Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312940571> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4312940571 abstract "Automating video-based data and machine learning pipelines poses several challenges including metadata generation for efficient storage and retrieval and isolation of key-frames for scene understanding tasks. In this work, we present two semi-supervised approaches that automate this process of manual frame sifting in video streams by automatically classifying scenes for content and filtering frames for fine-tuning scene understanding tasks. The first rule-based method starts from a pre-trained object detector and it assigns scene type, uncertainty and lighting categories to each frame based on probability distributions of foreground objects. Next, frames with the highest uncertainty and structural dissimilarity are isolated as key-frames. The second method relies on the simCLR model for frame encoding followed by label-spreading from 20% of frame samples to label the remaining frames for scene and lighting categories. Also, clustering the video frames in the encoded feature space further isolates key-frames at cluster boundaries. The proposed methods achieve 64–93% accuracy for automated scene categorization for outdoor image videos from public domain datasets of JAAD and KITTI. Also, less than 10% of all input frames can be filtered as key-frames that can then be sent for annotation and fine tuning of machine vision algorithms. Thus, the proposed framework can be scaled to additional video data streams for automated training of perception-driven systems with minimal training images." @default.
- W4312940571 created "2023-01-05" @default.
- W4312940571 creator A5050360160 @default.
- W4312940571 creator A5053638360 @default.
- W4312940571 date "2022-07-18" @default.
- W4312940571 modified "2023-09-28" @default.
- W4312940571 title "Semi-supervised and Deep learning Frameworks for Video Classification and Key-frame Identification" @default.
- W4312940571 cites W2065244205 @default.
- W4312940571 cites W2150066425 @default.
- W4312940571 cites W2771583656 @default.
- W4312940571 cites W2919234133 @default.
- W4312940571 cites W3107543738 @default.
- W4312940571 cites W3188533866 @default.
- W4312940571 cites W639708223 @default.
- W4312940571 doi "https://doi.org/10.1109/ijcnn55064.2022.9891884" @default.
- W4312940571 hasPublicationYear "2022" @default.
- W4312940571 type Work @default.
- W4312940571 citedByCount "0" @default.
- W4312940571 crossrefType "proceedings-article" @default.
- W4312940571 hasAuthorship W4312940571A5050360160 @default.
- W4312940571 hasAuthorship W4312940571A5053638360 @default.
- W4312940571 hasBestOaLocation W43129405712 @default.
- W4312940571 hasConcept C111919701 @default.
- W4312940571 hasConcept C126042441 @default.
- W4312940571 hasConcept C153180895 @default.
- W4312940571 hasConcept C154945302 @default.
- W4312940571 hasConcept C199360897 @default.
- W4312940571 hasConcept C26517878 @default.
- W4312940571 hasConcept C2780139006 @default.
- W4312940571 hasConcept C31972630 @default.
- W4312940571 hasConcept C38652104 @default.
- W4312940571 hasConcept C41008148 @default.
- W4312940571 hasConcept C43521106 @default.
- W4312940571 hasConcept C73555534 @default.
- W4312940571 hasConcept C76155785 @default.
- W4312940571 hasConcept C93518851 @default.
- W4312940571 hasConcept C94124525 @default.
- W4312940571 hasConcept C98045186 @default.
- W4312940571 hasConceptScore W4312940571C111919701 @default.
- W4312940571 hasConceptScore W4312940571C126042441 @default.
- W4312940571 hasConceptScore W4312940571C153180895 @default.
- W4312940571 hasConceptScore W4312940571C154945302 @default.
- W4312940571 hasConceptScore W4312940571C199360897 @default.
- W4312940571 hasConceptScore W4312940571C26517878 @default.
- W4312940571 hasConceptScore W4312940571C2780139006 @default.
- W4312940571 hasConceptScore W4312940571C31972630 @default.
- W4312940571 hasConceptScore W4312940571C38652104 @default.
- W4312940571 hasConceptScore W4312940571C41008148 @default.
- W4312940571 hasConceptScore W4312940571C43521106 @default.
- W4312940571 hasConceptScore W4312940571C73555534 @default.
- W4312940571 hasConceptScore W4312940571C76155785 @default.
- W4312940571 hasConceptScore W4312940571C93518851 @default.
- W4312940571 hasConceptScore W4312940571C94124525 @default.
- W4312940571 hasConceptScore W4312940571C98045186 @default.
- W4312940571 hasLocation W43129405711 @default.
- W4312940571 hasLocation W43129405712 @default.
- W4312940571 hasOpenAccess W4312940571 @default.
- W4312940571 hasPrimaryLocation W43129405711 @default.
- W4312940571 hasRelatedWork W2002492624 @default.
- W4312940571 hasRelatedWork W2132593223 @default.
- W4312940571 hasRelatedWork W2372652133 @default.
- W4312940571 hasRelatedWork W2394559091 @default.
- W4312940571 hasRelatedWork W2571916269 @default.
- W4312940571 hasRelatedWork W2588505718 @default.
- W4312940571 hasRelatedWork W2810201907 @default.
- W4312940571 hasRelatedWork W2906664357 @default.
- W4312940571 hasRelatedWork W4213373515 @default.
- W4312940571 hasRelatedWork W855007925 @default.
- W4312940571 isParatext "false" @default.
- W4312940571 isRetracted "false" @default.
- W4312940571 workType "article" @default.