Matches in SemOpenAlex for { <https://semopenalex.org/work/W2894881218> ?p ?o ?g. }
- W2894881218 endingPage "756" @default.
- W2894881218 startingPage "737" @default.
- W2894881218 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.
- W2894881218 created "2018-10-12" @default.
- W2894881218 creator A5007557621 @default.
- W2894881218 creator A5038328783 @default.
- W2894881218 creator A5048295582 @default.
- W2894881218 creator A5076846509 @default.
- W2894881218 date "2018-01-01" @default.
- W2894881218 modified "2023-10-13" @default.
- W2894881218 title "Reinforced Temporal Attention and Split-Rate Transfer for Depth-Based Person Re-identification" @default.
- W2894881218 cites W138224622 @default.
- W2894881218 cites W1518138188 @default.
- W2894881218 cites W1565402342 @default.
- W2894881218 cites W1572940804 @default.
- W2894881218 cites W1586939924 @default.
- W2894881218 cites W1594368566 @default.
- W2894881218 cites W166429404 @default.
- W2894881218 cites W1902237438 @default.
- W2894881218 cites W1920259731 @default.
- W2894881218 cites W1928419358 @default.
- W2894881218 cites W1949591461 @default.
- W2894881218 cites W1971955426 @default.
- W2894881218 cites W1979260620 @default.
- W2894881218 cites W1982925187 @default.
- W2894881218 cites W1984031350 @default.
- W2894881218 cites W1996889296 @default.
- W2894881218 cites W1998443077 @default.
- W2894881218 cites W1998808035 @default.
- W2894881218 cites W1999610780 @default.
- W2894881218 cites W2001881450 @default.
- W2894881218 cites W200708128 @default.
- W2894881218 cites W2009566328 @default.
- W2894881218 cites W2009907187 @default.
- W2894881218 cites W2014764728 @default.
- W2894881218 cites W2014850105 @default.
- W2894881218 cites W2022469758 @default.
- W2894881218 cites W2046835352 @default.
- W2894881218 cites W2048110836 @default.
- W2894881218 cites W2051960621 @default.
- W2894881218 cites W2060280062 @default.
- W2894881218 cites W2065398867 @default.
- W2894881218 cites W2068042582 @default.
- W2894881218 cites W2074852221 @default.
- W2894881218 cites W2079972027 @default.
- W2894881218 cites W2080836485 @default.
- W2894881218 cites W2088900896 @default.
- W2894881218 cites W2089074647 @default.
- W2894881218 cites W2097117768 @default.
- W2894881218 cites W2098807270 @default.
- W2894881218 cites W2113609219 @default.
- W2894881218 cites W2115669554 @default.
- W2894881218 cites W2117539524 @default.
- W2894881218 cites W2125889200 @default.
- W2894881218 cites W2130265848 @default.
- W2894881218 cites W2133378540 @default.
- W2894881218 cites W2135442311 @default.
- W2894881218 cites W2144545035 @default.
- W2894881218 cites W2151873133 @default.
- W2894881218 cites W2155893237 @default.
- W2894881218 cites W2157598322 @default.
- W2894881218 cites W2167292325 @default.
- W2894881218 cites W2204750386 @default.
- W2894881218 cites W2300840837 @default.
- W2894881218 cites W2342611082 @default.
- W2894881218 cites W2463071499 @default.
- W2894881218 cites W2465670578 @default.
- W2894881218 cites W2471048925 @default.
- W2894881218 cites W2472272718 @default.
- W2894881218 cites W2475284720 @default.
- W2894881218 cites W2497344197 @default.
- W2894881218 cites W2519373641 @default.
- W2894881218 cites W2519803806 @default.
- W2894881218 cites W2520433280 @default.
- W2894881218 cites W2520831962 @default.
- W2894881218 cites W2558681897 @default.
- W2894881218 cites W2575671312 @default.
- W2894881218 cites W2584637367 @default.
- W2894881218 cites W2585635281 @default.
- W2894881218 cites W2604211872 @default.
- W2894881218 cites W2604627275 @default.
- W2894881218 cites W2606377603 @default.
- W2894881218 cites W2622829582 @default.
- W2894881218 cites W2736410039 @default.
- W2894881218 cites W2738760914 @default.
- W2894881218 cites W2739491435 @default.
- W2894881218 cites W2740687571 @default.
- W2894881218 cites W2747359207 @default.
- W2894881218 cites W2752903123 @default.
- W2894881218 cites W2777534232 @default.
- W2894881218 cites W2778652957 @default.
- W2894881218 cites W2778775889 @default.
- W2894881218 cites W2779003141 @default.
- W2894881218 cites W2780159079 @default.
- W2894881218 cites W2951183276 @default.
- W2894881218 cites W2962883796 @default.
- W2894881218 cites W2963438548 @default.
- W2894881218 cites W2963574614 @default.
- W2894881218 cites W2963589138 @default.
- W2894881218 cites W2963690547 @default.