This work considers gradient-based mesh optimization, where we iterative...
Masked autoencoder (MAE) has attracted unprecedented attention and achie...
Event skeleton generation, aiming to induce an event schema skeleton gra...
Reconstruction and intrinsic decomposition of scenes from captured image...
Event extraction is a fundamental task in natural language processing th...
We present Mask-then-Fill, a flexible and effective data augmentation
fr...
DreamFusion has recently demonstrated the utility of a pre-trained
text-...
Event extraction (EE) is crucial to downstream tasks such as new aggrega...
We present Twin Answer Sentences Attack (TASA), an adversarial attack me...
As several industries are moving towards modeling massive 3D virtual wor...
Existing transformer-based image backbones typically propagate feature
i...
Graph Neural Networks (GNNs) have achieved great success in various grap...
We present IBR, an Iterative Backward Reasoning model to solve the proof...
The goal of empathetic response generation is to enhance the ability of
...
Exploiting light field data makes it possible to obtain dense and accura...
Representations of events described in text are important for various ta...
Native code is now commonplace within Android app packages where it co-e...
We present an efficient method for joint optimization of topology, mater...
We introduce DMTet, a deep 3D conditional generative model that can
synt...
We consider the challenging problem of predicting intrinsic object prope...
We propose a method to create plausible geometric and texture style
vari...
Graph Neural Networks (GNNs) have already been widely applied in various...
The lack of reliable automatic evaluation metrics is a major impediment ...
We introduce DatasetGAN: an automatic procedure to generate massive data...
Infectious diseases are caused by pathogenic microorganisms, such as
bac...
3D shape representations that accommodate learning-based 3D reconstructi...
Differentiable rendering has paved the way to training neural networks t...
The Whittaker 2d growth model is a triangular continuous Markov diffusio...
In this work, we propose information laundering, a novel framework for
e...
Inferring detailed 3D geometry of the scene is crucial for robotics
appl...
In modern computer vision, images are typically represented as a fixed
u...
Android framework-specific app crashes are hard to debug. Indeed, the
ca...
Light fields record not only the spatial information of observed scenes ...
Neural conversation models such as encoder-decoder models are easy to
ge...
Many machine learning models operate on images, but ignore the fact that...
We study an interesting problem in training neural network-based models ...
Sentence function is an important linguistic feature referring to a user...
Product bundling, offering a combination of items to customers, is one o...
We present a method for compositing virtual objects into a photograph su...
Manually labeling objects by tracing their boundaries is a laborious pro...
Reconstruction of geometry based on different input modes, such as image...
Neural generative models have become popular and achieved promising
perf...
Fine-grained classification is challenging due to the difficulty of find...
A user can be represented as what he/she does along the history. A commo...
This paper consider a new secure communication scene where a full-duplex...
We present a growing collection of Android apps collected from several
s...
The excited states of polyatomic systems are rather complex, and often
e...