PP-HumanSeg: Connectivity-Aware Portrait Segmentation with a Large-Scale Teleconferencing Video Dataset

Chu, Lutao; Liu, Yi; Wu, Zewu; Tang, Shiyu; Chen, Guowei; Hao, Yuying; Jia, Peng; Chen, Zeyu; Lai, Baohua; Xiong, Haoyi

doi:10.1109/wacvw54805.2022.00026

Cited by 16 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It has been widely applied in real-world applications, e.g. medical imaging [30], autonomous driving [10,24], video conferencing [5], semiautomatic annotation [9]. As a fundamental task in computer vision, semantic segmentation has attracted a lot of attention from researchers [13,16].…”

Section: Introductionmentioning

confidence: 99%

PP-LiteSeg: A Superior Real-Time Semantic Segmentation Model

Jia¹,

Liu²,

Tang³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Real-world applications have high demands for semantic segmentation methods. Although semantic segmentation has made remarkable leap-forwards with deep learning, the performance of real-time methods is not satisfactory. In this work, we propose PP-LiteSeg, a novel lightweight model for the real-time semantic segmentation task. Specifically, we present a Flexible and Lightweight Decoder (FLD) to reduce computation overhead of previous decoder. To strengthen feature representations, we propose a Unified Attention Fusion Module (UAFM), which takes advantage of spatial and channel attention to produce a weight and then fuses the input features with the weight. Moreover, a Simple Pyramid Pooling Module (SPPM) is proposed to aggregate global context with low computation cost. Extensive evaluations demonstrate that PP-LiteSeg achieves a superior tradeoff between accuracy and speed compared to other methods. On the Cityscapes test set, PP-LiteSeg achieves 72.0% mIoU/273.6 FPS and 77.5% mIoU/102.6 FPS on NVIDIA GTX 1080Ti. Source code and models are available at Pad-dleSeg: https://github.com/PaddlePaddle/PaddleSeg.

show abstract

Section: Introductionmentioning

confidence: 99%

PP-LiteSeg: A Superior Real-Time Semantic Segmentation Model

Jia¹,

Liu²,

Tang³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…This resulted in unprecedented growth in the number of video conferencing users. Face detection and portrait segmentation have made great support for video conference, providing convenience for homeschooling and telework [43] , [44] , [45] . Robotic technologies, including examination robot [46] , healthcare robot [47] , monitoring robot [48] , disinfection and cleaning robots [49] , delivery and logistic robot [50] etc., leveraging face detection, voice recognition, and sensors, have been globally used to facilitate the diagnosis and treatment, reduce personnel contact and aid human daily life.…”

Section: Overview Of Big Data and Artificial Intelligence In Epidemicmentioning

confidence: 99%

Application of big data and artificial intelligence in epidemic surveillance and containment

Jiao¹,

Ji²,

Yan³

et al. 2023

Intelligent Medicine

View full text Add to dashboard Cite

“…For instance, they mention how online studies could lead to noisier data and higher drop-out rates, but, at the same time, they make it possible to collect more extensive and quicker data amounts and ensure higher anonymity. [7] illustrates a study in which a data-set containing conference videos was used to validate their semantic segmentation approach. Moving on to social interaction studies, [16] describes deception detection in group video conversations and points out the importance of considering such a kind of interaction, as video calls are becoming increasingly common after the Covid-19 hit.…”

Section: Data-sets In the Age Of Covid-19mentioning

confidence: 99%

Social Interaction Data-sets in the Age of Covid-19: a Case Study on Digital Commensality

Ceccaldi

Lucia

Niewiadomski

et al. 2022

Proceedings of the 2022 International Conference on Advanced Visual Interfaces

View full text Add to dashboard Cite

Research focusing on social interaction often leverages data-sets, allowing annotation, analysis, and modeling of social behavior. When it comes to commensality, researchers have started working on computational models of food and eating-related activities recognition. The growing research area known as Digital Commensality, has focused on meals shared online, for instance, through videochat. However, to investigate this topic, traditional data-sets recorded in laboratory settings may not be the best option in terms of ecological validity. Covid-19 restrictions and lock-downs have increased in online gatherings, with many people becoming used to the idea of sharing meals online. Following this trend, we propose the concept of collecting data by recording online interactions and discuss the challenges related to this methodology. We illustrate our approach in creating the first Digital Commensality data-set, containing recordings of food-related social interactions collected online during the Covid-19 outbreak.

show abstract

PP-HumanSeg: Connectivity-Aware Portrait Segmentation with a Large-Scale Teleconferencing Video Dataset

Cited by 16 publications

References 17 publications

PP-LiteSeg: A Superior Real-Time Semantic Segmentation Model

PP-LiteSeg: A Superior Real-Time Semantic Segmentation Model

Application of big data and artificial intelligence in epidemic surveillance and containment

Social Interaction Data-sets in the Age of Covid-19: a Case Study on Digital Commensality

Contact Info

Product

Resources

About