In this study, we address the challenge of 3D scene structure recovery f...
Due to the extremely low latency, events have been recently exploited to...
In this paper, we propose a reduced-dimensional smoothed particle
hydrod...
Vectorized high-definition map online construction has garnered consider...
Unsupervised methods for reconstructing structures face significant
chal...
Recent strides in Text-to-3D techniques have been propelled by distillin...
We introduce UbiPhysio, a milestone framework that delivers fine-grained...
Intuitive physics is pivotal for human understanding of the physical wor...
Predicting the future behavior of agents is a fundamental task in autono...
The remarkable multimodal capabilities demonstrated by OpenAI's GPT-4 ha...
Reconstructing accurate 3D scenes from images is a long-standing vision ...
In this perspective paper, we first comprehensively review existing
eval...
Social media streams contain large and diverse amount of information, ra...
This report introduces the 1st place winning solution for the Autonomous...
Vectorized high-definition map (HD-map) construction, which focuses on t...
Without explicit feedback, humans can rapidly learn the meaning of words...
The recent advancements in image-text diffusion models have stimulated
r...
Digital transformation in buildings accumulates massive operational data...
Predicting pedestrian behavior when interacting with vehicles is one of ...
In this article, physical layer security (PLS) in an intelligent reflect...
Verification plays an essential role in the formal analysis of
safety-cr...
We study building a multi-task agent in Minecraft. Without human
demonst...
In practical recommendation scenarios, users often interact with items u...
This paper introduces XFL, an industrial-grade federated learning projec...
The wide popularity of short videos on social media poses new opportunit...
Neural network controllers (NNCs) have shown great promise in autonomous...
As convolutional neural networks (CNN) become the most successful
recons...
Recent advancements in reinforcement learning algorithms have opened doo...
With recent advances in image-to-image translation tasks, remarkable pro...
Data-intensive applications involving irregular memory streams are
ineff...
In this paper, we address monocular depth estimation with deep neural
ne...
In unsupervised person Re-ID, peer-teaching strategy leveraging two netw...
Is dynamics prediction indispensable for physical reasoning? If so, what...
The recent breakthroughs in deep learning methods have sparked a wave of...
Physics-informed neural networks (PINN) can achieve lower development an...
Note that the serial structure of blockchain has many essential pitfalls...
In Multi-Agent Reinforcement Learning, communication is critical to enco...
Few-shot segmentation aims to learn a segmentation model that can be
gen...
Supervised multi-view stereo (MVS) methods have achieved remarkable prog...
Recently, Implicit Neural Representations (INRs) parameterized by neural...
Few-shot open-set recognition aims to classify both seen and novel image...
Obtaining high quality particle distribution representing clean geometry...
This technical report presents an effective method for motion prediction...
Product images are essential for providing desirable user experience in ...
Theoretical ideas and empirical research have shown us a seemingly surpr...
Ensembling certifiably robust neural networks has been shown to be a
pro...
Machine learning is rapidly being used in database research to improve t...
The wide popularity of short videos on social media poses new opportunit...
In this paper, we proposed an automatic Scenario-based Multi-product
Adv...
This article investigates physical layer security (PLS) in reconfigurabl...