Inicio  /  Future Internet  /  Vol: 14 Par: 1 (2022)  /  Artículo
ARTÍCULO
TITULO

Global Contextual Dependency Network for Object Detection

Junda Li    
Chunxu Zhang and Bo Yang    

Resumen

Current two-stage object detectors extract the local visual features of Regions of Interest (RoIs) for object recognition and bounding-box regression. However, only using local visual features will lose global contextual dependencies, which are helpful to recognize objects with featureless appearances and restrain false detections. To tackle the problem, a simple framework, named Global Contextual Dependency Network (GCDN), is presented to enhance the classification ability of two-stage detectors. Our GCDN mainly consists of two components, Context Representation Module (CRM) and Context Dependency Module (CDM). Specifically, a CRM is proposed to construct multi-scale context representations. With CRM, contextual information can be fully explored at different scales. Moreover, the CDM is designed to capture global contextual dependencies. Our GCDN includes multiple CDMs. Each CDM utilizes local Region of Interest (RoI) features and single-scale context representation to generate single-scale contextual RoI features via the attention mechanism. Finally, the contextual RoI features generated by parallel CDMs independently are combined with the original RoI features to help classification. Experiments on MS-COCO 2017 benchmark dataset show that our approach brings continuous improvements for two-stage detectors.

 Artículos similares

       
 
Xinlu Li, Yuanyuan Lei and Shengwei Ji    
Sentiment analysis of online Chinese buzzwords (OCBs) is important for healthy development of platforms, such as games and social networking, which can avoid transmission of negative emotions through prediction of users? sentiment tendencies. Buzzwords h... ver más
Revista: Future Internet

 
Jing Mei, Huahu Xu, Yang Li, Minjie Bian and Yuzhe Huang    
RGB?IR cross modality person re-identification (RGB?IR Re-ID) is an important task for video surveillance in poorly illuminated or dark environments. In addition to the common challenge of Re-ID, the large cross-modality variations between RGB and IR ima... ver más
Revista: Future Internet

 
Jing Li, Yong Liu, Yindan Zhang and Yang Zhang    
The use of very-high-resolution images to extract urban, suburban and rural roads has important application value. However, it is still a problem to effectively extract the road area occluded by roadside tree canopy or high-rise buildings to maintain the... ver más

 
Chao Jiang, Lin Liu, Xiaoxing Qin, Suhong Zhou and Kai Liu    
The importance of combining spatial and temporal aspects has been increasingly recognized over recent years, yet pertinent pattern analysis methods in place-based crime research still need further development to explicitly indicate spatial-temporal local... ver más

 
Lovelin Obi, Bankole Awuzie, Chukwudi Obi, Temitope S. Omotayo, Adekunle Oke and Oluyomi Osobajo    
Transitioning from demolition to deconstruction practices for end-of-life performances is gaining increasing attention following the need for the construction industry to minimise construction and demolition waste. Building information modelling (BIM) pr... ver más
Revista: Buildings