wanderley M., Neto, Edgard D. Medeiros, Mansano, Alex F., Costa, Pablo B., Caridá, Vinicius F.
Scarcity of domain-specific data in the Portuguese financial domain has disfavored the development of Natural Language Processing (NLP) applications. To address this limitation, the present study advocates for the utilization of synthetic data genera
Externí odkaz:
http://arxiv.org/abs/2311.11331
Autor:
de Melo, Álvaro M. G., Letellier, Hector, Apoorva, Apoorva, Glicenstein, Antoine, Kaiser, Robin
We report laser frequency stabilization by the combination of modulation transfer spectroscopy and balanced detection of a relatively weak hyperfine transition of the R(158)25-0 line of molecular iodine (${}^{127}$I$_{2}$), which is used as a new fre
Externí odkaz:
http://arxiv.org/abs/2311.08542
We study the problem of human action recognition using motion capture (MoCap) sequences. Unlike existing techniques that take multiple manual steps to derive standardized skeleton representations as model input, we propose a novel Spatial-Temporal Me
Externí odkaz:
http://arxiv.org/abs/2303.18177
Autor:
Reddy, Arun V., Shah, Ketul, Paul, William, Mocharla, Rohita, Hoffman, Judy, Katyal, Kapil D., Manocha, Dinesh, de Melo, Celso M., Chellappa, Rama
Human action recognition is a challenging problem, particularly when there is high variability in factors such as subject appearance, backgrounds and viewpoint. While deep neural networks (DNNs) have been shown to perform well on action recognition t
Externí odkaz:
http://arxiv.org/abs/2303.10280
Autor:
Wang, Xijun, Xian, Ruiqi, Guan, Tianrui, de Melo, Celso M., Nogar, Stephen M., Bera, Aniket, Manocha, Dinesh
We propose a novel approach for aerial video action recognition. Our method is designed for videos captured using UAVs and can run on edge or mobile devices. We present a learning-based approach that uses customized auto zoom to automatically identif
Externí odkaz:
http://arxiv.org/abs/2303.01589
Systems with 1-bit quantization and oversampling are promising for the Internet of Things (IoT) devices in order to reduce the power consumption of the analog-to-digital-converters. The novel time-instance zero-crossing (TI ZX) modulation is a promis
Externí odkaz:
http://arxiv.org/abs/2301.12035
Automatic Target Recognition (ATR) is a category of computer vision algorithms which attempts to recognize targets on data obtained from different sensors. ATR algorithms are extensively used in real-world scenarios such as military and surveillance
Externí odkaz:
http://arxiv.org/abs/2211.05883