Lichao Zhang won the VOT-RGBT challenge this year. His work is published in the VOT 2019 workshop:
Multi-Modal Fusion for End-to-End RGB-T Tracking.
Winner VOT-RGBT:
Posted by Joost Van de Weijer
on 25/11/2019
3 papers at ICCV2019
Posted by Joost Van de Weijer
on 01/10/2019
Lichao’s paper on visual tracking Learning the Model Update for Siamese Trackers and Hamed’s paper on active learning Active Learning for Deep Detection Neural Networks (github) have been accepted for ICCV. Also, David Berga has a paper with Xavier Otazu on saliency detection: SID4VAM: A Benchmark Dataset With Synthetic Images for Visual Attention Modeling .
PR on fine-grained object detection
Posted by Joost Van de Weijer
on 06/05/2019
The journal of Carola on ‘Saliency for Fine-grained Object Recognition in Domains with Scarce Training Data’ (pdf) has been accepted for publication in Pattern Recognition.
BLOG posts:
MeRGANs: generating images without forgetting (NIPS 2018 + video)
Mix and match networks (CVPR 2018)
Rotating networks to prevent catastrophic forgetting (ICPR 2018)
Deep network compression and adaptation (ICCV2017)
Learning RGB-D features for images and videos (AAAI 2017, TIP 2018)
CVPR 2019
Posted by Joost Van de Weijer
on 09/04/2019
Our paper on
Learning Metrics from Teachers: Compact Networks for Image Embedding has been accepted for presentation at CVPR 2019.
PAMI on learning from rankings
Posted by Joost Van de Weijer
on 19/02/2019
Xialei’s PAMI ‘Exploiting Unlabeled Data in CNNs by Self-supervised Learning to Rank’ (pdf) has been accepted for publication at PAMI.
MediaEval Challenge 2018
Posted by Joost Van de Weijer
on 09/11/2018
Laura has obtained ‘distinctive mention’ in the Multimedia Satellite Task: Emergency Response for Flooding Events at MediaEval 2018.
TIP accepted on tracking FIR
Posted by Joost Van de Weijer
on 06/11/2018
The paper ‘Synthetic data generation for end-to-end thermal infrared tracking’ of Lichao Zhang has been accepted for publication at IEEE TIP.
Thesis Aymen Azaza
Posted by Joost Van de Weijer
on 02/11/2018
Aymen Azaza has been awarded his PhD both at the UAB and the University of Monastir (Tunisie) for his thesis on ‘Context, Motion, and Semantic Information for Computational Saliency’.
talk at BCN.AI
Posted by Joost Van de Weijer
on 24/09/2018
