Matches in SemOpenAlex for { <https://semopenalex.org/work/W4382053020> ?p ?o ?g. }
- W4382053020 abstract "A method of facial expression recognition using a vision language model is proposed. Recently vision-language models for example CLIP (Contrastive Language-Image Pre-training) models developed by OpenAI have achieved exceptional results on a variety of image recognition and retrieval tasks, exhibiting strong zero-shot performance. Transferable representations can be adapted through prompt tuning to a variety of downstream tasks. From the general knowledge stored in a pre-trained model, prompt tuning attempts to extract useful information for downstream tasks. In order to avoid time-consuming prompt engineering, recent works use a small amount of labeled data for adapting vision language models to downstream image recognition problems. However, requiring target datasets to be labeled may restrict their scalability. Moreover, we also note that adapting prompt learning techniques in only one branch of CLIP (vision or language) is suboptimal because it won't allow for the dynamic adjustment of both representation spaces on a downstream task. In this paper, we evaluated the performance of the CLIP model as a zero-shot face recognizer and proposed an Unsupervised Dual Modality Prompt Learning framework for Facial Expression Recognition. Our model tunes the prompts through learning text and visual prompts simultaneously to improve alignment between the linguistic and visual representations when labels are not provided for the target dataset. The experimental results on CK+, JAFFE, RAF-DB, and FER2013 datasets showed that our proposed method performs better compared with CLIP Zero-Shot and other unsupervised prompt-based learning methods for facial expression recognition tasks." @default.
- W4382053020 created "2023-06-27" @default.
- W4382053020 creator A5075523693 @default.
- W4382053020 date "2023-04-21" @default.
- W4382053020 modified "2023-09-23" @default.
- W4382053020 title "Unsupervised Dual Modality Prompt Learning for Facial Expression Recognition" @default.
- W4382053020 cites W2041616772 @default.
- W4382053020 cites W2103943262 @default.
- W4382053020 cites W2106115875 @default.
- W4382053020 cites W2108598243 @default.
- W4382053020 cites W2194775991 @default.
- W4382053020 cites W2560730294 @default.
- W4382053020 cites W2562153041 @default.
- W4382053020 cites W2738672149 @default.
- W4382053020 cites W2766176255 @default.
- W4382053020 cites W2955429306 @default.
- W4382053020 cites W2963785020 @default.
- W4382053020 cites W2964345214 @default.
- W4382053020 cites W2990230185 @default.
- W4382053020 cites W3034655362 @default.
- W4382053020 cites W3098267758 @default.
- W4382053020 cites W3166986030 @default.
- W4382053020 cites W3174770825 @default.
- W4382053020 cites W3205021045 @default.
- W4382053020 cites W4205991051 @default.
- W4382053020 cites W4285247752 @default.
- W4382053020 cites W4312238419 @default.
- W4382053020 cites W4312310776 @default.
- W4382053020 cites W4312424618 @default.
- W4382053020 cites W4324080637 @default.
- W4382053020 doi "https://doi.org/10.1109/icccs57501.2023.10151313" @default.
- W4382053020 hasPublicationYear "2023" @default.
- W4382053020 type Work @default.
- W4382053020 citedByCount "0" @default.
- W4382053020 crossrefType "proceedings-article" @default.
- W4382053020 hasAuthorship W4382053020A5075523693 @default.
- W4382053020 hasConcept C119857082 @default.
- W4382053020 hasConcept C124952713 @default.
- W4382053020 hasConcept C136197465 @default.
- W4382053020 hasConcept C142362112 @default.
- W4382053020 hasConcept C144024400 @default.
- W4382053020 hasConcept C153180895 @default.
- W4382053020 hasConcept C154945302 @default.
- W4382053020 hasConcept C162324750 @default.
- W4382053020 hasConcept C17744445 @default.
- W4382053020 hasConcept C187736073 @default.
- W4382053020 hasConcept C195704467 @default.
- W4382053020 hasConcept C199360897 @default.
- W4382053020 hasConcept C199539241 @default.
- W4382053020 hasConcept C204321447 @default.
- W4382053020 hasConcept C2776359362 @default.
- W4382053020 hasConcept C2779304628 @default.
- W4382053020 hasConcept C2780226545 @default.
- W4382053020 hasConcept C2780451532 @default.
- W4382053020 hasConcept C2780980858 @default.
- W4382053020 hasConcept C36289849 @default.
- W4382053020 hasConcept C41008148 @default.
- W4382053020 hasConcept C48044578 @default.
- W4382053020 hasConcept C59404180 @default.
- W4382053020 hasConcept C77088390 @default.
- W4382053020 hasConcept C90559484 @default.
- W4382053020 hasConcept C94625758 @default.
- W4382053020 hasConceptScore W4382053020C119857082 @default.
- W4382053020 hasConceptScore W4382053020C124952713 @default.
- W4382053020 hasConceptScore W4382053020C136197465 @default.
- W4382053020 hasConceptScore W4382053020C142362112 @default.
- W4382053020 hasConceptScore W4382053020C144024400 @default.
- W4382053020 hasConceptScore W4382053020C153180895 @default.
- W4382053020 hasConceptScore W4382053020C154945302 @default.
- W4382053020 hasConceptScore W4382053020C162324750 @default.
- W4382053020 hasConceptScore W4382053020C17744445 @default.
- W4382053020 hasConceptScore W4382053020C187736073 @default.
- W4382053020 hasConceptScore W4382053020C195704467 @default.
- W4382053020 hasConceptScore W4382053020C199360897 @default.
- W4382053020 hasConceptScore W4382053020C199539241 @default.
- W4382053020 hasConceptScore W4382053020C204321447 @default.
- W4382053020 hasConceptScore W4382053020C2776359362 @default.
- W4382053020 hasConceptScore W4382053020C2779304628 @default.
- W4382053020 hasConceptScore W4382053020C2780226545 @default.
- W4382053020 hasConceptScore W4382053020C2780451532 @default.
- W4382053020 hasConceptScore W4382053020C2780980858 @default.
- W4382053020 hasConceptScore W4382053020C36289849 @default.
- W4382053020 hasConceptScore W4382053020C41008148 @default.
- W4382053020 hasConceptScore W4382053020C48044578 @default.
- W4382053020 hasConceptScore W4382053020C59404180 @default.
- W4382053020 hasConceptScore W4382053020C77088390 @default.
- W4382053020 hasConceptScore W4382053020C90559484 @default.
- W4382053020 hasConceptScore W4382053020C94625758 @default.
- W4382053020 hasLocation W43820530201 @default.
- W4382053020 hasOpenAccess W4382053020 @default.
- W4382053020 hasPrimaryLocation W43820530201 @default.
- W4382053020 hasRelatedWork W2031420897 @default.
- W4382053020 hasRelatedWork W2081647779 @default.
- W4382053020 hasRelatedWork W2136485282 @default.
- W4382053020 hasRelatedWork W2168819821 @default.
- W4382053020 hasRelatedWork W2347601237 @default.
- W4382053020 hasRelatedWork W2353697322 @default.
- W4382053020 hasRelatedWork W2383164569 @default.
- W4382053020 hasRelatedWork W2897995864 @default.
- W4382053020 hasRelatedWork W3185852197 @default.