Zobrazeno 1 - 10
of 157
pro vyhledávání: '"P. Bertinetto"'
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2022
In this paper we introduce SiamMask, a framework to perform both visual object tracking and video object segmentation, in real-time, with the same simple method. We improve the offline training procedure of popular fully-convolutional Siamese approac
Externí odkaz:
http://arxiv.org/abs/2207.02088
A recent line of work on black-box adversarial attacks has revived the use of transfer from surrogate models by integrating it into query-based search. However, we find that existing approaches of this type underperform their potential, and can be ov
Externí odkaz:
http://arxiv.org/abs/2203.08725
Training state-of-the-art vision models has become prohibitively expensive for researchers and practitioners. For the sake of accessibility and resource reuse, it is important to focus on adapting these models to a variety of downstream scenarios. An
Externí odkaz:
http://arxiv.org/abs/2201.05718
Autor:
Wang, Zhongdao, Zhao, Hengshuang, Li, Ya-Li, Wang, Shengjin, Torr, Philip H. S., Bertinetto, Luca
Tracking objects of interest in a video is one of the most popular and widely applicable problems in computer vision. However, with the years, a Cambrian explosion of use cases and benchmarks has fragmented the problem in a multitude of different exp
Externí odkaz:
http://arxiv.org/abs/2107.02156
Autor:
Laenen, Steinar, Bertinetto, Luca
Episodic learning is a popular practice among researchers and practitioners interested in few-shot learning. It consists of organising training in a series of learning problems (or episodes), each divided into a small training and validation subset t
Externí odkaz:
http://arxiv.org/abs/2012.09831
Autor:
Bertinetto, Luca, Mueller, Romain, Tertikas, Konstantinos, Samangooei, Sina, Lord, Nicholas A.
Deep neural networks have improved image classification dramatically over the past decade, but have done so by focusing on performance measures that treat all classes other than the ground truth as equally wrong. This has led to a situation in which
Externí odkaz:
http://arxiv.org/abs/1912.09393
Unsupervised video object segmentation has often been tackled by methods based on recurrent neural networks and optical flow. Despite their complexity, these kinds of approaches tend to favour short-term temporal dependencies and are thus prone to ac
Externí odkaz:
http://arxiv.org/abs/1910.10895
Many applications require a camera to be relocalised online, without expensive offline training on the target scene. Whilst both keyframe and sparse keypoint matching methods can be used online, the former often fail away from the training trajectory
Externí odkaz:
http://arxiv.org/abs/1906.08744
In this paper we illustrate how to perform both visual object tracking and semi-supervised video object segmentation, in real-time, with a single simple approach. Our method, dubbed SiamMask, improves the offline training procedure of popular fully-c
Externí odkaz:
http://arxiv.org/abs/1812.05050
Adapting deep networks to new concepts from a few examples is challenging, due to the high computational requirements of standard fine-tuning procedures. Most work on few-shot learning has thus focused on simple learning techniques for adaptation, su
Externí odkaz:
http://arxiv.org/abs/1805.08136