Výsledky vyhledávání

Report

Geometric Features Enhanced Human-Object Interaction Detection

Autor: Zhu, Manli, Ho, Edmond S. L., Chen, Shuang, Yang, Longzhi, Shum, Hubert P. H.

Cameras are essential vision instruments to capture images for pattern detection and measurement. Human-object interaction (HOI) detection is one of the most popular pattern detection approaches for captured human-centric visual scenes. Recently, Tra

Externí odkaz: http://arxiv.org/abs/2406.18691

Zobrazit plný text záznamu

Report

Detect2Interact: Localizing Object Key Field in Visual Question Answering (VQA) with LLMs

Autor: Wang, Jialou, Zhu, Manli, Li, Yulei, Li, Honglei, Yang, Longzhi, Woo, Wai Lok

Localization plays a crucial role in enhancing the practicality and precision of VQA systems. By enabling fine-grained identification and interaction with specific parts of an object, it significantly improves the system's ability to provide contextu

Externí odkaz: http://arxiv.org/abs/2404.01151

Zobrazit plný text záznamu

Report

A Two-stream Convolutional Network for Musculoskeletal and Neurological Disorders Prediction

Autor: Zhu, Manli, Men, Qianhui, Ho, Edmond S. L., Leung, Howard, Shum, Hubert P. H.

Musculoskeletal and neurological disorders are the most common causes of walking problems among older people, and they often lead to diminished quality of life. Analyzing walking motion data manually requires trained professionals and the evaluations

Externí odkaz: http://arxiv.org/abs/2208.08848

Zobrazit plný text záznamu

Report

A Skeleton-aware Graph Convolutional Network for Human-Object Interaction Detection

Autor: Zhu, Manli, Ho, Edmond S. L., Shum, Hubert P. H.

Detecting human-object interactions is essential for comprehensive understanding of visual scenes. In particular, spatial connections between humans and objects are important cues for reasoning interactions. To this end, we propose a skeleton-aware g

Externí odkaz: http://arxiv.org/abs/2207.05733

Zobrazit plný text záznamu

Report

Interpreting Deep Learning based Cerebral Palsy Prediction with Channel Attention

Autor: Zhu, Manli, Men, Qianhui, Ho, Edmond S. L., Leung, Howard, Shum, Hubert P. H.

Early prediction of cerebral palsy is essential as it leads to early treatment and monitoring. Deep learning has shown promising results in biomedical engineering thanks to its capacity of modelling complicated data with its non-linear architecture.

Externí odkaz: http://arxiv.org/abs/2106.04471

Zobrazit plný text záznamu