Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering

Existing visual question answering methods often suffer from cross-modal spurious correlations and oversimplified event-level reasoning processes that fail to capture event temporality, causality, and dynamics spanning over the video. In this work, to address the task of event-level visual question...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 45(2023), 10 vom: 27. Okt., Seite 11624-11641
1. Verfasser: Liu, Yang (VerfasserIn)
Weitere Verfasser: Li, Guanbin, Lin, Liang
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2023
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article
LEADER 01000caa a22002652c 4500
001 NLM357914201
003 DE-627
005 20250304212053.0
007 cr uuu---uuuuu
008 231226s2023 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2023.3284038  |2 doi 
028 5 2 |a pubmed25n1192.xml 
035 |a (DE-627)NLM357914201 
035 |a (NLM)37289602 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Liu, Yang  |e verfasserin  |4 aut 
245 1 0 |a Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering 
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 06.09.2023 
500 |a published: Print-Electronic 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a Existing visual question answering methods often suffer from cross-modal spurious correlations and oversimplified event-level reasoning processes that fail to capture event temporality, causality, and dynamics spanning over the video. In this work, to address the task of event-level visual question answering, we propose a framework for cross-modal causal relational reasoning. In particular, a set of causal intervention operations is introduced to discover the underlying causal structures across visual and linguistic modalities. Our framework, named Cross-Modal Causal RelatIonal Reasoning (CMCIR), involves three modules: i) Causality-aware Visual-Linguistic Reasoning (CVLR) module for collaboratively disentangling the visual and linguistic spurious correlations via front-door and back-door causal interventions; ii) Spatial-Temporal Transformer (STT) module for capturing the fine-grained interactions between visual and linguistic semantics; iii) Visual-Linguistic Feature Fusion (VLFF) module for learning the global semantic-aware visual-linguistic representations adaptively. Extensive experiments on four event-level datasets demonstrate the superiority of our CMCIR in discovering visual-linguistic causal structures and achieving robust event-level visual question answering 
650 4 |a Journal Article 
700 1 |a Li, Guanbin  |e verfasserin  |4 aut 
700 1 |a Lin, Liang  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 45(2023), 10 vom: 27. Okt., Seite 11624-11641  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnas 
773 1 8 |g volume:45  |g year:2023  |g number:10  |g day:27  |g month:10  |g pages:11624-11641 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2023.3284038  |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 10  |b 27  |c 10  |h 11624-11641