Winner VOT-RGBT:

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.

3 papers at ICCV2019

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

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

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

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

Laura has obtained ‘distinctive mention’ in the Multimedia Satellite Task: Emergency Response for Flooding Events at MediaEval 2018.

TIP accepted on tracking FIR

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

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

Joost gave a talk at BCN.AI which can be viewed on youtube.