Search

Stock price prediction has always been a difficult task for forecasters. Using cutting-edge deep learning techniques, stock price prediction based on investor sentiment extracted from online forums has become feasible. We propose a novel hybrid deep learning framework for predicting stock prices. The framework leverages the XLNET model to analyze the sentiment conveyed in user posts on online forums, combines these sentiments with the post popularity factor to compute daily group sentiments, and integrates this information with stock technical indicators into an improved BiLSTM-highway model for stock price prediction. Through a series of comparative experiments involving four stocks on the Chinese stock market, it is demonstrated that the hybrid framework effectively predicts stock prices. This study reveals the necessity of analyzing investors' textual views for stock price prediction.

Humans watch more than a billion hours of video per day. Most of this video was edited manually, which is a tedious process. However, AI-enabled video-generation and video-editing is on the rise. Building on text-to-image models like Stable Diffusion and Imagen, generative AI has improved dramatically on video tasks. But it's hard to evaluate progress in these video tasks because there is no standard benchmark. So, we propose a new dataset for text-guided video editing (TGVE), and we run a competition at CVPR to evaluate models on our TGVE dataset. In this paper we present a retrospective on the competition and describe the winning method. The competition dataset is available at https://sites.google.com/view/loveucvpr23/track4., Comment: Project page: https://sites.google.com/view/loveucvpr23/track4

Recommender systems have been acknowledged as efficacious tools for managing information overload. Nevertheless, conventional algorithms adopted in such systems primarily emphasize precise recommendations and, consequently, overlook other vital aspects like the coverage, diversity, and novelty of items. This approach results in less exposure for long-tail items. In this paper, to personalize the recommendations and allocate recommendation resources more purposively, a method named PIM+RA is proposed. This method utilizes a bipartite network that incorporates self-connecting edges and weights. Furthermore, an improved Pearson correlation coefficient is employed for better redistribution. The evaluation of PIM+RA demonstrates a significant enhancement not only in accuracy but also in coverage, diversity, and novelty of the recommendation. It leads to a better balance in recommendation frequency by providing effective exposure to long-tail items, while allowing customized parameters to adjust the recommendation list bias.

Text-based person search (TBPS) is of significant importance in intelligent surveillance, which aims to retrieve pedestrian images with high semantic relevance to a given text description. This retrieval task is characterized with both modal heterogeneity and fine-grained matching. To implement this task, one needs to extract multi-scale features from both image and text domains, and then perform the cross-modal alignment. However, most existing approaches only consider the alignment confined at their individual scales, e.g., an image-sentence or a region-phrase scale. Such a strategy adopts the presumable alignment in feature extraction, while overlooking the cross-scale alignment, e.g., image-phrase. In this paper, we present a transformer-based model to extract multi-scale representations, and perform Asymmetric Cross-Scale Alignment (ACSA) to precisely align the two modalities. Specifically, ACSA consists of a global-level alignment module and an asymmetric cross-attention module, where the former aligns an image and texts on a global scale, and the latter applies the cross-attention mechanism to dynamically align the cross-modal entities in region/image-phrase scales. Extensive experiments on two benchmark datasets CUHK-PEDES and RSTPReid demonstrate the effectiveness of our approach. Codes are available at \href{url}{https://github.com/mul-hjh/ACSA}., Comment: Accepted by IEEE Transactions on Multimedia

Electrocatalytic hydrogen evolution reaction (HER) in alkaline media is a promising electrochemical energy conversion strategy. Ruthenium (Ru) is an efficient catalyst with a desirable cost for HER, however, the sluggish H2O dissociation process, due to the low H2O adsorption on its surface, currently hampers the performances of this catalyst in alkaline HER. Herein, we demonstrate that the H2O adsorption improves significantly by the construction of Ru-O-Mo sites. We prepared Ru/MoO2 catalysts with Ru-O-Mo sites through a facile thermal treatment process and assessed the creation of Ru-O-Mo interfaces by transmission electron microscope (TEM) and extended X-ray absorption fine structure (EXAFS). By using Fourier-transform infrared spectroscopy (FTIR) and H2O adsorption tests, we proved Ru-O-Mo sites have tenfold stronger H2O adsorption ability than that of Ru catalyst. The catalysts with Ru-O-Mo sites exhibited a state-of-the-art overpotential of 16 mV at 10 mA cm-2 in 1 M KOH electrolyte, demonstrating a threefold reduction than the previous bests of Ru (59 mV) and commercial Pt (31 mV) catalysts. We proved the stability of these performances over 40 hours without decline. These results could open a new path for designing efficient and stable catalysts.

Electrochemical CO2 reduction is a promising strategy for utilization of CO2 and intermittent excess electricity. Cu is the only single-metal catalyst that can electrochemically convert CO2 to multi-carbon products. However, Cu has an undesirable selectivity and activity for C2 products, due to its insufficient amount of CO* for C-C coupling. Considering the strong CO2 adsorption and ultra-fast reaction kinetics of CO* formation on Pd, an intimate CuPd(100) interface was designed to lower the intermediate reaction barriers and then improve the efficiency of C2 products. Density functional theory (DFT) calculations showed that the CuPd(100) interface has enhanced CO2 adsorption and decreased CO2* hydrogenation energy barrier, which are beneficial for C-C coupling. The potential-determining step (PDS) barrier of CO2 to C2 products on CuPd(100) interface is 0.61 eV, which is lower than that on Cu(100) (0.72 eV). Motivated by the DFT calculation, the CuPd(100) interface catalyst was prepared by a facile chemical solution method and demonstrated by transmission electron microscope (TEM). The CO2 temperature programmed desorption (CO2-TPD) and gas sensor experiments proved the enhancements of CO2 adsorption and CO2* hydrogenation abilities on CuPd(100) interface catalyst. As a result, the obtained CuPd(100) interface catalyst exhibits a C2 Faradaic efficiency of 50.3 (+/-) 1.2% at -1.4 VRHE in 0.1 M KHCO3, which is 2.1 times higher than 23.6(+/-) 1.5% of Cu catalyst. This work provides a rational design of Cu-based electrocatalyst for multi-carbon products by fine-tuning the intermediate reaction barriers.

The argyrodite sulfides are getting more and more attractive as highly promising solid-state electrolytes (SSEs) for high-performance all-solid-state batteries (ASSBs), owing to their high ionic conductivity, adequate plasticity, and decent mechanical strength. However, their poor incompatibility with Li metal anode and high voltage cathodes and as well as serious sensitivity to air significantly hinder their practical applications. Herein, we have devised an effective strategy to overcome these challenging shortcomings through modification of chalcogen chemistry under the guidance of theoretical modeling. The resultant Li6.25PS4O1.25Cl0.75 delivered excellent electrochemical compatibility with both pure Li anode and high-voltage LiCoO2 cathode, without detrimental impact upon the superb ionic conductivity of the pristine sulfide. Furthermore, the current SSE also exhibited highly improved stability to oxygen and moisture in air, with further advantage being more insulating to electrons. The remarkably enhanced compatibility with electrodes is attributed to in situ formation of solid anode electrolyte interphase (AEI) and cathode electrolyte interphase (CEI) layers. The formation of in situ AEI enabled ultra-stable Li plating/stripping at a record high current density up to 1 mAh cm-2 in Li|Li6.25PS4O1.25Cl0.75|Li symmetric cells over 1800 hours. The in situ CEI facilitated protection of the SSE from decomposition at elevated voltage. Consequently, the synergistic effect of AEI and CEI helped the LiCoO2|Li6.25PS4O1.25Cl0.75|Li battery cell to achieve markedly better cycling stability than that using the pristine Li6PS5Cl as SSE, at a high areal loading of the active cathode material (4 mg cm-2). This work adds a desirable SSE in the argyrodite sulfide family, so that high-performance solid battery cells could even be fabricated in ambient air.