Matches in SemOpenAlex for { <https://semopenalex.org/work/W4382407365> ?p ?o ?g. }
- W4382407365 endingPage "4058" @default.
- W4382407365 startingPage "4046" @default.
- W4382407365 abstract "With the rapid development of face forgery techniques, the existing frame-based deepfake video detection methods have fell into a dilemma that frame-based methods may fail when encountering extremely realistic images. To overcome the above problem, many approaches attempted to model the spatio-temporal inconsistency of videos to distinguish real and fake videos. However, current works model spatio-temporal inconsistency by combining intra-frame and inter-frame information, but ignore the disturbance caused by facial motions that would limit further improvement in detection performance. To address this issue, we investigate into long and short range inter-frame motions and propose a novel dynamic difference learning method to distinguish between the inter-frame differences caused by face manipulation and the inter-frame differences caused by facial motions in order to model precise spatio-temporal inconsistency for deepfake video detection. Moreover, we elaborately design a dynamic fine-grained difference capture module (DFDC-module) and a multi-scale spatio-temporal aggregation module (MSA-module) to collaboratively model spatio-temporal inconsistency. Specifically, the DFDC-module applies self-attention mechanism and fine-grained denoising operation to eliminate the differences caused by facial motions and generates long range difference attention maps. The MSA-module is devised to aggregate multi-direction and multi-scale temporal information to model spatio-temporal inconsistency. The existing 2D CNNs can be extended into dynamic spatio-temporal inconsistency capture networks by integrating the proposed two modules. Extensive experimental results demonstrate that our proposed algorithm steadily outperforms state-of-the-art methods by a clear margin in different benchmark datasets." @default.
- W4382407365 created "2023-06-29" @default.
- W4382407365 creator A5043431408 @default.
- W4382407365 creator A5047964483 @default.
- W4382407365 creator A5070946001 @default.
- W4382407365 creator A5083054357 @default.
- W4382407365 date "2023-01-01" @default.
- W4382407365 modified "2023-10-16" @default.
- W4382407365 title "Dynamic Difference Learning With Spatio–Temporal Correlation for Deepfake Video Detection" @default.
- W4382407365 cites W2194775991 @default.
- W4382407365 cites W2531409750 @default.
- W4382407365 cites W2752782242 @default.
- W4382407365 cites W2891145043 @default.
- W4382407365 cites W2896689692 @default.
- W4382407365 cites W2911424785 @default.
- W4382407365 cites W2913399670 @default.
- W4382407365 cites W2914447220 @default.
- W4382407365 cites W2943520232 @default.
- W4382407365 cites W2962858109 @default.
- W4382407365 cites W2963091558 @default.
- W4382407365 cites W2963684180 @default.
- W4382407365 cites W2964080601 @default.
- W4382407365 cites W2979259381 @default.
- W4382407365 cites W2982058372 @default.
- W4382407365 cites W2995516027 @default.
- W4382407365 cites W3007646528 @default.
- W4382407365 cites W3034371424 @default.
- W4382407365 cites W3034713808 @default.
- W4382407365 cites W3035063907 @default.
- W4382407365 cites W3035494777 @default.
- W4382407365 cites W3036198682 @default.
- W4382407365 cites W3092997524 @default.
- W4382407365 cites W3094728142 @default.
- W4382407365 cites W3101998545 @default.
- W4382407365 cites W3102988878 @default.
- W4382407365 cites W3108854358 @default.
- W4382407365 cites W3116818516 @default.
- W4382407365 cites W3135133133 @default.
- W4382407365 cites W3135413014 @default.
- W4382407365 cites W3140970613 @default.
- W4382407365 cites W3158734383 @default.
- W4382407365 cites W3167034882 @default.
- W4382407365 cites W3174508664 @default.
- W4382407365 cites W3174572554 @default.
- W4382407365 cites W3174656926 @default.
- W4382407365 cites W3174814557 @default.
- W4382407365 cites W3176241004 @default.
- W4382407365 cites W3177027279 @default.
- W4382407365 cites W3188897163 @default.
- W4382407365 cites W3196204467 @default.
- W4382407365 cites W3207531490 @default.
- W4382407365 cites W4210623456 @default.
- W4382407365 cites W4214876496 @default.
- W4382407365 cites W4224314237 @default.
- W4382407365 cites W4226333682 @default.
- W4382407365 cites W4283802557 @default.
- W4382407365 cites W4312830050 @default.
- W4382407365 doi "https://doi.org/10.1109/tifs.2023.3290752" @default.
- W4382407365 hasPublicationYear "2023" @default.
- W4382407365 type Work @default.
- W4382407365 citedByCount "0" @default.
- W4382407365 crossrefType "journal-article" @default.
- W4382407365 hasAuthorship W4382407365A5043431408 @default.
- W4382407365 hasAuthorship W4382407365A5047964483 @default.
- W4382407365 hasAuthorship W4382407365A5070946001 @default.
- W4382407365 hasAuthorship W4382407365A5083054357 @default.
- W4382407365 hasConcept C119857082 @default.
- W4382407365 hasConcept C126042441 @default.
- W4382407365 hasConcept C134306372 @default.
- W4382407365 hasConcept C144024400 @default.
- W4382407365 hasConcept C151201525 @default.
- W4382407365 hasConcept C153180895 @default.
- W4382407365 hasConcept C154945302 @default.
- W4382407365 hasConcept C159985019 @default.
- W4382407365 hasConcept C172849965 @default.
- W4382407365 hasConcept C192562407 @default.
- W4382407365 hasConcept C196340769 @default.
- W4382407365 hasConcept C204323151 @default.
- W4382407365 hasConcept C2779304628 @default.
- W4382407365 hasConcept C31972630 @default.
- W4382407365 hasConcept C3261483 @default.
- W4382407365 hasConcept C33923547 @default.
- W4382407365 hasConcept C36289849 @default.
- W4382407365 hasConcept C39394851 @default.
- W4382407365 hasConcept C41008148 @default.
- W4382407365 hasConcept C4679612 @default.
- W4382407365 hasConcept C76155785 @default.
- W4382407365 hasConcept C774472 @default.
- W4382407365 hasConcept C97541855 @default.
- W4382407365 hasConceptScore W4382407365C119857082 @default.
- W4382407365 hasConceptScore W4382407365C126042441 @default.
- W4382407365 hasConceptScore W4382407365C134306372 @default.
- W4382407365 hasConceptScore W4382407365C144024400 @default.
- W4382407365 hasConceptScore W4382407365C151201525 @default.
- W4382407365 hasConceptScore W4382407365C153180895 @default.
- W4382407365 hasConceptScore W4382407365C154945302 @default.
- W4382407365 hasConceptScore W4382407365C159985019 @default.
- W4382407365 hasConceptScore W4382407365C172849965 @default.