The shutter strategy applied to the photo-shooting process has a signifi...
Temporal Knowledge graph completion (TKGC) is a crucial task that involv...
In this work, we focus on synthesizing high-fidelity novel view images f...
The 3D Lookup Table (3D LUT) is a highly-efficient tool for real-time im...
Temporal modeling is crucial for video super-resolution. Most of the vid...
The ability to make educated predictions about their surroundings, and
a...
Recording fast motion in a high FPS (frame-per-second) requires expensiv...
Color constancy aims to restore the constant colors of a scene under
dif...
Domain adaptive semantic segmentation aims to learn a model with the
sup...
RGB-D saliency detection integrates information from both RGB images and...
In this paper, we propose an end-to-end learning framework for event-bas...
High dynamic range (HDR) imaging from multiple low dynamic range (LDR) i...
Most existing domain adaptation methods focus on adaptation from only on...
Recently unsupervised domain adaptation for the semantic segmentation ta...
Multi-source unsupervised domain adaptation (MSDA) aims at adapting mode...
Data-driven based approaches, in spite of great success in many tasks, h...
In the last few years, image denoising has benefited a lot from the fast...
Most video super-resolution methods super-resolve a single reference fra...
Video super-resolution, which aims at producing a high-resolution video ...
Few-shot learning has attracted intensive research attention in recent y...
This work investigates the task of unsupervised model personalization,
a...
The task of single image super-resolution (SISR) aims at reconstructing ...
Although remarkable progress has been made on single image super-resolut...
Artificial neural networks thrive in solving the classification problem ...
Generative adversarial networks (GANs) have been successfully used for
c...
This paper proposes the novel task of video generation conditioned on a
...
Image-to-image translation task has become a popular topic recently. Mos...
Deep learning based methods have recently pushed the state-of-the-art on...
Pixelwise semantic image labeling is an important, yet challenging, task...
This paper proposes the novel Pose Guided Person Generation Network (PG^...
In a traditional convolutional layer, the learned filters stay fixed aft...
In this work we focus on the problem of image caption generation. We pro...