Matches in SemOpenAlex for { <https://semopenalex.org/work/W4210262512> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W4210262512 endingPage "21" @default.
- W4210262512 startingPage "10" @default.
- W4210262512 abstract "Human action can be recognized in still images since the whole image represents an action with some spatial clues, such as human poses, action-specific parts, and global surroundings. To represent the spatial clues, the recent methods require labor-intensive annotations to locate the human body and objects, which are computationally intensive. To eliminate strong supervision, a Multiple Spatial Clues Network (MSCNet) is proposed to represent the spatial clues with only image-level action label. Neither accurately manual annotated bounding boxes nor extra labeled datasets are required as additional supervision. First, the proposed MSCNet exploits spatial-attention module to generate spatial attention regions, and detects the spatial clues with minimal supervision. Then, spatial clues exploitation is proposed to utilize the learned spatial clues with three modules: the context module, body + context module and body + semantics module. Experiments on three benchmark datasets demonstrate the effectiveness of the proposed MSCNet." @default.
- W4210262512 created "2022-02-08" @default.
- W4210262512 creator A5007883693 @default.
- W4210262512 creator A5018824735 @default.
- W4210262512 creator A5065068394 @default.
- W4210262512 creator A5068918243 @default.
- W4210262512 date "2022-04-01" @default.
- W4210262512 modified "2023-10-05" @default.
- W4210262512 title "Human action recognition by multiple spatial clues network" @default.
- W4210262512 cites W1536680647 @default.
- W4210262512 cites W1765260417 @default.
- W4210262512 cites W1976546217 @default.
- W4210262512 cites W2028138594 @default.
- W4210262512 cites W2037227137 @default.
- W4210262512 cites W2080873731 @default.
- W4210262512 cites W2102605133 @default.
- W4210262512 cites W2109875425 @default.
- W4210262512 cites W2129947832 @default.
- W4210262512 cites W2169852119 @default.
- W4210262512 cites W2194775991 @default.
- W4210262512 cites W2507518827 @default.
- W4210262512 cites W2510249351 @default.
- W4210262512 cites W2583194072 @default.
- W4210262512 cites W2650426111 @default.
- W4210262512 cites W2765246080 @default.
- W4210262512 cites W2765268259 @default.
- W4210262512 cites W2774319743 @default.
- W4210262512 cites W2791779647 @default.
- W4210262512 cites W2802056861 @default.
- W4210262512 cites W2884675507 @default.
- W4210262512 cites W2905037335 @default.
- W4210262512 cites W2921940552 @default.
- W4210262512 cites W2946820375 @default.
- W4210262512 cites W2949686305 @default.
- W4210262512 cites W2963097937 @default.
- W4210262512 cites W2964505754 @default.
- W4210262512 cites W3015031299 @default.
- W4210262512 cites W3020188837 @default.
- W4210262512 cites W3024041237 @default.
- W4210262512 cites W3030221510 @default.
- W4210262512 cites W3035201044 @default.
- W4210262512 cites W3036066034 @default.
- W4210262512 cites W3043248469 @default.
- W4210262512 cites W3082293699 @default.
- W4210262512 cites W3102046438 @default.
- W4210262512 cites W3154634026 @default.
- W4210262512 cites W3193627072 @default.
- W4210262512 cites W326271615 @default.
- W4210262512 cites W874179280 @default.
- W4210262512 doi "https://doi.org/10.1016/j.neucom.2022.01.091" @default.
- W4210262512 hasPublicationYear "2022" @default.
- W4210262512 type Work @default.
- W4210262512 citedByCount "1" @default.
- W4210262512 countsByYear W42102625122023 @default.
- W4210262512 crossrefType "journal-article" @default.
- W4210262512 hasAuthorship W4210262512A5007883693 @default.
- W4210262512 hasAuthorship W4210262512A5018824735 @default.
- W4210262512 hasAuthorship W4210262512A5065068394 @default.
- W4210262512 hasAuthorship W4210262512A5068918243 @default.
- W4210262512 hasConcept C121332964 @default.
- W4210262512 hasConcept C153180895 @default.
- W4210262512 hasConcept C154945302 @default.
- W4210262512 hasConcept C2777212361 @default.
- W4210262512 hasConcept C2780791683 @default.
- W4210262512 hasConcept C2987834672 @default.
- W4210262512 hasConcept C41008148 @default.
- W4210262512 hasConcept C62520636 @default.
- W4210262512 hasConceptScore W4210262512C121332964 @default.
- W4210262512 hasConceptScore W4210262512C153180895 @default.
- W4210262512 hasConceptScore W4210262512C154945302 @default.
- W4210262512 hasConceptScore W4210262512C2777212361 @default.
- W4210262512 hasConceptScore W4210262512C2780791683 @default.
- W4210262512 hasConceptScore W4210262512C2987834672 @default.
- W4210262512 hasConceptScore W4210262512C41008148 @default.
- W4210262512 hasConceptScore W4210262512C62520636 @default.
- W4210262512 hasLocation W42102625121 @default.
- W4210262512 hasOpenAccess W4210262512 @default.
- W4210262512 hasPrimaryLocation W42102625121 @default.
- W4210262512 hasRelatedWork W2033914206 @default.
- W4210262512 hasRelatedWork W2042327336 @default.
- W4210262512 hasRelatedWork W2046077695 @default.
- W4210262512 hasRelatedWork W2146076056 @default.
- W4210262512 hasRelatedWork W2163831990 @default.
- W4210262512 hasRelatedWork W2378160586 @default.
- W4210262512 hasRelatedWork W2941155331 @default.
- W4210262512 hasRelatedWork W2996038082 @default.
- W4210262512 hasRelatedWork W3003836766 @default.
- W4210262512 hasRelatedWork W3106494386 @default.
- W4210262512 hasVolume "483" @default.
- W4210262512 isParatext "false" @default.
- W4210262512 isRetracted "false" @default.
- W4210262512 workType "article" @default.