Using liquid crystalline self-assembly of cellulose nanocrystals, we achieve long-range alignment of anisotropic metal nanoparticles in colloidal nanocrystal dispersions that are then used to deposit thin structured films with ordering features highly dependent on the deposition method. These hybrid films are comprised of gold nanorods unidirectionally aligned in a matrix that can be made of ordered cellulose nanocrystals or silica nanostructures obtained by using cellulose-based nanostructures as a replica. The ensuing long-range alignment of gold nanorods in both cellulose-based and nanoporous silica films results in a polarization-sensitive surface plasmon resonance. The demonstrated device-scale bulk nanoparticle alignment may enable engineering of new material properties arising from combining the orientational ordering of host nanostructures and properties of the anisotropic plasmonic metal nanoparticles. Our approach may also allow for scalable fabrication of plasmonic polarizers and nanoporous silica structures with orientationally ordered anisotropic plasmonic nanoinclusions.

Fruit quality assessment plays a crucial role in determining their market value, consumer acceptance, and post-harvest management. In recent years, spectroscopic techniques have gained significant attention as non-destructive methods for evaluating fruit quality. In this study, we propose a novel deep-learning network, called GCNN-LSTM-AT, for the prediction of five important parameters of tangerines using visible and near-infrared spectroscopy (Vis–NIR). The quality attributes include soluble solid content (SSC), total acidity (TA), acid–sugar ratio (A/S), firmness, and Vitamin C (VC). The proposed model combines the strengths of graph convolutional network (GCN), convolutional neural networks (CNNs), and long short-term memory (LSTM) to capture both spatial and sequential dependencies in the spectra data, and incorporates an attention mechanism to enhance the discriminative ability of the model. To investigate the effectiveness and stability of the model, comparisons with three traditional machine-learning algorithms—moving window partial least squares (MWPLS), random forest (RF), and support vector regression (SVR)—and two deep neural networks—DeepSpectra2D and CNN-AT—are provided. The results have shown that the GCNN-LSTM-AT network outperforms other algorithms and models, achieving accurate predictions for SSC ($R^2$: 0.9885, RMSECV: 0.1430 ${}^{\circ }$Brix), TA ($R^2$: 0.8075, RMSECV: 0.0868%), A/S ($R^2$: 0.9014, RMSECV: 1.9984), firmness ($R^2$: 0.9472, RMSECV: 0.0294 kg), and VC ($R^2$: 0.7386, RMSECV: 29.4104 mg/100 g) of tangerines.

A bendable ultra-black material consisting of graphite nanocones and nanowires is fabricated through a simple plasma etching process. The optical properties of the absorber are characterized in the wavelength range of 400-2000 nm with average specular reflectance 0.05 ± 0.03% at normal incidence and the material thickness is only around 5 μm. The reflectance of the absorber remains low at large incident angles and is relatively independent of polarization. Simulations confirm the cooperative effect of the nanowires and nanocones leading to an ultra-black thin carbon material.

DeepLab v3+ neural network shows excellent performance in semantic segmentation. In this paper, we proposed a segmentation framework based on DeepLab v3+ neural network and applied it to the problem of hyperspectral imagery classification (HSIC). The dimensionality reduction of the hyperspectral image is performed using principal component analysis (PCA). DeepLab v3+ is used to extract spatial features, and those are fused with spectral features. A support vector machine (SVM) classifier is used for fitting and classification. Experimental results show that the framework proposed in this paper outperforms most traditional machine learning algorithms and deep-learning algorithms in hyperspectral imagery classification tasks.

Localization and tracking in multi-player sports present significant challenges, particularly in wide and crowded scenes where severe occlusions can occur. Traditional solutions relying on a single camera are limited in their ability to accurately identify players and may result in ambiguous detection. To overcome these challenges, we proposed fusing information from multiple cameras positioned around the field to improve positioning accuracy and eliminate occlusion effects. Specifically, we focused on soccer, a popular and representative multi-player sport, and developed a multi-view recording system based on a $1+N$ strategy. This system enabled us to construct a new benchmark dataset and continuously collect data from several sports fields. The dataset includes 17 sets of densely annotated multi-view videos, each lasting 2 min, as well as 1100+ min multi-view videos. It encompasses a wide range of game types and nearly all scenarios that could arise during real game tracking. Finally, we conducted a thorough assessment of four multi-view multi-object tracking (MVMOT) methods and gained valuable insights into the tracking process in actual games.

Optical waveplates play an essential role in controlling polarization in various applications. We show the feasibility of facile production of optical waveplates from plant-based cellulose nanocrystal (CNC) nematics. We align CNC nematic liquid crystals doped with polyethylene glycol on periodically patterned polydimethylsiloxane substrates on large scale by shearing forces and prepare a 1/4 λ and a 1/2 λ CNC waveplates for 530 nm by bonding two slices of CNC nematic films with half-period displacement. The optical performance of the CNC waveplates is investigated by Mueller matrix analysis and is examined by measuring the transmission spectra of the waveplate between two polarizers, and optical extinction and birefringence of CNCs are extracted from the measured spectra. Our CNC waveplates of arbitrary phase difference are flexible and can be tailored into any desirable shape conveniently.