FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3010717207> ?p ?o ?g. }

• W3010717207 abstract "Face anti-spoofing is critical to the security of face recognition systems. Depth supervised learning has been proven as one of the most effective methods for face anti-spoofing. Despite the great success, most previous works still formulate the problem as a single-frame multi-task one by simply augmenting the loss with depth, while neglecting the detailed fine-grained information and the interplay between facial depths and moving patterns. In contrast, we design a new approach to detect presentation attacks from multiple frames based on two insights: 1) detailed discriminative clues (e.g., spatial gradient magnitude) between living and spoofing face may be discarded through stacked vanilla convolutions, and 2) the dynamics of 3D moving faces provide important clues in detecting the spoofing faces. The proposed method is able to capture discriminative details via Residual Spatial Gradient Block (RSGB) and encode spatio-temporal information from Spatio-Temporal Propagation Module (STPM) efficiently. Moreover, a novel Contrastive Depth Loss is presented for more accurate depth supervision. To assess the efficacy of our method, we also collect a Double-modal Anti-spoofing Dataset (DMAD) which provides actual depth for each sample. The experiments demonstrate that the proposed approach achieves state-of-the-art results on five benchmark datasets including OULU-NPU, SiW, CASIA-MFSD, Replay-Attack, and the new DMAD. Codes will be available at https://github.com/clks-wzz/FAS-SGTD." @default.
• W3010717207 created "2020-03-23" @default.
• W3010717207 creator A5009776777 @default.
• W3010717207 creator A5011611330 @default.
• W3010717207 creator A5016416183 @default.
• W3010717207 creator A5026407712 @default.
• W3010717207 creator A5033870633 @default.
• W3010717207 creator A5054137460 @default.
• W3010717207 creator A5062522283 @default.
• W3010717207 creator A5083763247 @default.
• W3010717207 date "2020-03-18" @default.
• W3010717207 modified "2023-09-23" @default.
• W3010717207 title "Deep Spatial Gradient and Temporal Depth Learning for Face Anti-spoofing" @default.
• W3010717207 cites W1487288055 @default.
• W3010717207 cites W1591599950 @default.
• W3010717207 cites W1704933117 @default.
• W3010717207 cites W1770095230 @default.
• W3010717207 cites W1889383825 @default.
• W3010717207 cites W1924770834 @default.
• W3010717207 cites W1982209341 @default.
• W3010717207 cites W2003092530 @default.
• W3010717207 cites W2017745767 @default.
• W3010717207 cites W2042883034 @default.
• W3010717207 cites W2063661788 @default.
• W3010717207 cites W2068723942 @default.
• W3010717207 cites W2095252718 @default.
• W3010717207 cites W2106852298 @default.
• W3010717207 cites W2107227001 @default.
• W3010717207 cites W2136666231 @default.
• W3010717207 cites W2145131129 @default.
• W3010717207 cites W2151343288 @default.
• W3010717207 cites W2174309130 @default.
• W3010717207 cites W2187089797 @default.
• W3010717207 cites W2194775991 @default.
• W3010717207 cites W2341318667 @default.
• W3010717207 cites W2409050142 @default.
• W3010717207 cites W2418633638 @default.
• W3010717207 cites W2522438482 @default.
• W3010717207 cites W2551249768 @default.
• W3010717207 cites W2578178601 @default.
• W3010717207 cites W2617869948 @default.
• W3010717207 cites W2724592263 @default.
• W3010717207 cites W2728977829 @default.
• W3010717207 cites W2776778982 @default.
• W3010717207 cites W2778720069 @default.
• W3010717207 cites W2787613668 @default.
• W3010717207 cites W2792256986 @default.
• W3010717207 cites W2802734296 @default.
• W3010717207 cites W2888286956 @default.
• W3010717207 cites W2927522063 @default.
• W3010717207 cites W2949978251 @default.
• W3010717207 cites W2963656031 @default.
• W3010717207 cites W2964094092 @default.
• W3010717207 cites W3005729266 @default.
• W3010717207 cites W3035240864 @default.
• W3010717207 doi "https://doi.org/10.48550/arxiv.2003.08061" @default.
• W3010717207 hasPublicationYear "2020" @default.
• W3010717207 type Work @default.
• W3010717207 sameAs 3010717207 @default.
• W3010717207 citedByCount "2" @default.
• W3010717207 countsByYear W30107172072020 @default.
• W3010717207 countsByYear W30107172072021 @default.
• W3010717207 crossrefType "posted-content" @default.
• W3010717207 hasAuthorship W3010717207A5009776777 @default.
• W3010717207 hasAuthorship W3010717207A5011611330 @default.
• W3010717207 hasAuthorship W3010717207A5016416183 @default.
• W3010717207 hasAuthorship W3010717207A5026407712 @default.
• W3010717207 hasAuthorship W3010717207A5033870633 @default.
• W3010717207 hasAuthorship W3010717207A5054137460 @default.
• W3010717207 hasAuthorship W3010717207A5062522283 @default.
• W3010717207 hasAuthorship W3010717207A5083763247 @default.
• W3010717207 hasBestOaLocation W30107172071 @default.
• W3010717207 hasConcept C108583219 @default.
• W3010717207 hasConcept C125411270 @default.
• W3010717207 hasConcept C126042441 @default.
• W3010717207 hasConcept C13280743 @default.
• W3010717207 hasConcept C144024400 @default.
• W3010717207 hasConcept C153180895 @default.
• W3010717207 hasConcept C154945302 @default.
• W3010717207 hasConcept C167900197 @default.
• W3010717207 hasConcept C185798385 @default.
• W3010717207 hasConcept C205649164 @default.
• W3010717207 hasConcept C2779304628 @default.
• W3010717207 hasConcept C28490314 @default.
• W3010717207 hasConcept C31258907 @default.
• W3010717207 hasConcept C31510193 @default.
• W3010717207 hasConcept C31972630 @default.
• W3010717207 hasConcept C36289849 @default.
• W3010717207 hasConcept C41008148 @default.
• W3010717207 hasConcept C76155785 @default.
• W3010717207 hasConcept C97931131 @default.
• W3010717207 hasConceptScore W3010717207C108583219 @default.
• W3010717207 hasConceptScore W3010717207C125411270 @default.
• W3010717207 hasConceptScore W3010717207C126042441 @default.
• W3010717207 hasConceptScore W3010717207C13280743 @default.
• W3010717207 hasConceptScore W3010717207C144024400 @default.
• W3010717207 hasConceptScore W3010717207C153180895 @default.
• W3010717207 hasConceptScore W3010717207C154945302 @default.
• W3010717207 hasConceptScore W3010717207C167900197 @default.
• W3010717207 hasConceptScore W3010717207C185798385 @default.

• next