Recovering hard-to-find object instances by sampling context-based object proposals

Autor: M., Jose Oramas, Tuytelaars, Tinne

In this paper we focus on improving object detection performance in terms of recall. We propose a post-detection stage during which we explore the image with the objective of recovering missed detections. This exploration is performed by sampling obj

Externí odkaz: http://arxiv.org/abs/1511.01954

In defense of LSTMs for addressing multiple instance learning problems

Autor: Tinne Tuytelaars, M José Oramas, Kaili Wang

Publikováno v: Computer Vision : ACCV 2020 15th Asian Conference on Computer Vision, Kyoto, Japan, November 30 – December 4, 2020, Revised Selected Papers, Part VI
Computer Vision – ACCV 2020 ISBN: 9783030695439
ACCV (6)

LSTMs have a proven track record in analyzing sequential data. But what about unordered instance bags, as found under a Multiple Instance Learning (MIL) setting? While not often used for this, we show LSTMs excell under this setting too. In addition,

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bdf373920a937fd80618996627a51005

From Pixels to Actions: Learning to Drive a Car with Deep Neural Networks

Autor: Seppe Iven, M José Oramas, Jonas Heylen, Bert De Brabandere, Luc Van Gool, Tinne Tuytelaars

Publikováno v: WACV

© 2018 IEEE. The promise of self-driving cars promotes several advantages, e.g. they have the ability to outperform human drivers while being safer. Here we take a deeper look into some aspects from algorithms aimed at making this promise a reality.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7e2245d0941997a8c870829eb087e945
https://doi.org/10.1109/wacv.2018.00072

Context-based Object Viewpoint Estimation: A 2D Relational Approach

Autor: Luc De Raedt, M José Oramas, Tinne Tuytelaars

Publikováno v: Computer vision and image understanding

The task of object viewpoint estimation has been a challenge since the early days of computer vision. To estimate the viewpoint (or pose) of an object, people have mostly looked at object intrinsic features, such as shape or appearance. Surprisingly,

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1aa35f7438a69554645f99ef40e32a45
http://arxiv.org/abs/1704.06610

Modeling video evolution for action recognition

Autor: Efstratios Gavves, Tinne Tuytelaars, M José Oramas, Amir Ghodrati, Basura Fernando

Publikováno v: CVPR

© 2015 IEEE. In this paper we present a method to capture video-wide temporal information for action recognition. We postulate that a function capable of ordering the frames of a video temporally (based on the appearance) captures well the evolution

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0e6093cdc574c41d97a502545f772d4d
https://lirias.kuleuven.be/handle/123456789/511413