FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2949968360> ?p ?o ?g. }

• W2949968360 abstract "We address the problem of person re-identification from commodity depth sensors. One challenge for depth-based recognition is data scarcity. Our first contribution addresses this problem by introducing split-rate RGB-to-Depth transfer, which leverages large RGB datasets more effectively than popular fine-tuning approaches. Our transfer scheme is based on the observation that the model parameters at the bottom layers of a deep convolutional neural network can be directly shared between RGB and depth data while the remaining layers need to be fine-tuned rapidly. Our second contribution enhances re-identification for video by implementing temporal attention as a Bernoulli-Sigmoid unit acting upon frame-level features. Since this unit is stochastic, the temporal attention parameters are trained using reinforcement learning. Extensive experiments validate the accuracy of our method in person re-identification from depth sequences. Finally, in a scenario where subjects wear unseen clothes, we show large performance gains compared to a state-of-the-art model which relies on RGB data." @default.
• W2949968360 created "2019-06-27" @default.
• W2949968360 creator A5007557621 @default.
• W2949968360 creator A5038328783 @default.
• W2949968360 creator A5048295582 @default.
• W2949968360 creator A5076846509 @default.
• W2949968360 date "2017-05-28" @default.
• W2949968360 modified "2023-09-23" @default.
• W2949968360 title "Reinforced Temporal Attention and Split-Rate Transfer for Depth-Based Person Re-Identification" @default.
• W2949968360 cites W1518138188 @default.
• W2949968360 cites W1565402342 @default.
• W2949968360 cites W1581407678 @default.
• W2949968360 cites W1836465849 @default.
• W2949968360 cites W1902237438 @default.
• W2949968360 cites W1904365287 @default.
• W2949968360 cites W1920259731 @default.
• W2949968360 cites W1928419358 @default.
• W2949968360 cites W1947481528 @default.
• W2949968360 cites W1971955426 @default.
• W2949968360 cites W1998808035 @default.
• W2949968360 cites W2001881450 @default.
• W2949968360 cites W2022469758 @default.
• W2949968360 cites W2048110836 @default.
• W2949968360 cites W2051960621 @default.
• W2949968360 cites W2060280062 @default.
• W2949968360 cites W2065398867 @default.
• W2949968360 cites W2068042582 @default.
• W2949968360 cites W2074852221 @default.
• W2949968360 cites W2080836485 @default.
• W2949968360 cites W2088900896 @default.
• W2949968360 cites W2097117768 @default.
• W2949968360 cites W2117539524 @default.
• W2949968360 cites W2119717200 @default.
• W2949968360 cites W2133378540 @default.
• W2949968360 cites W2144545035 @default.
• W2949968360 cites W2149933564 @default.
• W2949968360 cites W2154171558 @default.
• W2949968360 cites W2155893237 @default.
• W2949968360 cites W2157598322 @default.
• W2949968360 cites W2162931300 @default.
• W2949968360 cites W2300840837 @default.
• W2949968360 cites W2318812529 @default.
• W2949968360 cites W2342611082 @default.
• W2949968360 cites W2463071499 @default.
• W2949968360 cites W2471048925 @default.
• W2949968360 cites W2472272718 @default.
• W2949968360 cites W2475284720 @default.
• W2949968360 cites W2558681897 @default.
• W2949968360 cites W2575671312 @default.
• W2949968360 cites W2622829582 @default.
• W2949968360 cites W2739491435 @default.
• W2949968360 cites W2740687571 @default.
• W2949968360 cites W2777534232 @default.
• W2949968360 cites W2778652957 @default.
• W2949968360 cites W2779003141 @default.
• W2949968360 cites W2950307714 @default.
• W2949968360 cites W2951527505 @default.
• W2949968360 cites W2962835968 @default.
• W2949968360 cites W2962883796 @default.
• W2949968360 cites W2963277399 @default.
• W2949968360 cites W2963438548 @default.
• W2949968360 cites W2963721283 @default.
• W2949968360 cites W2963960612 @default.
• W2949968360 cites W2964163358 @default.
• W2949968360 cites W2964304299 @default.
• W2949968360 cites W753012316 @default.
• W2949968360 hasPublicationYear "2017" @default.
• W2949968360 type Work @default.
• W2949968360 sameAs 2949968360 @default.
• W2949968360 citedByCount "0" @default.
• W2949968360 crossrefType "posted-content" @default.
• W2949968360 hasAuthorship W2949968360A5007557621 @default.
• W2949968360 hasAuthorship W2949968360A5038328783 @default.
• W2949968360 hasAuthorship W2949968360A5048295582 @default.
• W2949968360 hasAuthorship W2949968360A5076846509 @default.
• W2949968360 hasConcept C116834253 @default.
• W2949968360 hasConcept C119857082 @default.
• W2949968360 hasConcept C126042441 @default.
• W2949968360 hasConcept C127413603 @default.
• W2949968360 hasConcept C146978453 @default.
• W2949968360 hasConcept C150899416 @default.
• W2949968360 hasConcept C152361515 @default.
• W2949968360 hasConcept C153180895 @default.
• W2949968360 hasConcept C154945302 @default.
• W2949968360 hasConcept C31972630 @default.
• W2949968360 hasConcept C41008148 @default.
• W2949968360 hasConcept C59822182 @default.
• W2949968360 hasConcept C76155785 @default.
• W2949968360 hasConcept C81363708 @default.
• W2949968360 hasConcept C82990744 @default.
• W2949968360 hasConcept C86803240 @default.
• W2949968360 hasConceptScore W2949968360C116834253 @default.
• W2949968360 hasConceptScore W2949968360C119857082 @default.
• W2949968360 hasConceptScore W2949968360C126042441 @default.
• W2949968360 hasConceptScore W2949968360C127413603 @default.
• W2949968360 hasConceptScore W2949968360C146978453 @default.
• W2949968360 hasConceptScore W2949968360C150899416 @default.
• W2949968360 hasConceptScore W2949968360C152361515 @default.
• W2949968360 hasConceptScore W2949968360C153180895 @default.
• W2949968360 hasConceptScore W2949968360C154945302 @default.

• next