Matches in SemOpenAlex for { <https://semopenalex.org/work/W4381233075> ?p ?o ?g. }
Showing items 1 to 68 of
68
with 100 items per page.
- W4381233075 endingPage "1" @default.
- W4381233075 startingPage "1" @default.
- W4381233075 abstract "Recent years have witnessed a growing interest in compressed video action recognition due to the rapid growth of online videos. It remarkably reduces the storage by replacing raw videos with sparsely sampled RGB frames and other compressed motion cues (motion vectors and residuals). However, existing compressed video action recognition methods face two main issues: First, the inefficiency caused by the usage of coarse-level information under full resolution, and second, the disturbing due to the noisy dynamics in motion vectors. To address the two issues, this paper proposes a dynamic spatial focus method for efficient compressed video action recognition (CoViFocus). Specifically, we first use a light-weighted two-stream architecture to localize the task-relevant patches for both the RGB frames and motion vectors. Then the selected patch pair will be processed by a high-capacity two-stream deep model for the final prediction. Such a patch selection strategy crops out the irrelevant motion noise in motion vectors, as well as reduces the spatial redundancy of the inputs, leading to the high efficiency of our method in the compressed domain. Moreover, we found that the motion vectors can help our method to address the possibly happened <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>static-issue</i> , which means that the focus patches get stuck at some regions related to static objects rather than target actions, which further improves our method. Extensive results on both the HMDB-51 and UCF-101 datasets demonstrate the effectiveness and efficiency of our method in compressed video action recognition tasks." @default.
- W4381233075 created "2023-06-20" @default.
- W4381233075 creator A5013240918 @default.
- W4381233075 creator A5015605020 @default.
- W4381233075 creator A5028955345 @default.
- W4381233075 creator A5029745350 @default.
- W4381233075 creator A5056506680 @default.
- W4381233075 creator A5063046834 @default.
- W4381233075 creator A5070173038 @default.
- W4381233075 date "2023-01-01" @default.
- W4381233075 modified "2023-10-15" @default.
- W4381233075 title "Dynamic Spatial Focus for Efficient Compressed Video Action Recognition" @default.
- W4381233075 doi "https://doi.org/10.1109/tcsvt.2023.3287201" @default.
- W4381233075 hasPublicationYear "2023" @default.
- W4381233075 type Work @default.
- W4381233075 citedByCount "0" @default.
- W4381233075 crossrefType "journal-article" @default.
- W4381233075 hasAuthorship W4381233075A5013240918 @default.
- W4381233075 hasAuthorship W4381233075A5015605020 @default.
- W4381233075 hasAuthorship W4381233075A5028955345 @default.
- W4381233075 hasAuthorship W4381233075A5029745350 @default.
- W4381233075 hasAuthorship W4381233075A5056506680 @default.
- W4381233075 hasAuthorship W4381233075A5063046834 @default.
- W4381233075 hasAuthorship W4381233075A5070173038 @default.
- W4381233075 hasConcept C10161872 @default.
- W4381233075 hasConcept C111919701 @default.
- W4381233075 hasConcept C120665830 @default.
- W4381233075 hasConcept C121332964 @default.
- W4381233075 hasConcept C128840427 @default.
- W4381233075 hasConcept C152124472 @default.
- W4381233075 hasConcept C153180895 @default.
- W4381233075 hasConcept C154945302 @default.
- W4381233075 hasConcept C192209626 @default.
- W4381233075 hasConcept C31972630 @default.
- W4381233075 hasConcept C41008148 @default.
- W4381233075 hasConcept C82990744 @default.
- W4381233075 hasConceptScore W4381233075C10161872 @default.
- W4381233075 hasConceptScore W4381233075C111919701 @default.
- W4381233075 hasConceptScore W4381233075C120665830 @default.
- W4381233075 hasConceptScore W4381233075C121332964 @default.
- W4381233075 hasConceptScore W4381233075C128840427 @default.
- W4381233075 hasConceptScore W4381233075C152124472 @default.
- W4381233075 hasConceptScore W4381233075C153180895 @default.
- W4381233075 hasConceptScore W4381233075C154945302 @default.
- W4381233075 hasConceptScore W4381233075C192209626 @default.
- W4381233075 hasConceptScore W4381233075C31972630 @default.
- W4381233075 hasConceptScore W4381233075C41008148 @default.
- W4381233075 hasConceptScore W4381233075C82990744 @default.
- W4381233075 hasFunder F4320321001 @default.
- W4381233075 hasFunder F4320321543 @default.
- W4381233075 hasLocation W43812330751 @default.
- W4381233075 hasOpenAccess W4381233075 @default.
- W4381233075 hasPrimaryLocation W43812330751 @default.
- W4381233075 hasRelatedWork W2046284878 @default.
- W4381233075 hasRelatedWork W2131710332 @default.
- W4381233075 hasRelatedWork W2132969715 @default.
- W4381233075 hasRelatedWork W2145347751 @default.
- W4381233075 hasRelatedWork W2147120701 @default.
- W4381233075 hasRelatedWork W2158825824 @default.
- W4381233075 hasRelatedWork W2901949253 @default.
- W4381233075 hasRelatedWork W4206673776 @default.
- W4381233075 hasRelatedWork W578691330 @default.
- W4381233075 hasRelatedWork W851866491 @default.
- W4381233075 isParatext "false" @default.
- W4381233075 isRetracted "false" @default.
- W4381233075 workType "article" @default.