Title | ||
---|---|---|
Combining gradient histograms using orientation tensors for human action recognition. |
Abstract | ||
---|---|---|
We present a method for human action recognition based on the combination of Histograms of Gradients into orientation tensors. It uses only information from HOG3D: no features or points of interest are extracted. The resulting raw histograms obtained per frame are combined into an orientation tensor, making it a simple, fast to compute and effective global descriptor. The addition of new videos and/or new action cathegories does not require any recomputation or changes to the previously computed descriptors. Our method reaches 92:01% of recognition rate with KTH, comparable to the best local approaches. For the Hollywood2 dataset, our recognition rate is lower than local approaches but is fairly competitive, suitable when the dataset is frequently updated or the time response is a major application issue. |
Year | Venue | Keywords |
---|---|---|
2012 | ICPR | gradient methods,tensors,video databases,video signal processing,HOG3D information,Hollywood2 dataset,KTH,global descriptor,histograms of gradients,human action recognition,orientation tensors,previously computed descriptors,recognition rate,video analysis |
Field | DocType | ISSN |
Computer vision,Histogram,Tensor,Pattern recognition,Computer science,Action recognition,Artificial intelligence,Orientation tensor,Point of interest,Time response | Conference | 1051-4651 |
Citations | PageRank | References |
3 | 0.39 | 0 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Eder de Almeida Perez | 1 | 4 | 1.14 |
Virgínia Fernandes Mota | 2 | 5 | 2.17 |
Luiz Maurilio Maciel | 3 | 4 | 0.74 |
Dhiego Oliveira Sad | 4 | 4 | 1.08 |
Marcelo Bernardes Vieira | 5 | 50 | 15.30 |