Active learning selects informative samples for annotation within budget...
We propose a sparse end-to-end multi-person pose regression framework, t...
Multi-person pose estimation generally follows top-down and bottom-up
pa...
Co-occurrent visual pattern makes context aggregation become an essentia...
Open-world instance segmentation (OWIS) aims to segment class-agnostic
i...
Feature pyramid network (FPN) is one of the key components for object
de...
Off-the-shelf single-stage multi-person pose regression methods generall...
Multi-person pose estimation methods generally follow top-down and botto...
Utilizing trimap guidance and fusing multi-level features are two import...
Multi-object tracking (MOT) aims at estimating bounding boxes and identi...
Supervised learning is dominant in person search, but it requires elabor...
Video scene parsing is a long-standing challenging task in computer visi...
This paper studies the context aggregation problem in semantic image
seg...
We consider the challenging multi-person 3D body mesh estimation task in...
Although single-image super-resolution (SISR) methods have achieved grea...
Although deep learning based methods have achieved great progress in
uns...
Human pose estimation is a fundamental yet challenging task in computer
...
Semi-supervised video object segmentation is an interesting yet challeng...
Multi-person pose estimation is a fundamental yet challenging task in
co...
Multi-person pose estimation is an important but challenging problem in
...
In this work, we propose a mask propagation network to treat the video
s...