Progressive Instance-Aware Feature Learning for Compositional Action Recognition

Progressive Instance-Aware Feature Learning for Compositional Action Recognition

In order to enable the model to generalize to unseen "action-objects" (compositional action), previous methods encode multiple pieces of information (i.e., the appearance, position, and identity of visual instances) independently and concatenate them for classification. However, these meth...

Description complète

Détails bibliographiques
Publié dans:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 45(2023), 8 vom: 17. Aug., Seite 10317-10330
Auteur principal: Yan, Rui (Auteur)
Autres auteurs: Xie, Lingxi, Shu, Xiangbo, Zhang, Liyan, Tang, Jinhui
Format: Article en ligne
Langue:English
Publié: 2023
Accès à la collection:IEEE transactions on pattern analysis and machine intelligence
Sujets:Journal Article
LEADER 01000caa a22002652c 4500
001 NLM355354411
003 DE-627
005 20250304152808.0
007 cr uuu---uuuuu
008 231226s2023 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2023.3261659  |2 doi 
028 5 2 |a pubmed25n1184.xml 
035 |a (DE-627)NLM355354411 
035 |a (NLM)37030795 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Yan, Rui  |e verfasserin  |4 aut 
245 1 0 |a Progressive Instance-Aware Feature Learning for Compositional Action Recognition 
264 1 |c 2023 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Revised 04.06.2024 
500 |a published: Print-Electronic 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a In order to enable the model to generalize to unseen "action-objects" (compositional action), previous methods encode multiple pieces of information (i.e., the appearance, position, and identity of visual instances) independently and concatenate them for classification. However, these methods ignore the potential supervisory role of instance information (i.e., position and identity) in the process of visual perception. To this end, we present a novel framework, namely Progressive Instance-aware Feature Learning (PIFL), to progressively extract, reason, and predict dynamic cues of moving instances from videos for compositional action recognition. Specifically, this framework extracts features from foreground instances that are likely to be relevant to human actions (Position-aware Appearance Feature Extraction in Section III-B1), performs identity-aware reasoning among instance-centric features with semantic-specific interactions (Identity-aware Feature Interaction in Section III-B2), and finally predicts instances' position from observed states to force the model into perceiving their movement (Semantic-aware Position Prediction in Section III-B3). We evaluate our approach on two compositional action recognition benchmarks, namely, Something-Else and IKEA-Assembly. Our approach achieves consistent accuracy gain beyond off-the-shelf action recognition algorithms in terms of both ground truth and detected position of instances 
650 4 |a Journal Article 
700 1 |a Xie, Lingxi  |e verfasserin  |4 aut 
700 1 |a Shu, Xiangbo  |e verfasserin  |4 aut 
700 1 |a Zhang, Liyan  |e verfasserin  |4 aut 
700 1 |a Tang, Jinhui  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 45(2023), 8 vom: 17. Aug., Seite 10317-10330  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnas 
773 1 8 |g volume:45  |g year:2023  |g number:8  |g day:17  |g month:08  |g pages:10317-10330 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2023.3261659  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 45  |j 2023  |e 8  |b 17  |c 08  |h 10317-10330