24 citations · 45 across the 17 of their papers we have counts for
7 papers · 1 filter
Two-shot Video Object Segmentation
Kun Yan, Xiao Li, Fangyun Wei +4
Previous works on video object segmentation (VOS) are trained on densely annotated videos. Nevertheless, acquiring annotations in pixel level is expensive and time-consuming. In th…
Neural Capture of Animatable 3D Human from Monocular Video
Gusi Te, Xiu Li, Xiao Li +3
We present a novel paradigm of building an animatable 3D human representation from a monocular video input, such that it can be rendered in any unseen poses and views. Our method i…
Neighbor Correspondence Matching for Flow-based Video Frame Synthesis
Zhaoyang Jia, Yan Lu, Houqiang Li
Video frame synthesis, which consists of interpolation and extrapolation, is an essential video processing technique that can be applied to various scenarios. However, most existin…
Online Video Instance Segmentation via Robust Context Fusion
Xiang Li, Jinglu Wang, Xiaohao Xu +2
Video instance segmentation (VIS) aims at classifying, segmenting and tracking object instances in video sequences. Recent transformer-based neural networks have demonstrated their…
Towards Robust Video Object Segmentation with Adaptive Object Calibration
Xiaohao Xu, Jinglu Wang, Xiang Ming +1
In the booming video era, video segmentation attracts increasing research attention in the multimedia community. Semi-supervised video object segmentation (VOS) aims at segmenting…
Turbo: Opportunistic Enhancement for Edge Video Analytics
Yan Lu, Shiqi Jiang, Ting Cao +1
Edge computing is being widely used for video analytics. To alleviate the inherent tension between accuracy and cost, various video analytics pipelines have been proposed to optimi…