Peak response regularization for localization.

Deep convolutional neural networks approaches often assume that the feature response has a Gaussian distribution with target-centered peak response, which can be used to guide the target location and classification. Nevertheless, such an assumption is implausible when there is progressive interference from other targets and/or background noise, which produces sub-peaks on the tracking response map and causes model drift. In this paper, we propose a feature response regularization approach for sub-peak response suppression and peak response enforcement and aim to handle progressive interference systematically. Our approach, referred to as Peak Response Regularization (PRR), applies simple-yet-efficient method to aggregate and align discriminative features, which convert local extremal response in discrete feature space to extremal response in continuous space, which enforces the localization and representation capability of convolutional features. Experiments on human pose detection, object detection, object tracking, and image classification demonstrate that PRR improves the performance of image tasks with a negligible computational cost.

Polarity- and Pressure-Induced Emission from a Benzophenone-Based Luminophore.

Since strong polarity usually causes emission quenching, materials with polarity-induced emission (PIE) are rarely reported despite their important applications in polar environments. Herein, an N-phenylcarbazole-substituted benzophenone derivative (BP-3-Cz) with a twisted electron donor-acceptor (D-A) structure is synthesized. The incorporation of heteroatoms into the twisted π-conjugated D-A backbone simultaneously endows BP-3-Cz with obvious polarity- and pressure-induced emission. Spectral analysis, X-ray diffraction, differential scanning calorimetry, and quantum chemical calculation results confirm that BP-3-Cz has special optical features related to the molecular conformation change and excited state turning to planarized intramolecular charge transfer with an increase in polarity or applied pressure. These findings contribute to the understanding of the PIE mechanism and the design of new PIE materials.

Adaptive stochastic parallel gradient descent approach for efficient fiber coupling.

In high-speed free-space optical communication systems, the received laser beam must be coupled into a single-mode fiber at the input of the receiver module. However, propagation through atmospheric turbulence degrades the spatial coherence of a laser beam and poses challenges for fiber coupling. In this paper, we propose a novel method, called as adaptive stochastic parallel gradient descent (ASPGD), to achieve efficient fiber coupling. To be specific, we formulate the fiber coupling problem as a model-free optimization problem and solve it using ASPGD in parallel. To avoid converging to the extremum points and accelerate its convergence speed, we integrate the momentum and the adaptive gain coefficient estimation to the original stochastic parallel gradient descent (SPGD) method. Simulation and experimental results demonstrate that the proposed method reduces 50% of iterations, while keeping the stability by comparing it with the original SPGD method.