Video outpainting aims to adequately complete missing areas at the edges...
In this paper, we investigate federated contextual linear bandit learnin...
Text design is one of the most critical procedures in poster design, as ...
Stylized visual captioning aims to generate image or video descriptions ...
We consider the problem of optimizing a grey-box objective function, i.e...
Click-Through Rate (CTR) prediction serves as a fundamental component in...
Cascading architecture has been widely adopted in large-scale advertisin...
Conversion rate (CVR) prediction is one of the core components in online...
Automatically narrating a video with natural language can assist people ...
This paper studies the problem of online performance optimization of
con...
In this work, we present a new computer vision task named video object o...
In this paper, the CONFIG algorithm, a simple and provably efficient
con...
With the recent advances in mobile energy storage technologies, electric...
Motion transfer aims to transfer the motion of a driving video to a sour...
Image animation aims to animate a source image by using motion learned f...
Efficient global optimization is a widely used method for optimizing
exp...
Layout generation is a novel task in computer vision, which combines the...
Despite the development of ranking optimization techniques, the pointwis...
Recently, online shopping has gradually become a common way of shopping ...
Video captioning aims to understand the spatio-temporal semantic concept...
Existing image captioning systems are dedicated to generating narrative
...
Recent efforts on scene text erasing have shown promising results. Howev...
Temporal action detection (TAD) aims to locate and recognize the actions...
Given a source image and a driving video depicting the same object type,...
The goal of video highlight detection is to select the most attractive
s...
Federated learning (FL) is a promising learning paradigm that can tackle...
Federated learning (FL), as an emerging edge artificial intelligence
par...
Creative image animations are attractive in e-commerce applications, whe...
The objective of image outpainting is to extend image current border and...
Advertising expenditures have become the major source of revenue for
e-c...
Over-the-air computation (AirComp) is a disruptive technique for fast
wi...
Let a labeled dataset be given with scattered samples and consider the
h...
Visual Semantic Embedding (VSE) is a dominant approach for vision-langua...
This paper introduces an open-source software for distributed and
decent...
This paper introduces the Attribute-Decomposed GAN, a novel generative m...
Automatic map extraction is of great importance to urban computing and
l...
We present a new, embarrassingly simple approach to instance segmentatio...
Monocular depth estimation enables 3D perception from a single 2D image,...
Convolutional neural networks require numerous data for training. Consid...
We propose the Unified Visual-Semantic Embeddings (Unified VSE) for lear...
We propose Unified Visual-Semantic Embeddings (UniVSE) for learning a jo...
We present FoveaBox, an accurate, flexible and completely anchor-free
fr...
Decentralized optimization algorithms are important in different context...
We present consistent optimization for single stage object detection.
Pr...
Modern CNN-based object detectors rely on bounding box regression and
no...
Humans recognize the visual world at multiple levels: we effortlessly
ca...
We study the problem of grounding distributional representations of text...
The present paper applies the recently proposed Augmented Lagrangian
Alt...
Detecting individual pedestrians in a crowd remains a challenging proble...
The improvements in recent CNN-based object detection works, from R-CNN ...