HOTS: A Hierarchy of Event-Based Time-Surfaces for Pattern Recognition
Citations
756 citations
697 citations
Cites methods from "HOTS: A Hierarchy of Event-Based Ti..."
...romorphic versions of popular traditional computer vision datasets, such as MNIST and Caltech101, have been obtained by using saccade-like motions [219], [252]. These datasets have been used in [16], [17], [18], [106], [124], [125], among others, to benchmark event-based recognition algorithms. The DVS emulator in [83] and the simulator in [205] are based on the operation principle of an ideal DVS pix...
[...]
511 citations
Cites background from "HOTS: A Hierarchy of Event-Based Ti..."
...Time surface features (Lagorce et al., 2017) capture the local spatio-temporal dynamics around events by computing a continuous-valued feature for small spatial and temporal windows around each event, which describes the spiking activity of nearby events....
[...]
479 citations
Cites background from "HOTS: A Hierarchy of Event-Based Ti..."
...Furthermore, there are growing efforts towards the direct use of asynchronous event-based data produced by spiking sensors such as the DVS [37]–[42]....
[...]
344 citations
References
46,906 citations
42,067 citations
5,947 citations
"HOTS: A Hierarchy of Event-Based Ti..." refers methods in this paper
...overcome using basis function decomposition similarly to what has been introduced in [34]....
[...]
3,475 citations
2,183 citations
"HOTS: A Hierarchy of Event-Based Ti..." refers methods in this paper
...We will also use the Bhattacharyya distance [32] defined as...
[...]