In this paper, we propose a novel training strategy called SupFusion, wh...
Estimating the 3D structure of the human body from natural scenes is a
f...
Recently, digital humans for interpersonal interaction in virtual
enviro...
Accurate polyp detection is essential for assisting clinical rectal canc...
It is widely reported that deep generative models can classify
out-of-di...
Despite the simplicity, stochastic gradient descent (SGD)-like algorithm...
In recent years, the Transformer architecture has shown its superiority ...
Although recent point cloud analysis achieves impressive progress, the
p...
Weakly Supervised Object Localization (WSOL), which aims to localize obj...
As camera and LiDAR sensors capture complementary information used in
au...
The colorectal polyps classification is a critical clinical examination....
Integrating multi-modal data to improve medical image analysis has recei...
Despite the considerable progress in automatic abdominal multi-organ
seg...
Dancing video retargeting aims to synthesize a video that transfers the ...
Recent advanced methods for fashion landmark detection are mainly driven...
Dense video captioning aims to generate multiple associated captions wit...
Accurate polyp segmentation is of great importance for colorectal cancer...
Crowd counting is critical for numerous video surveillance scenarios. On...
The recent vision transformer(i.e.for image classification) learns non-l...
Reducing the complexity of the pipeline of instance segmentation is cruc...
Point Cloud Sampling and Recovery (PCSR) is critical for massive real-ti...
Image virtual try-on aims to fit a garment image (target clothes) to a p...
Compared with the visual grounding in 2D images, the natural-language-gu...
LiDAR point cloud analysis is a core task for 3D computer vision, especi...
Although a polygon is a more accurate representation than an upright bou...
This paper reviews the second AIM learned ISP challenge and provides the...
Aggregating multi-level feature representation plays a critical role in
...
Normalization techniques are important in different advanced neural netw...
Image visual try-on aims at transferring a target clothing image onto a
...
Group convolution, which divides the channels of ConvNets into groups, h...
Group convolution, which divides the channels of ConvNets into groups, h...
Modern deep neural networks are often vulnerable to adversarial samples....
We address a learning-to-normalize problem by proposing Switchable
Norma...
Normalization methods improve both optimization and generalization of
Co...
Understanding fashion images has been advanced by benchmarks with rich
a...
Yes, they do. This work investigates a perspective for deep learning: wh...
Semantic image parsing, which refers to the process of decomposing image...
Traffic flow prediction is crucial for urban traffic management and publ...
Video person re-identification attracts much attention in recent years. ...
This paper investigates a fundamental problem of scene understanding: ho...
Recent successes in learning-based image classification, however, heavil...
This paper addresses a fundamental problem of scene understanding: How t...
This paper addresses the problem of geometric scene parsing, i.e.
simult...
Constructing effective representations is a critical but challenging pro...
This paper investigates a general framework to discover categories of
un...