Unsupervised Object Discovery and Tracking in Video Collections - Archive ouverte HAL Access content directly
Conference Papers Year :

Unsupervised Object Discovery and Tracking in Video Collections


This paper addresses the problem of automatically localizing dominant objects as spatio-temporal tubes in a noisy collection of videos with minimal or even no supervision. We formulate the problem as a combination of two complementary processes: discovery and tracking. The first one establishes correspondences between prominent regions across videos, and the second one associates successive similar object regions within the same video. Interestingly , our algorithm also discovers the implicit topology of frames associated with instances of the same object class across different videos, a role normally left to supervisory information in the form of class labels in conventional image and video understanding methods. Indeed, as demonstrated by our experiments, our method can handle video collections featuring multiple object classes, and substantially outperforms the state of the art in colocalization, even though it tackles a broader problem with much less supervision.
Fichier principal
Vignette du fichier
video_obj_local.pdf (8.24 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01153017 , version 1 (19-05-2015)
hal-01153017 , version 2 (07-12-2015)



Suha Kwak, Minsu Cho, Ivan Laptev, Jean Ponce, Cordelia Schmid. Unsupervised Object Discovery and Tracking in Video Collections. ICCV - IEEE International Conference on Computer Vision, Dec 2015, Santiago, Chile. pp.3173-3181, ⟨10.1109/ICCV.2015.363⟩. ⟨hal-01153017v2⟩
791 View
471 Download



Gmail Facebook Twitter LinkedIn More