A Tensor Motion Descriptor Based on Multiple Gradient Estimators

Sad, Dhiego Oliveira; Mota, Virgínia Fernandes; Maciel, Luiz Maurílio da Silva; Vieira, Marcelo Bernardes; Araújo, Arnaldo A.

doi:10.1109/sibgrapi.2013.19

Cited by 7 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Trajectories Relationship Modeling [24] 95.6 [25] 97.4 [26] 98.2 [27] 94.8* [28] 95.3 [29] 94.5 [30] 93.9 [31] 94.2 [32] 94.5 [33] 93.8 Tensor [34] 94.2 Our approaches [18] 93.3 [20] 93.2 [19] 92.5 [21] 92.0 [22] 87.8 [23] 86.6…”

Section: Local Descriptorsmentioning

confidence: 99%

FASTensor: A tensor framework for spatiotemporal description

Mota¹,

Santos²,

Araújo³

2019

Anais Estendidos Do XXXII Conference on Graphics, Patterns and Images (SIBRAPI Estendido 2019)

View full text Add to dashboard Cite

Spatiotemporal description is a research field with applications in various areas such as video indexing, surveillance, human-computer interfaces, among others. Big Data problems in large databases are now being treated with Deep Learning tools, however we still have room for improvement in spatiotemporal handcraft description. Moreover, we still have problems that involve small data in which data augmentation and other techniques are not valid. The main contribution of this Ph.D. Thesis 1 is the development of a framework for spatiotemporal representation using orientation tensors enabling dimension reduction and invariance. This is a multipurpose framework called Features As Spatiotemporal Tensors (FASTensor). We evaluate this framework in three different applications: Human Action recognition, Video Pornography classification and Cancer Cell classification. The latter one is also a contribution of this work, since we introduce a new dataset called Melanoma Cancer Cell dataset (MCC). It is a small data that cannot be artificially augmented due the difficulty of extraction and the nature of motion. The results were competitive, while also being fast and simple to implement. Finally, our results in the MCC dataset can be used in other cancer cell treatment analysis.

show abstract

Section: Local Descriptorsmentioning

confidence: 99%

FASTensor: A tensor framework for spatiotemporal description

Mota¹,

Santos²,

Araújo³

2019

Anais Estendidos Do XXXII Conference on Graphics, Patterns and Images (SIBRAPI Estendido 2019)

View full text Add to dashboard Cite

show abstract

“…The proposed version outperforms approaches from the same period in most of the evaluated datasets. Many other HOG-based descriptors have been proposed in the literature [59,78,91,93,103,110], achieving good rates and consolidating HOG as an important tool for the human action recognition problem.…”

Section: Chapter 3 Related Workmentioning

confidence: 99%

Visual rhythm-based convolutional neural networks and adaptive fusion for a multi-stream architecture applied to human action recognition

Maia¹

View full text Add to dashboard Cite

laborate. I am very thankful to my family. My parents for the support, my sisters, with whom I talked almost every day during these five years, my lovely nieces Isadora and Elisa, and my unborn nephew Apolo. I am grateful to my grandmother Ana for being by my side when I decided to move to Campinas. I thank Aza for the privilege of being together with a scientist who provided me many rich discussions and for being so supportive during these years. I thank his mother, Vera, for encouraging me to travel to the conferences.I thank my friends, Bel, Bruno, Carol, Dani, Laura, Leticia, Luiz, Ronaro, Sandra and Weslley, for the oldest and invaluable friendship, and Caetano for the talks and music sharing. I thank the DPG group for the gaming sessions. I thank my friends from Campinas Carol, Fabi, Luís, Mari, Otávio, Peixe and Samuka for their friendship during this time. I also thank my first friends from Campinas, my roommates from the first house.

show abstract