Abstract: Cover song identification (CSI) focuses on finding the same mu...
We present XFormer, a novel human mesh and motion capture method that
ac...
Continual learning refers to the capability of continuously learning fro...
Recent advances in image editing techniques have posed serious challenge...
We propose PD-GAN, a probabilistic diverse GAN for image inpainting. Giv...
User-intended visual content fills the hole regions of an input image in...
We present a self-supervised learning approach to learning monocular 3D ...
Fine-grained image categorization is challenging due to the subtle
inter...
Training an object detector on a data-rich domain and applying it to a
d...
Nowadays, skeleton information in videos plays an important role in
huma...
A family of loss functions built on pair-based computation have been pro...
Visual compatibility is critical for fashion analysis, yet is missing in...
It has been witnessed an emerging demand for image manipulation segmenta...
Image manipulation detection is different from traditional semantic obje...
In this paper, we propose a partition-masked Convolution Neural Network ...
Harvesting dense pixel-level annotations to train deep neural networks f...
We propose a two-stream network for face tampering detection. We train
G...
We present an image-based VIirtual Try-On Network (VITON) without using ...
To reduce the significant redundancy in deep Convolutional Neural Networ...
This paper proposes an automatic spatially-aware concept discovery appro...
The ubiquity of online fashion shopping demands effective recommendation...
Style transfer is an important task in which the style of a source image...
VRFP is a real-time video retrieval framework based on short text input
...
Complex event retrieval is a challenging research problem, especially wh...
The visualization of an image collection is the process of displaying a
...