Learning to Track Any Object - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Learning to Track Any Object

Résumé

Object tracking can be formulated as "finding the right object in a video". We observe that recent approaches for class-agnostic tracking tend to focus on the "finding" part, but largely overlook the "object" part of the task, essentially doing a template matching over a frame in a sliding-window. In contrast, class-specific trackers heavily rely on object priors in the form of category-specific object detectors. In this work, we re-purpose category-specific appearance models into a generic objectness prior. Our approach converts a category-specific object detector into a category-agnostic, object-specific detector (i.e. a tracker) efficiently, on the fly. Moreover, at test time the same network can be applied to detection and tracking, resulting in a unified approach for the two tasks. We achieve state-of-the-art results on two recent large-scale tracking benchmarks (OxUvA and GOT, using external data). By simply adding a mask prediction branch, our approach is able to produce instance segmentation masks for the tracked object. Despite only using box-level information on the first frame, our method outputs high-quality masks, as evaluated on the DAVIS '17 video object segmentation benchmark.
Fichier principal
Vignette du fichier
1910.11844.pdf (4.04 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03990657 , version 1 (15-02-2023)

Identifiants

Citer

Achal Dave, Pavel Tokmakov, Cordelia Schmid, Deva Ramanan. Learning to Track Any Object. ICCV workshop - Holistic Video Understanding, Oct 2019, Seoul, South Korea. ⟨hal-03990657⟩
31 Consultations
31 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More