Stock price forecasting is a complex and highly uncertain task within the financial domain. Existing research has two main limitations: 1.Previous studies have underestimated the importance of market states, often relying solely on predefined stock data such as stock prices and trading volumes for prediction. 2.Existing research has primarily focused on time-aligned feature correlations, with limited exploration of asynchronous time correlations between stocks. To address these challenges, we introduce an innovative stock prediction model that integrates an LSTM-based adaptive market gating mechanism with a multi-scale time fusion approach. Specifically, the LSTM-based market gating mechanism dynamically adjusts feature selection, allowing the model to adapt to varying market conditions across different time spans. Meanwhile, the multi-scale time fusion mechanism integrates features at various temporal scales, alternately aggregating intra-stock and inter-stock relationships, thereby effectively capturing asynchronous relationships and improving the model’s prediction accuracy and stability. Experimental results indicate that the proposed model significantly outperforms existing baseline methods on the CSI300 and CSI800 datasets, demonstrating superior performance in both prediction accuracy and generalization capability.

In the tasks of pose estimation and behavior analysis in computer vision, conventional models are often constrained by various factors or complex environments (such as multiple targets, small targets, occluded targets, etc.). To address this problem, this paper proposes a symmetric cascaded additive network (MulAG) to improve the accuracy of posture estimation and behavior analysis in complex environments. MulAG consists of two modules, MulA and MulG. The MulA module is designed based on a cascaded symmetric network structure and incorporates the addition operation. MulA extracts the posture spatial features of the target from a single frame image. And, the MulG module is designed based on three continuous GRUs (gated recurrent unit). Based on the MulA, MulG extracts the posture temporal features from the posture spatial features of the moving target and predicts the posture temporal features of the moving target. The paper firstly demonstrates the feasibility of addition operations in pose estimation tasks by comparing with MobileNet-v3 in ablation experiments. Secondly, on the HiEve and CrowdPose datasets, MulA achieves accuracy of 79.6% and 80.4%, respectively, outperforming the PTM model by 12.0% and 21.2%. And detection speed of MulA achieves the best value at 8.6ms, which is 1 times higher than HDGCN. The result demonstrates the effectiveness of MulA in multi-target pose estimation in complex scenes. Finally, on the HDMB-51 and UCF-101 datasets, MulAG achieves accuracy of 74.8% and 86.3%, respectively, outperforming HDGCN by 9.6% and 9.5%. Compared with SKP and GIST, the fps of MulAG (44.8s-1) is improved by 8.2% and 8.9%. These experiments highlight the generalizability and superiority of MulAG in behavior analysis and pose estimation tasks.

Depth cues are essential for visual perception tasks like Salient Object Detection (SOD). Due to varying depth reliability across scenes, some researchers propose evaluating the overall quality of the depth maps and discarding the less reliable ones to avoid contamination. However, these methods often fail to fully utilize valuable information in depth maps, leading to sub-optimal performance particularly when depth quality is unreliable. Since low-quality depth maps still contain useful information that potentially improves model performance, we propose a Depth Pixel-wise Potential-aware Network to leverage these depth cues effectively. This network includes two novel components designed: 1) A learning strategy for explicitly modeling the confidence of each depth pixel to assist the model in locating valid information in the depth map. 2) A cross-modal adaptive multiple fusion module that fuses features from both RGB and depth modalities. It aims to mitigate the contamination effect of unreliable depth maps and fully exploit the benefits of multiple fusion strategies. Experimental results show that on four publicly available datasets, our method outperforms 17 mainstream methods on various evaluation metrics.

Capturing sufficient global context and rich spatial structure information is critical for dense prediction tasks. Convolutional Neural Network (CNN) is particularly adept at modeling fine-grained local features, while Transformer excels at modeling global context information. It is evident that CNN and Transformer exhibit complementary characteristics. Exploring the design of a network, that efficiently fuses these two models to leverage their strengths fully and achieve more accurate detection, represents a promising and worthwhile research topic. In this paper, we introduce a novel CNN-Transformer Iterative Fusion Network (CTIF-Net) for salient object detection. It efficiently combines CNN and Transformer to achieve superior performance by using a parallel dual encoder structure and a feature iterative fusion module. Firstly, CTIF-Net extracts features from the image using the CNN and the Transformer, respectively. Secondly, two feature convertors and a feature iterative fusion module are employed to combine and iteratively refine the two sets of features. The experimental results on multiple SOD datasets show that CTIF-Net outperforms 17 state-of-the-art methods, achieving higher performance in various mainstream evaluation metrics such as F-measure, S-measure, and MAE value. The code will be publicly available.

Summary It is imperative for us to develop the technology of image semantic segmentation with the increasing demand in the image processing. Nowadays, the development of deep learning is of great significance to the improvement of image segmentation. Furthermore, the paper discussed the relationship between image semantic segmentation and animal image research based on the actual situation, and found that animal image processing technology plays a more important role in the field of protecting precious animals. The end‐to‐end network training of this paper is consisted of Fully Convolutional Network (FCN) for the front end and Conditional Random Fields as Recurrent Neural Networks (CRF‐RNN) for the back end via comparing a variety of research methods. The experiments achieved desired outcome for the semantic segmentation of animal images by utilizing Caffe deep learning framework and explained the implementation details from the aspects of training and testing.

Confusing visual appearance and scattered small-scale patterns commonly exist in natural images, which forms a challenge for prior saliency detection methods. Inspired by the sensitivity to edge information of Human Visual Systems, we propose a universal edge-oriented framework to improve the performance of existing salient detection methods. Firstly, edge probability map is extracted from images and utilized to get edge-based over segmentation. Secondly, merging segments by a hierarchical model to generate edge regions. Finally, the proposed framework turns saliency detection to assign a saliency value to each edge region. Experimental results demonstrate the effectiveness of our framework.