Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Seidenschwarz, Jenny"'
We tackle semi-supervised object detection based on motion cues. Recent results suggest that heuristic-based clustering methods in conjunction with object trackers can be used to pseudo-label instances of moving objects and use these as supervisory s
Externí odkaz:
http://arxiv.org/abs/2402.19463
Autor:
Seidenschwarz, Jenny, Brasó, Guillem, Serrano, Victor Castro, Elezi, Ismail, Leal-Taixé, Laura
For a long time, the most common paradigm in Multi-Object Tracking was tracking-by-detection (TbD), where objects are first detected and then associated over video frames. For association, most models resourced to motion and appearance cues, e.g., re
Externí odkaz:
http://arxiv.org/abs/2206.04656
Autor:
Elezi, Ismail, Seidenschwarz, Jenny, Wagner, Laurin, Vascon, Sebastiano, Torcinovich, Alessandro, Pelillo, Marcello, Leal-Taixe, Laura
Deep metric learning has yielded impressive results in tasks such as clustering and image retrieval by leveraging neural networks to obtain highly discriminative feature embeddings, which can be used to group samples into different classes. Much rese
Externí odkaz:
http://arxiv.org/abs/2204.01509
The goal of metric learning is to learn a function that maps samples to a lower-dimensional space where similar samples lie closer than dissimilar ones. Particularly, deep metric learning utilizes neural networks to learn such a mapping. Most approac
Externí odkaz:
http://arxiv.org/abs/2102.07753
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Elezi, Ismail, Seidenschwarz, Jenny, Wagner, Laurin, Vascon, Sebastiano, Torcinovich, Alessandro, Pelillo, Marcello, Leal-Taixe, Laura
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence; February 2023, Vol. 45 Issue: 2 p2505-2518, 14p