Search

Visual odometry shows excellent performance in a wide range of environments. However, in visually-denied scenarios (e.g. heavy smoke or darkness), pose estimates degrade or even fail. Thermal cameras are commonly used for perception and inspection when the environment has low visibility. However, their use in odometry estimation is hampered by the lack of robust visual features. In part, this is as a result of the sensor measuring the ambient temperature profile rather than scene appearance and geometry. To overcome this issue, we propose a Deep Neural Network model for thermal-inertial odometry (DeepTIO) by incorporating a visual hallucination network to provide the thermal network with complementary information. The hallucination network is taught to predict fake visual features from thermal images by using Huber loss. We also employ selective fusion to attentively fuse the features from three different modalities, i.e thermal, hallucination, and inertial features. Extensive experiments are performed in hand-held and mobile robot data in benign and smoke-filled environments, showing the efficacy of the proposed model., Comment: Accepted to IEEE Robotics and Automation Letters (RAL)

Deep learning has achieved impressive results in camera localization, but current single-image techniques typically suffer from a lack of robustness, leading to large outliers. To some extent, this has been tackled by sequential (multi-images) or geometry constraint approaches, which can learn to reject dynamic objects and illumination conditions to achieve better performance. In this work, we show that attention can be used to force the network to focus on more geometrically robust objects and features, achieving state-of-the-art performance in common benchmark, even if using only a single image as input. Extensive experimental evidence is provided through public indoor and outdoor datasets. Through visualization of the saliency maps, we demonstrate how the network learns to reject dynamic objects, yielding superior global camera pose regression performance. The source code is avaliable at https://github.com/BingCS/AtLoc.

Facial recognition is a key enabling component for emerging Internet of Things (IoT) services such as smart homes or responsive offices. Through the use of deep neural networks, facial recognition has achieved excellent performance. However, this is only possibly when trained with hundreds of images of each user in different viewing and lighting conditions. Clearly, this level of effort in enrolment and labelling is impossible for wide-spread deployment and adoption. Inspired by the fact that most people carry smart wireless devices with them, e.g. smartphones, we propose to use this wireless identifier as a supervisory label. This allows us to curate a dataset of facial images that are unique to a certain domain e.g. a set of people in a particular office. This custom corpus can then be used to finetune existing pre-trained models e.g. FaceNet. However, due to the vagaries of wireless propagation in buildings, the supervisory labels are noisy and weak.We propose a novel technique, AutoTune, which learns and refines the association between a face and wireless identifier over time, by increasing the inter-cluster separation and minimizing the intra-cluster distance. Through extensive experiments with multiple users on two sites, we demonstrate the ability of AutoTune to design an environment-specific, continually evolving facial recognition system with entirely no user effort., Comment: 11 pages, accepted in the Web Conference (WWW'2019)

Dynamical models estimate and predict the temporal evolution of physical systems. State Space Models (SSMs) in particular represent the system dynamics with many desirable properties, such as being able to model uncertainty in both the model and measurements, and optimal (in the Bayesian sense) recursive formulations e.g. the Kalman Filter. However, they require significant domain knowledge to derive the parametric form and considerable hand-tuning to correctly set all the parameters. Data driven techniques e.g. Recurrent Neural Networks have emerged as compelling alternatives to SSMs with wide success across a number of challenging tasks, in part due to their ability to extract relevant features from rich inputs. They however lack interpretability and robustness to unseen conditions. In this work, we present DynaNet, a hybrid deep learning and time-varying state-space model which can be trained end-to-end. Our neural Kalman dynamical model allows us to exploit the relative merits of each approach. We demonstrate state-of-the-art estimation and prediction on a number of physically challenging tasks, including visual odometry, sensor fusion for visual-inertial navigation and pendulum control. In addition we show how DynaNet can indicate failures through investigation of properties such as the rate of innovation (Kalman Gain)., Comment: Accepted by IEEE Transactions on Neural Networks and Learning Systems (TNNLS)

Deep learning approaches for Visual-Inertial Odometry (VIO) have proven successful, but they rarely focus on incorporating robust fusion strategies for dealing with imperfect input sensory data. We propose a novel end-to-end selective sensor fusion framework for monocular VIO, which fuses monocular images and inertial measurements in order to estimate the trajectory whilst improving robustness to real-life issues, such as missing and corrupted data or bad sensor synchronization. In particular, we propose two fusion modalities based on different masking strategies: deterministic soft fusion and stochastic hard fusion, and we compare with previously proposed direct fusion baselines. During testing, the network is able to selectively process the features of the available sensor modalities and produce a trajectory at scale. We present a thorough investigation on the performances on three public autonomous driving, Micro Aerial Vehicle (MAV) and hand-held VIO datasets. The results demonstrate the effectiveness of the fusion strategies, which offer better performances compared to direct fusion, particularly in presence of corrupted data. In addition, we study the interpretability of the fusion networks by visualising the masking layers in different scenarios and with varying data corruption, revealing interesting correlations between the fusion networks and imperfect sensory input data., Comment: Accepted by CVPR 2019

Inertial sensors play a pivotal role in indoor localization, which in turn lays the foundation for pervasive personal applications. However, low-cost inertial sensors, as commonly found in smartphones, are plagued by bias and noise, which leads to unbounded growth in error when accelerations are double integrated to obtain displacement. Small errors in state estimation propagate to make odometry virtually unusable in a matter of seconds. We propose to break the cycle of continuous integration, and instead segment inertial data into independent windows. The challenge becomes estimating the latent states of each window, such as velocity and orientation, as these are not directly observable from sensor data. We demonstrate how to formulate this as an optimization problem, and show how deep recurrent neural networks can yield highly accurate trajectories, outperforming state-of-the-art shallow techniques, on a wide range of tests and attachments. In particular, we demonstrate that IONet can generalize to estimate odometry for non-periodic motion, such as a shopping trolley or baby-stroller, an extremely challenging task for existing techniques., Comment: To appear in AAAI18 (Oral)

Chen C, Zhang Z, Li J, Sun Y. Onco Targets Ther. 2018;11: 6081–6090.On page 6089, the acknowledgment section was not included:AcknowledgmentThis study was funded by National Natural Science Foundation of China (No 81600217), Natural Science Foundation of Jiangsu Province (BK20160346), Jiangyin Municipal Transformation of Scientific and Technological Achievements Project of China (No JYKJ3308).Read the original article.

Changhao Chen,1,* Zhiwei Zhang,2,* Jie Li,3 Yuejun Sun4 1Department of General Surgery, The Second Hospital of Nanjing, Nanjing University of Chinese Medicine, Nanjing, Jiangsu 210003, China; 2Department of Cardiothoracic Surgery, The Second Affiliated Hospital of Soochow University, Suzhou, Jiangsu 215004, China; 3Department of Respiratory Medicine, Affiliated Jiangyin Hospital of Southeast University Medical College, Jiangyin, Jiangsu 214400, China; 4Department of Pathology, Affiliated Jiangyin Hospital of Southeast University Medical College, Jiangyin, Jiangsu 214400, China *These authors contributed equally to this work Background: Recently, various dynamically expressed lncRNAs are known to play critical roles in cancer progression. Small nucleolar RNA host genes (SNHG), a stable cytoplasmic lncRNA, which have been widely reported to act as an oncogene in non-small cell lung cancer (NSCLC). As an important member of SNHG, SNHG8 have been suggested to over-expressed in several cancer disease, while the biological function in NSCLC remains unclear. Purpose: Here we investigated the biological function and underlying mechanism of SNHG8 in human NSCLC. Patients and methods: The relationship between SNHG8 expression and clinicopathologic characteristic in NSCLC patients were observed from January 2014 to December 2014 in 120 NSCLC patients. The expression of SNHG8 were analyzed by qRT-PCR assay in cancer tissues and cells. Cell proliferation ability were detected in NSCLC cells by CCK-8 assay. Flow cytometric analysis were performed to detected the cell apoptosis and cell cycle. Luciferase assay and Western blot assay were performed on NSCLC cells to detected the underlying mechanism of SNHG8 in NSCLC. Moreover, Tumor xenografts in nude mice were performed to detected the in vivo function of SNHG8. Results: SNHG8 was over-expressed in NSCLC tissues and cells. Patients with high SNHG8 expression have poorer overall survival (OS) and progression-free survival (PFS) th