Georgios Kapidis‘ work on multi-dataset multitask learning has been accepted to IEEE Transactions on Pattern Analysis and Machine Intelligence! Congratulations! We propose a method to improve egocentric action recognition using additional datasets with potentially different label sets, and different classification and regression tasks. We can thus learn by considering only weakly related data and tasks.
Alex Stergiou‘s paper “Learn to cycle: Time-consistent feature discovery for action recognition” now appears in Pattern Recognition Letters. We present a new method that can flexibly extract spatio-temporal patterns with varying temporal scales. We show state-of-the-art performance on benchmark datasets, including Kinetics-700, Moments in Time and HACS. The code is available!
Our lie detection research with Sophie van der Zee has been nominated for the Klokhuis science award. Klokhuis was that kids program that made you become curious about science. We are honored that our research on lying in families has been nominated for their 2020 science award. Everyone can vote for any of the 10 finalists. An episode about the topic of the winner will be made and aired. Cast your vote here! (We are “Kun jij beter liegen dan je ouders?”)
Thanks to Daan van Alkemade for the 8-second teaser video!
Group play appears to have a positive effect on the physical and mental development of children. However, it is unclear what the effective elements of a group play intervention are. With colleagues from the Wilhelmina Children’s Hospital in Utrecht, we set out to thoroughly evaluate their “This is Me” sports- and play-based cognitive behavior therapy program. Major challenge was to systematically measure those aspects that measure play and wellbeing. The preprint of our article in Clinical Child Psychology and Psychiatry is now online. We are looking forward to hear from other groups that focus on measuring the process of group-based play therapy.
I’ve been accepted to the editorial board of IEEE Transactions on Affective Computing (TAC). Looking forward to receiving all your manuscripts!
The number of car incidents is rising again, after years of steady decline. One explanation is car drivers’ use of phones. The Dutch police is now introducing automated ticketing for drivers holding a phone, based on camera footage. The pilot for this technique has been developed in 2018 by my MSc student Jannes Elings. The Dutch police has continued to develop the technique, which is now ready for deployment on the public roads.
Georgios Kapidis will present his recent work on Multi-Task Learning for the recognition of actions in ego-centric videos at the EPIC workshop of ICCV. By predicting multiple outputs such as gaze targets and hand locations, we can improve the network structure which benefits other tasks such as action recognition. We demonstrate state-of-the-art results on the EGTEA Gaze+ dataset, and show nice improvements over only action recognition on EPIC Kitchens.
Alex Stergiou had a good run: three papers were accepted recently at ICIP (paper), ICMLA (paper) and the ICCV workshop on Interpreting and Explaining Visual Artificial Intelligence Models (paper). The papers deal with the visualization of what 3D CNNs learn for video recognition. Congrats on the acceptance!
From 1,997 entries, our documentary “A week without lying: The honesty experiment” has been selected as one of the 17 films at the APA Film Festival. It will be screened on Friday August 9. Should you be at the annual APA conference, make sure to watch it! Congratulations to Vicky Cooper and the team from Thoroughly Modern Media!
The Washington Post featured an article about USA President Trump’s 10,000st false or misleading claim. In the article, our paper “A personal model of trumpery: Deception detection in a real-world high-stakes setting” (by Sophie van der Zee, me, Alice Havrileck and Aurelien Baillon) has been mentioned. It describes our research on deception detection from President Trump’s tweets. Our research has greatly benefited from the Washington Post’s fact-checking endeavors.