7 citations · 16 across the 5 of their papers we have counts for
7 papers · 1 filter
Weakly-Supervised Multi-Person Action Recognition in 360 Videos
Junnan Li, Jianquan Liu, Yongkang Wong +2
The recent development of commodity 360 cameras have enabled a single video to capture an entire scene, which endows promising potentials in surveillance scenarios. Howev…
GradMix: Multi-source Transfer across Domains and Tasks
Junnan Li, Ziwei Xu, Yongkang Wong +2
The computer vision community is witnessing an unprecedented rate of new tasks being proposed and addressed, thanks to the deep convolutional networks' capability to find complex m…
Visual Social Relationship Recognition
Junnan Li, Yongkang Wong, Qi Zhao +1
Social relationships form the basis of social structure of humans. Developing computational models to understand social relationships from visual data is essential for building int…
Unsupervised Learning of View-invariant Action Representations
Junnan Li, Yongkang Wong, Qi Zhao +1
The recent success in human action recognition with deep learning methods mostly adopt the supervised learning paradigm, which requires significant amount of manually labeled data…
Interact as You Intend: Intention-Driven Human-Object Interaction Detection
Bingjie Xu, Junnan Li, Yongkang Wong +2
The recent advances in instance-level detection tasks lay strong foundation for genuine comprehension of the visual scenes. However, the ability to fully comprehend a social scene…
Attention Transfer from Web Images for Video Recognition
Junnan Li, Yongkang Wong, Qi Zhao +1
Training deep learning based video classifiers for action recognition requires a large amount of labeled videos. The labeling process is labor-intensive and time-consuming. On the…