Image composition targets at synthesizing a realistic composite image fr...
Image composition refers to inserting a foreground object into a backgro...
Foreground object search (FOS) aims to find compatible foreground object...
Image harmonization is an essential step in image composition that adjus...
Painterly image harmonization aims to insert photographic objects into
p...
Affordance learning considers the interaction opportunities for an actor...
The goal of image harmonization is adjusting the foreground appearance i...
Given a composite image, image harmonization aims to adjust the foregrou...
Image composition refers to inserting a foreground object into a backgro...
In few-shot image generation, directly training GAN models on just a han...
The performances of defect inspection have been severely hindered by
ins...
Image harmonization aims to produce visually harmonious composite images...
In this work, we present a new computer vision task named video object o...
Semantic segmentation is an important and prevalent task, but severely
s...
Synthetic images created by image editing operations are prevalent, but ...
With the prevalence of image editing techniques, users can create fantas...
Inharmonious region localization aims to localize the region in a synthe...
Object placement aims to place a foreground object over a background ima...
Few-shot image generation and few-shot image translation are two related...
Image cropping aims to find visually appealing crops in an image, which ...
When using cut-and-paste to acquire a composite image, the geometry
inco...
Image harmonization targets at adjusting the foreground in a composite i...
Video understanding has achieved great success in representation learnin...
Object placement assessment (OPA) aims to predict the rationality score ...
Video harmonization aims to adjust the foreground of a composite video t...
Object detection has achieved promising success, but requires large-scal...
Deep learning is a data-hungry approach, which requires massive training...
Weakly-supervised semantic segmentation (WSSS) with image-level labels h...
Video composition aims to generate a composite video by combining the
fo...
Given a composite image, image harmonization aims to adjust the foregrou...
Superimposing visible watermarks on images provides a powerful weapon to...
Image composition aims to generate realistic composite image by insertin...
As a common image editing operation, image composition aims to cut the
f...
Recently, DETR and Deformable DETR have been proposed to eliminate the n...
Image composition targets at inserting a foreground object on a backgrou...
The advance of image editing techniques allows users to create artistic
...
Image composition assessment is crucial in aesthetic assessment, which a...
Image harmonization has been significantly advanced with large-scale
har...
The information bottleneck (IB) method is a technique for extracting
inf...
Zero-shot learning has been actively studied for image classification ta...
Recognizing fine-grained categories remains a challenging task, due to t...
Image composition is a fundamental operation in image editing field. How...
Learning to generate new images for a novel category based on only a few...
Existing semantic segmentation models heavily rely on dense pixel-wise
a...
In order to generate images for a given category, existing deep generati...
Multi-task Learning (MTL) for classification with disjoint datasets aims...
To generate new images for a given category, most deep generative models...
Static image action recognition, which aims to recognize action based on...
The goal of Sketch-Based Image Retrieval (SBIR) is using free-hand sketc...
Image composition is an important operation in image processing, but the...