Matches in SemOpenAlex for { <https://semopenalex.org/work/W3023278545> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W3023278545 abstract "The research of action recognition has achieved excellent progress and results, but the common datasets in action recognition research usually have a large number of samples and are suitable for the training of neural network, such as UCF-101 and Kinetics. For anomalous action research, it is difficult to collect and make datasets due to the rare occurrence of anomalous actions. Therefore, the research on few-shot learning of action recognition has certain significance. Based on the above, this paper studies the few-shot learning of anomalous action recognition. We present an anomalous action recognition network based on few-shot learning. We clip the videos in UCF-Crime datasets and other videos collected on the network to make a new dataset named UCF-Crime+. The action recognition network pre-trained by kinetics named I3D is used to extract the feature of the anomalous action video. We use a few-shot learning network, named prototypical network to classify the video feature samples, so as to realize the few-shot learning and classification of the anomalous video. In order to increase the difference between clusters, we use the triplet loss function. At the same time, the feature fusion of I3D network is carried out, which increases the utilization and fusion of deep and shallow features. The experimental results show that the improved few-shot learning model has higher accuracy than the base network." @default.
- W3023278545 created "2020-05-13" @default.
- W3023278545 creator A5019062529 @default.
- W3023278545 creator A5044897858 @default.
- W3023278545 creator A5057382261 @default.
- W3023278545 date "2020-06-01" @default.
- W3023278545 modified "2023-09-27" @default.
- W3023278545 title "Anomalous Action Recognition Research for Few-shot Learning" @default.
- W3023278545 cites W1983364832 @default.
- W3023278545 cites W2117539524 @default.
- W3023278545 cites W2401823607 @default.
- W3023278545 cites W24089286 @default.
- W3023278545 cites W2619947201 @default.
- W3023278545 cites W2943605315 @default.
- W3023278545 cites W2962721361 @default.
- W3023278545 doi "https://doi.org/10.1109/itnec48623.2020.9084815" @default.
- W3023278545 hasPublicationYear "2020" @default.
- W3023278545 type Work @default.
- W3023278545 sameAs 3023278545 @default.
- W3023278545 citedByCount "0" @default.
- W3023278545 crossrefType "proceedings-article" @default.
- W3023278545 hasAuthorship W3023278545A5019062529 @default.
- W3023278545 hasAuthorship W3023278545A5044897858 @default.
- W3023278545 hasAuthorship W3023278545A5057382261 @default.
- W3023278545 hasConcept C119857082 @default.
- W3023278545 hasConcept C120665830 @default.
- W3023278545 hasConcept C121332964 @default.
- W3023278545 hasConcept C127413603 @default.
- W3023278545 hasConcept C138885662 @default.
- W3023278545 hasConcept C153180895 @default.
- W3023278545 hasConcept C154945302 @default.
- W3023278545 hasConcept C178790620 @default.
- W3023278545 hasConcept C185592680 @default.
- W3023278545 hasConcept C2776401178 @default.
- W3023278545 hasConcept C2778344882 @default.
- W3023278545 hasConcept C2780791683 @default.
- W3023278545 hasConcept C2992734406 @default.
- W3023278545 hasConcept C3019835501 @default.
- W3023278545 hasConcept C41008148 @default.
- W3023278545 hasConcept C41895202 @default.
- W3023278545 hasConcept C50644808 @default.
- W3023278545 hasConcept C52622490 @default.
- W3023278545 hasConcept C62520636 @default.
- W3023278545 hasConcept C78519656 @default.
- W3023278545 hasConceptScore W3023278545C119857082 @default.
- W3023278545 hasConceptScore W3023278545C120665830 @default.
- W3023278545 hasConceptScore W3023278545C121332964 @default.
- W3023278545 hasConceptScore W3023278545C127413603 @default.
- W3023278545 hasConceptScore W3023278545C138885662 @default.
- W3023278545 hasConceptScore W3023278545C153180895 @default.
- W3023278545 hasConceptScore W3023278545C154945302 @default.
- W3023278545 hasConceptScore W3023278545C178790620 @default.
- W3023278545 hasConceptScore W3023278545C185592680 @default.
- W3023278545 hasConceptScore W3023278545C2776401178 @default.
- W3023278545 hasConceptScore W3023278545C2778344882 @default.
- W3023278545 hasConceptScore W3023278545C2780791683 @default.
- W3023278545 hasConceptScore W3023278545C2992734406 @default.
- W3023278545 hasConceptScore W3023278545C3019835501 @default.
- W3023278545 hasConceptScore W3023278545C41008148 @default.
- W3023278545 hasConceptScore W3023278545C41895202 @default.
- W3023278545 hasConceptScore W3023278545C50644808 @default.
- W3023278545 hasConceptScore W3023278545C52622490 @default.
- W3023278545 hasConceptScore W3023278545C62520636 @default.
- W3023278545 hasConceptScore W3023278545C78519656 @default.
- W3023278545 hasLocation W30232785451 @default.
- W3023278545 hasOpenAccess W3023278545 @default.
- W3023278545 hasPrimaryLocation W30232785451 @default.
- W3023278545 hasRelatedWork W11765363 @default.
- W3023278545 hasRelatedWork W12546350 @default.
- W3023278545 hasRelatedWork W13357224 @default.
- W3023278545 hasRelatedWork W1383942 @default.
- W3023278545 hasRelatedWork W14516383 @default.
- W3023278545 hasRelatedWork W2883085 @default.
- W3023278545 hasRelatedWork W5052411 @default.
- W3023278545 hasRelatedWork W5983547 @default.
- W3023278545 hasRelatedWork W9190101 @default.
- W3023278545 hasRelatedWork W9770290 @default.
- W3023278545 isParatext "false" @default.
- W3023278545 isRetracted "false" @default.
- W3023278545 magId "3023278545" @default.
- W3023278545 workType "article" @default.