Deep High-Resolution Representation Learning for Visual Recognition
Citations
507 citations
Cites background or methods or result from "Deep High-Resolution Representation..."
...The overall training strategy is described in Section 4.4, which is the same as (Wang et al., 2020b)....
[...]
...Following the previous work (Wang et al., 2020b), the testing dataset contains 6 videos from 2DMOT15....
[...]
...We can see that our approach remarkably outperforms JDE (Wang et al., 2020b)....
[...]
...When we use the same training data as JDE (Wang et al., 2020b), we can achieve 72.9 MOTA, which remarkably outperforms JDE....
[...]
...The second strategy is POS-Anchor used in JDE (Wang et al., 2020b)....
[...]
459 citations
Cites background or methods from "Deep High-Resolution Representation..."
...HRNet [38, 40] consists of multiple branches with different resolutions....
[...]
...With multiscale fusions between branches, HRNet [38, 40] can generate high resolution feature maps with rich semantic....
[...]
...Topdown methods [34, 9, 16, 42, 38, 40, 39, 16] take a dependency on person detector to detect person instances each with a bounding box and then reduce the problem to a simHeatmap Aggregation CNN CNN...
[...]
...As both HRNet [38, 40, 40] and deconvolution are efficient, HigherHRNet is an efficient model for generating higher resolution feature maps for heatmap prediction....
[...]
...(4) Recently, a High-Resolution Network (HRNet) [38, 40] is proposed as an efficient way to keep a high resolution pass throughout the network....
[...]
418 citations
Cites background from "Deep High-Resolution Representation..."
...HRNet (Wang et al., 2019) adopts multi-branches to maintain the high resolution....
[...]
365 citations
282 citations
Additional excerpts
...8 Panoptic-DeepLab (HRNet-W48 [81]) [18] 3 71....
[...]
References
123,388 citations
111,197 citations
73,978 citations
49,914 citations
49,590 citations