Matches in SemOpenAlex for { <https://semopenalex.org/work/W4291653217> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W4291653217 endingPage "85940" @default.
- W4291653217 startingPage "85929" @default.
- W4291653217 abstract "Facial expression recognition (FER) is an extremely challenging task under unconstrained conditions. Especially, variant head poses degrade the performance dramatically due to the large variations in appearance of facial expressions. To address this problem, we propose a local attention network (LAN), which adaptively captures the important facial regions according to pose variations. The LAN emphasizes on more attentive regions while suppressing the regions not differentiated between classes. To find out attentive regions, we propose a simple yet efficient coarse-level attention guidance map annotation method in an unsupervised manner. The guidance map includes attention values for regions based on whether features are deformed by facial poses. Further, the attentive regional features obtained by our LAN and original global features are combined for pose-invariant FER. We validate our method on a controlled multiview dataset, KDEF, three popular in- the-wild datasets, RAF-DB, FERPlus, and AffectNet, and their subsets that contain images under pose variation conditions. Extensive experiments show that our LAN largely improves the performance of FER under pose variations. Our method also performs favorably against the previous methods." @default.
- W4291653217 created "2022-08-15" @default.
- W4291653217 creator A5029179064 @default.
- W4291653217 creator A5086483237 @default.
- W4291653217 date "2022-01-01" @default.
- W4291653217 modified "2023-09-27" @default.
- W4291653217 title "Learning Local Attention With Guidance Map for Pose Robust Facial Expression Recognition" @default.
- W4291653217 cites W171902450 @default.
- W4291653217 cites W1968015059 @default.
- W4291653217 cites W2060488580 @default.
- W4291653217 cites W2081835714 @default.
- W4291653217 cites W2095809036 @default.
- W4291653217 cites W2102605133 @default.
- W4291653217 cites W2104563967 @default.
- W4291653217 cites W2126234799 @default.
- W4291653217 cites W2138206939 @default.
- W4291653217 cites W2167015621 @default.
- W4291653217 cites W2194775991 @default.
- W4291653217 cites W2295107390 @default.
- W4291653217 cites W2481681431 @default.
- W4291653217 cites W2487852963 @default.
- W4291653217 cites W2730891243 @default.
- W4291653217 cites W2734399480 @default.
- W4291653217 cites W2738672149 @default.
- W4291653217 cites W2745497104 @default.
- W4291653217 cites W2787524669 @default.
- W4291653217 cites W2790989868 @default.
- W4291653217 cites W2798553619 @default.
- W4291653217 cites W2806927661 @default.
- W4291653217 cites W2886300652 @default.
- W4291653217 cites W2904483377 @default.
- W4291653217 cites W2963420686 @default.
- W4291653217 cites W2963559058 @default.
- W4291653217 cites W2997336602 @default.
- W4291653217 cites W3003720578 @default.
- W4291653217 cites W3034504038 @default.
- W4291653217 cites W3034552680 @default.
- W4291653217 cites W3035336958 @default.
- W4291653217 cites W3035783767 @default.
- W4291653217 cites W3101998545 @default.
- W4291653217 cites W3144848010 @default.
- W4291653217 cites W3182117591 @default.
- W4291653217 cites W3195286673 @default.
- W4291653217 cites W4285219239 @default.
- W4291653217 doi "https://doi.org/10.1109/access.2022.3198658" @default.
- W4291653217 hasPublicationYear "2022" @default.
- W4291653217 type Work @default.
- W4291653217 citedByCount "1" @default.
- W4291653217 countsByYear W42916532172022 @default.
- W4291653217 crossrefType "journal-article" @default.
- W4291653217 hasAuthorship W4291653217A5029179064 @default.
- W4291653217 hasAuthorship W4291653217A5086483237 @default.
- W4291653217 hasConcept C144024400 @default.
- W4291653217 hasConcept C153180895 @default.
- W4291653217 hasConcept C154945302 @default.
- W4291653217 hasConcept C162324750 @default.
- W4291653217 hasConcept C187736073 @default.
- W4291653217 hasConcept C195704467 @default.
- W4291653217 hasConcept C2779304628 @default.
- W4291653217 hasConcept C2780451532 @default.
- W4291653217 hasConcept C2987714656 @default.
- W4291653217 hasConcept C31510193 @default.
- W4291653217 hasConcept C31972630 @default.
- W4291653217 hasConcept C36289849 @default.
- W4291653217 hasConcept C41008148 @default.
- W4291653217 hasConceptScore W4291653217C144024400 @default.
- W4291653217 hasConceptScore W4291653217C153180895 @default.
- W4291653217 hasConceptScore W4291653217C154945302 @default.
- W4291653217 hasConceptScore W4291653217C162324750 @default.
- W4291653217 hasConceptScore W4291653217C187736073 @default.
- W4291653217 hasConceptScore W4291653217C195704467 @default.
- W4291653217 hasConceptScore W4291653217C2779304628 @default.
- W4291653217 hasConceptScore W4291653217C2780451532 @default.
- W4291653217 hasConceptScore W4291653217C2987714656 @default.
- W4291653217 hasConceptScore W4291653217C31510193 @default.
- W4291653217 hasConceptScore W4291653217C31972630 @default.
- W4291653217 hasConceptScore W4291653217C36289849 @default.
- W4291653217 hasConceptScore W4291653217C41008148 @default.
- W4291653217 hasLocation W42916532171 @default.
- W4291653217 hasLocation W42916532172 @default.
- W4291653217 hasOpenAccess W4291653217 @default.
- W4291653217 hasPrimaryLocation W42916532171 @default.
- W4291653217 hasRelatedWork W1775397219 @default.
- W4291653217 hasRelatedWork W1899364738 @default.
- W4291653217 hasRelatedWork W2103413230 @default.
- W4291653217 hasRelatedWork W2134472250 @default.
- W4291653217 hasRelatedWork W2248182120 @default.
- W4291653217 hasRelatedWork W2347601237 @default.
- W4291653217 hasRelatedWork W2897995864 @default.
- W4291653217 hasRelatedWork W2908959303 @default.
- W4291653217 hasRelatedWork W3194078543 @default.
- W4291653217 hasRelatedWork W43171467 @default.
- W4291653217 hasVolume "10" @default.
- W4291653217 isParatext "false" @default.
- W4291653217 isRetracted "false" @default.
- W4291653217 workType "article" @default.