Towards the understanding of object manipulations by means of combining common sense rules and deep networks

Csákvári Máté; Sárkány András: Towards the understanding of object manipulations by means of combining common sense rules and deep networks.

Előnézet

Cikk, tanulmány, mű cscs_2018_131-134.pdf Letöltés (928kB) | Előnézet

Absztrakt (kivonat)

Object detection on images and videos improved remarkably recently. However, state-of-theart methods still have considerable shortcomings: they require training data for each object class, are prone to occlusions and may have high false positive or false negative rates being prohibitive in diverse applications. We study a case that a) has a limited goal and works in a narrow context, b) includes common sense rules on ‘objectness’ and c) exploits state-of-the art deep detectors of different kinds. Our proposed method works on an image sequence from a stationary camera and detects objects that may be manipulated by actors in a scenario. The object types are not known to the system and we consider two actions: “taking an object from a table" and “putting an object onto the table". We quantitatively evaluate our method on manually annotated video segments and present precision and recall scores.

Mű típusa:	Konferencia vagy workshop anyag
Befoglaló folyóirat/kiadvány címe:	Conference of PhD Students in Computer Science
Dátum:	2018
Kötet:	11
Oldalak:	pp. 118-121
Konferencia neve:	Conference of PhD students in computer science (11.) (2018) (Szeged)
Befoglaló mű URL:	http://acta.bibl.u-szeged.hu/59477/
Kulcsszavak:	Számítástechnika
Megjegyzések:	Bibliogr.: 121. p. ; összefoglalás angol nyelven
Feltöltés dátuma:	2019. nov. 04. 12:57
Utolsó módosítás:	2022. nov. 08. 10:18
URI:	http://acta.bibl.u-szeged.hu/id/eprint/61781

Bővebben:

Tétel nézet