FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2969181873> ?p ?o ?g. }

• W2969181873 abstract "This paper provides a comprehensive and exhaustive study of adversarial attacks on human pose estimation models and the evaluation of their robustness. Besides highlighting the important differences between well-studied classification and human pose-estimation systems w.r.t. adversarial attacks, we also provide deep insights into the design choices of pose-estimation systems to shape future work. We benchmark the robustness of several 2D single person pose-estimation architectures trained on multiple datasets, MPII and COCO. In doing so, we also explore the problem of attacking non-classification networks including regression based networks, which has been virtually unexplored in the past. par We find that compared to classification and semantic segmentation, human pose estimation architectures are relatively robust to adversarial attacks with the single-step attacks being surprisingly ineffective. Our study shows that the heatmap-based pose-estimation models are notably robust than their direct regression-based systems and that the systems which explicitly model anthropomorphic semantics of human body fare better than their other counterparts. Besides, targeted attacks are more difficult to obtain than un-targeted ones and some body-joints are easier to fool than the others. We present visualizations of universal perturbations to facilitate unprecedented insights into their workings on pose-estimation. Additionally, we show them to generalize well across different networks. Finally we perform a user study about perceptibility of these examples." @default.
• W2969181873 created "2019-08-22" @default.
• W2969181873 creator A5019742155 @default.
• W2969181873 creator A5035471468 @default.
• W2969181873 creator A5055516208 @default.
• W2969181873 creator A5076249543 @default.
• W2969181873 date "2019-08-18" @default.
• W2969181873 modified "2023-09-23" @default.
• W2969181873 title "On the Robustness of Human Pose Estimation" @default.
• W2969181873 cites W1537698211 @default.
• W2969181873 cites W1673923490 @default.
• W2969181873 cites W1816678934 @default.
• W2969181873 cites W1861492603 @default.
• W2969181873 cites W1932198206 @default.
• W2969181873 cites W1945616565 @default.
• W2969181873 cites W2080873731 @default.
• W2969181873 cites W2101032778 @default.
• W2969181873 cites W2112507308 @default.
• W2969181873 cites W2113325037 @default.
• W2969181873 cites W2117539524 @default.
• W2969181873 cites W2136391815 @default.
• W2969181873 cites W2163605009 @default.
• W2969181873 cites W2180612164 @default.
• W2969181873 cites W2243397390 @default.
• W2969181873 cites W2307770531 @default.
• W2969181873 cites W2375583958 @default.
• W2969181873 cites W2408141691 @default.
• W2969181873 cites W2543927648 @default.
• W2969181873 cites W2559085405 @default.
• W2969181873 cites W2604375920 @default.
• W2969181873 cites W2604505099 @default.
• W2969181873 cites W2613718673 @default.
• W2969181873 cites W2727966874 @default.
• W2969181873 cites W2734506812 @default.
• W2969181873 cites W2770312844 @default.
• W2969181873 cites W2774644650 @default.
• W2969181873 cites W2781800156 @default.
• W2969181873 cites W2797328537 @default.
• W2969181873 cites W2799244840 @default.
• W2969181873 cites W2809890486 @default.
• W2969181873 cites W2884519271 @default.
• W2969181873 cites W2887603965 @default.
• W2969181873 cites W2889332130 @default.
• W2969181873 cites W2895595267 @default.
• W2969181873 cites W2912237282 @default.
• W2969181873 cites W2916798096 @default.
• W2969181873 cites W2945071622 @default.
• W2969181873 cites W2950864148 @default.
• W2969181873 cites W2950977907 @default.
• W2969181873 cites W2952270885 @default.
• W2969181873 cites W2952819818 @default.
• W2969181873 cites W2955127209 @default.
• W2969181873 cites W2962896489 @default.
• W2969181873 cites W2962933288 @default.
• W2969181873 cites W2963118571 @default.
• W2969181873 cites W2963389226 @default.
• W2969181873 cites W2963448658 @default.
• W2969181873 cites W2963491874 @default.
• W2969181873 cites W2963542245 @default.
• W2969181873 cites W2963784236 @default.
• W2969181873 cites W2963855547 @default.
• W2969181873 cites W2963857521 @default.
• W2969181873 cites W2964097310 @default.
• W2969181873 cites W2964105113 @default.
• W2969181873 cites W2964175514 @default.
• W2969181873 cites W2964221239 @default.
• W2969181873 cites W2970285700 @default.
• W2969181873 cites W2982517618 @default.
• W2969181873 cites W2983371255 @default.
• W2969181873 cites W3010812598 @default.
• W2969181873 cites W3035129432 @default.
• W2969181873 cites W3098473649 @default.
• W2969181873 cites W3098612954 @default.
• W2969181873 hasPublicationYear "2019" @default.
• W2969181873 type Work @default.
• W2969181873 sameAs 2969181873 @default.
• W2969181873 citedByCount "4" @default.
• W2969181873 countsByYear W29691818732019 @default.
• W2969181873 countsByYear W29691818732020 @default.
• W2969181873 countsByYear W29691818732021 @default.
• W2969181873 crossrefType "posted-content" @default.
• W2969181873 hasAuthorship W2969181873A5019742155 @default.
• W2969181873 hasAuthorship W2969181873A5035471468 @default.
• W2969181873 hasAuthorship W2969181873A5055516208 @default.
• W2969181873 hasAuthorship W2969181873A5076249543 @default.
• W2969181873 hasConcept C104317684 @default.
• W2969181873 hasConcept C105795698 @default.
• W2969181873 hasConcept C119857082 @default.
• W2969181873 hasConcept C127413603 @default.
• W2969181873 hasConcept C13280743 @default.
• W2969181873 hasConcept C154945302 @default.
• W2969181873 hasConcept C185592680 @default.
• W2969181873 hasConcept C185798385 @default.
• W2969181873 hasConcept C201995342 @default.
• W2969181873 hasConcept C205649164 @default.
• W2969181873 hasConcept C33923547 @default.
• W2969181873 hasConcept C37736160 @default.
• W2969181873 hasConcept C41008148 @default.
• W2969181873 hasConcept C52102323 @default.
• W2969181873 hasConcept C55493867 @default.

• next