Predicate |
Object |
assignee |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_cc4e13141d402ceb885f368dfa042348 http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_4c9e18516c8c175a92fbd5a45cd26ed1 |
classificationCPCAdditional |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-10016 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20084 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20081 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-30201 |
classificationCPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-084 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-253 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-24 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-0002 |
classificationIPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08 |
filingDate |
2020-12-24-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_2bb9f469d8179aea89c0a2dfb8092b61 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_4f5696a1a0cab58fbcc17232286b7e74 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_96630a5cebe541d72bd5590c1cd8faae http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_b7039af0b1f01d985b52d09c04b602e5 |
publicationDate |
2021-04-30-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber |
CN-112734696-A |
titleOfInvention |
Face-changing video tampering detection method and system based on multi-domain feature fusion |
abstract |
The invention discloses a face-changing video tampering detection method and system based on multi-domain feature fusion. The method comprises the following steps: dividing a data set; dividing the video into frames and selecting a frame sequence to be tested, and extracting the to-be-detected area of each frame image; Calculate the RGB features, DFT features and optical flow feature images of the detection area; construct a convolution feature extraction module of a multi-channel convolutional neural network; input the convolution features of each branch into the attention module to generate an attention-guided feature map; multi-channel attention Guide the feature cascade fusion, input the fully connected layer for feature classification; input the feature image into the multi-channel convolutional neural network for training, save the network model and the best weight; use the trained model for prediction and classification, and output face replacement Video tampering detection results. The invention can better combine the tampering information of the video in the space domain, the frequency domain and the time domain, improve the generalization ability of the model, and use the channel attention mechanism to optimize the learning of the classification features of multiple domains by the model. |
isCitedBy |
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113239857-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113837980-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113537027-B http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113609952-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-115273186-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113609952-B http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114598833-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113537027-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-116563957-B http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-116563957-A |
priorityDate |
2020-12-24-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type |
http://data.epo.org/linked-data/def/patent/Publication |