We present DySample, an ultra-lightweight and effective dynamic upsample...
We show that crowd counting can be viewed as a decomposable point queryi...
Deep learning (DL) has gained popularity in recent years as an effective...
In recent years, end-to-end scene text spotting approaches are evolving ...
Video stabilization refers to the problem of transforming a shaky video ...
Conditional spatial queries are recently introduced into DEtection
TRans...
We introduce the notion of point affiliation into feature upsampling. By...
We introduce Probabilistic Coordinate Fields (PCFs), a novel
geometric-i...
There is a long-standing problem of repeated patterns in correspondence
...
Remote photoplethysmography (rPPG) is an important technique for perceiv...
Class-agnostic counting (CAC) aims to count objects of interest from a q...
Operators from various industries have been pushing the adoption of wire...
All-in-Focus (AIF) photography is expected to be a commercial selling po...
This article studies the collaborative transportation of a cable-suspend...
Correspondence pruning aims to search consistent correspondences (inlier...
Point cloud segmentation is a fundamental task in 3D vision that serves ...
Remote photoplethysmography (rPPG) technology has drawn increasing atten...
Automatic image cropping algorithms aim to recompose images like human-b...
We study the composition style in deep image matting, a notion that
char...
Level 5 Autonomous Driving, a technology that a fully automated vehicle ...
We introduce point affiliation into feature upsampling, a notion that
de...
Neural Radiance Field (NeRF) and its variants have exhibited great succe...
Generative adversarial networks (GANs) have been trained to be professio...
We consider the problem of task-agnostic feature upsampling in dense
pre...
Learning accurate object detectors often requires large-scale training d...
Partial occlusion effects are a phenomenon that blurry objects near a ca...
We introduce a 3D instance representation, termed instance kernels, wher...
We propose BokehMe, a hybrid bokeh rendering framework that marries a ne...
Class-agnostic counting (CAC) aims to count all instances in a query ima...
Modern wireless cellular networks use massive multiple-input multiple-ou...
The paper describes an online deep learning algorithm for the adaptive
m...
Bootstrapping provides a flexible and effective approach for assessing t...
We show that learning affinity in upsampling provides an effective and
e...
We formulate counting as a sequential decision problem and present a nov...
Remote measurement of physiological signals from videos is an emerging t...
Visual counting, a task that aims to estimate the number of objects from...
Visual counting, a task that predicts the number of objects from an
imag...
We show that existing upsampling operators can be unified with the notio...
Joint replacement is the most common inpatient surgical treatment in the...
We introduce PreCo, a large-scale English dataset for coreference resolu...
In this paper, we present our deep attention-based classification (DABC)...
Domain adaption (DA) allows machine learning methods trained on data sam...
Accurately counting maize tassels is important for monitoring the growth...