An adaptive motion model for person tracking with instantaneous head-pose features

This letter presents novel behaviour-based tracking of people in low-resolution using instantaneous priors mediated by head-pose. We extend the Kalman Filter to adaptively combine motion information with an instantaneous prior belief about where the person will go based on where they are currently looking. We apply this new method to pedestrian surveillance, using automatically-derived head pose estimates, although the theory is not limited to head-pose priors. We perform a statistical analysis of pedestrian gazing behaviour and demonstrate tracking performance on a set of simulated and real pedestrian observations. We show that by using instantaneous `intentional' priors our algorithm significantly outperforms a standard Kalman Filter on comprehensive test data.

Person Re-Identification using Deep Convnets with Multi-task Learning

Person re-identification involves recognizing a person across non-overlapping camera views, with different pose, illumination, and camera characteristics. We propose to tackle this problem by training a deep convolutional network to represent a person’s appearance as a low-dimensional feature vector that is invariant to common appearance variations encountered in the re-identification problem. Specifically, a Siamese-network architecture is used to train a feature extraction network using pairs of similar and dissimilar images. We show that use of a novel multi-task learning objective is crucial for regularizing the network parameters in order to prevent over-fitting due to the small size the training dataset. We complement the verification task, which is at the heart of re-identification, by training the network to jointly perform verification, identification, and to recognise attributes related to the clothing and pose of the person in each image. Additionally, we show that our proposed approach performs well even in the challenging cross-dataset scenario, which may better reflect real-world expected performance. 

Antiplatelet therapy versus observation in low-risk essential thrombocythemia with CALR mutation

The role of antiplatelet therapy as primary prophylaxis of thrombosis in low-risk essential thrombocythemia has not been studied in randomized clinical trials. We assessed the benefit/risk of low-dose aspirin in 433 low-risk essential thrombocythemia patients (CALR-mutated n=271, JAK2V617F-mutated n=162) who were on antiplatelet therapy or observation only. After a 2215 person-years follow-up free from cytoreduction, 25 thrombotic and 17 bleeding episodes were recorded. In CALR-mutated patients, antiplatelet therapy did not affect the risk of thrombosis but was associated with a higher incidence of bleeding (12.9 vs. 1.8 x1000 patient-years, p=0.03). In JAK2V617F-mutated patients, low-dose aspirin was associated with a reduced incidence of venous thrombosis with no effect on the risk of bleeding. Coexistence of JAK2V617F-mutation and cardiovascular risk factors increased the risk of thrombosis, even after adjusting for treatment with low-dose aspirin (incidence rate ratio: 9.8; 95% confidence interval: 2.3-42.3; p=0.02). Time free from cytoreduction was significantly shorter in CALR-mutated than in JAK2V617F-mutated essential thrombocythemia (median time 5 years and 9.8 years, respectively; p=0.0002) usually to control extreme thrombocytosis. In conclusion, in patients with low-risk, CALR-mutated essential thrombocythemia, low-dose aspirin does not reduce the risk of thrombosis and may increase the risk of bleeding.