Tianshan Liu
YOU?
Author Swipe
View article: GCS-YOLO: A Lightweight Detection Algorithm for Grape Leaf Diseases Based on Improved YOLOv8
GCS-YOLO: A Lightweight Detection Algorithm for Grape Leaf Diseases Based on Improved YOLOv8 Open
In view of the issues of high complexity, significant computational resource consumption, and slow inference speed in the detection algorithm for grape leaf diseases, this paper proposes GCS-YOLO, a lightweight detection algorithm based on…
View article: An End-to-End Two-Stream Network Based on RGB Flow and Representation Flow for Human Action Recognition
An End-to-End Two-Stream Network Based on RGB Flow and Representation Flow for Human Action Recognition Open
With the rapid advancements in deep learning, computer vision tasks have seen significant improvements, making two-stream neural networks a popular focus for video based action recognition. Traditional models using RGB and optical flow str…
View article: Day2Dark: Pseudo-Supervised Activity Recognition Beyond Silent Daylight
Day2Dark: Pseudo-Supervised Activity Recognition Beyond Silent Daylight Open
This paper strives to recognize activities in the dark, as well as in the day. We first establish that state-of-the-art activity recognizers are effective during the day, but not trustworthy in the dark. The main causes are the limited ava…
View article: Category-Aware Saliency Enhance Learning Based on CLIP for Weakly Supervised Salient Object Detection
Category-Aware Saliency Enhance Learning Based on CLIP for Weakly Supervised Salient Object Detection Open
Weakly supervised salient object detection (SOD) using image-level category labels has been proposed to reduce the annotation cost of pixel-level labels. However, existing methods mostly train a classification network to generate a class a…
View article: Deep Progressive Feature Aggregation Network for High Dynamic Range Imaging
Deep Progressive Feature Aggregation Network for High Dynamic Range Imaging Open
High dynamic range (HDR) imaging is an important task in image processing that aims to generate well-exposed images in scenes with varying illumination. Although existing multi-exposure fusion methods have achieved impressive results, gene…
View article: Structure-Enhanced Attentive Learning For Spine Segmentation From Ultrasound Volume Projection Images
Structure-Enhanced Attentive Learning For Spine Segmentation From Ultrasound Volume Projection Images Open
Automatic spine segmentation, based on ultrasound volume projection imaging (VPI), is of great value in clinical applications to diagnose scoliosis in teenagers. In this paper, we propose a novel framework to improve the segmentation accur…
View article: Flow-guided Spatial Attention Tracking for Egocentric Activity Recognition
Flow-guided Spatial Attention Tracking for Egocentric Activity Recognition Open
The popularity of wearable cameras has opened up a new dimension for egocentric activity recognition. While some methods introduce attention mechanisms into deep learning networks to capture fine-grained hand-object interactions, they ofte…
View article: Deep Multi-task Learning for Facial Expression Recognition and Synthesis Based on Selective Feature Sharing
Deep Multi-task Learning for Facial Expression Recognition and Synthesis Based on Selective Feature Sharing Open
Multi-task learning is an effective learning strategy for deep-learning-based facial expression recognition tasks. However, most existing methods take into limited consideration the feature selection, when transferring information between …
View article: Deep Multi-task Learning for Facial Expression Recognition and Synthesis Based on Selective Feature Sharing
Deep Multi-task Learning for Facial Expression Recognition and Synthesis Based on Selective Feature Sharing Open
Multi-task learning is an effective learning strategy for deep-learning-based facial expression recognition tasks. However, most existing methods take into limited consideration the feature selection, when transferring information between …
View article: Progressive Motion Representation Distillation With Two-Branch Networks for Egocentric Activity Recognition
Progressive Motion Representation Distillation With Two-Branch Networks for Egocentric Activity Recognition Open
Video-based egocentric activity recognition involves fine-grained spatio-temporal human-object interactions. State-of-the-art methods, based on the two-branch-based architecture, rely on pre-calculated optical flows to provide motion infor…
View article: Adaptive Weight Collaborative Complementary Learning for Robust Visual Tracking
Adaptive Weight Collaborative Complementary Learning for Robust Visual Tracking Open
Discriminative correlation filter (DCF) based tracking algorithms have recently shown impressive performance on benchmark datasets.However, amount of recent researches are vulnerable to heavy occlusions, irregular deformations and so on.In…
View article: Study on Urban Agglomeration and Land Use Efficiency in China
Study on Urban Agglomeration and Land Use Efficiency in China Open
With the urban statistical data from 2000 to 2016, this paper witch focus on the relationship between geography and urban land use efficiency, proves that the current land policy has a great negative impact on urban land use efficiency.The…
View article: Attempt to Train Compound Professional Talents
Attempt to Train Compound Professional Talents Open
In order to solve the orientation problem of applied chemistry, according to the actual situation of the school, we should play multidisciplinary comprehensive advantage and train compound talents to make the students form three-dimensiona…
View article: Research on the Risk and Countermeasure of China's Foreign Direct Investment under the Background of the Belt and Road Initiative
Research on the Risk and Countermeasure of China's Foreign Direct Investment under the Background of the Belt and Road Initiative Open
Chinese enterprises overseas investment is facing a series of direct investment risk, under the Background of The Belt and Road Initiative.Based on the current situation and characteristics of China's direct investment in the Belt and Road…