As the next-generation paradigm for content creation, AI-Generated Conte...
Recent work on Neural Radiance Fields (NeRF) has demonstrated significan...
The high-accuracy and resource-intensive deep neural networks (DNNs) hav...
Generative Diffusion Models (GDMs) have emerged as a transformative forc...
3D lane detection from monocular images is a fundamental yet challenging...
Limited by expensive pixel-level labels, polyp segmentation models are
p...
Extremely large-scale multiple-input-multiple-output (XL-MIMO), which of...
This paper studies the over-the-air computation (AirComp) in an orthogon...
In this paper, we introduce a realistic and challenging domain adaptatio...
This paper studies a multi-intelligent-reflecting-surface-(IRS)-enabled
...
This paper investigates the energy efficiency of a multiple-input
multip...
High-quality data is essential for conversational recommendation systems...
Accurate polyp detection is essential for assisting clinical rectal canc...
Federated edge learning (FEEL) enables privacy-preserving model training...
Remote zero-shot object recognition, i.e., offloading zero-shot object
r...
This correspondence studies the wireless powered over-the-air computatio...
Despite the simplicity, stochastic gradient descent (SGD)-like algorithm...
3D shape completion from point clouds is a challenging task, especially ...
With the recent advancements in edge artificial intelligence (AI), futur...
The traditional methods for data compression are typically based on the
...
3D single object tracking in LiDAR point clouds (LiDAR SOT) plays a cruc...
Being data-driven is one of the most iconic properties of deep learning
...
Existing neural radiance fields (NeRF) methods for large-scale scene mod...
In this work, we tackle the challenging problem of learning-based single...
Accurate polyp segmentation is of great significance for the diagnosis a...
When using LiDAR semantic segmentation models for safety-critical
applic...
Gaussian process state-space model (GPSSM) is a fully probabilistic
stat...
The mainstream of the existing approaches for video prediction builds up...
Accurate polyp segmentation is of great importance for colorectal cancer...
Measuring and alleviating the discrepancies between the synthetic (sourc...
Dialogue state tracking (DST) aims to convert the dialogue history into
...
Pushing artificial intelligence (AI) from central cloud to network edge ...
Few-shot dialogue state tracking (DST) is a realistic problem that train...
Although recent point cloud analysis achieves impressive progress, the
p...
In 3D medical image segmentation, small targets segmentation is crucial ...
This paper considers improving wireless communication and computation
ef...
Estimating accurate lane lines in 3D space remains challenging due to th...
In this paper, a semantic communication framework is proposed for textua...
Over-the-air federated edge learning (Air-FEEL) has emerged as a promisi...
360 videos in recent years have experienced booming development.
Compare...
In recent years, the exponential increase in the demand of wireless data...
Real-world text applications often involve composing a wide range of tex...
We present a new framework to reconstruct holistic 3D indoor scenes incl...
Recent progress on 3D scene understanding has explored visual grounding
...
This paper studies a new multi-device edge artificial-intelligent (AI)
s...
In this paper, we address the problem of joint sensing, computation, and...
Mobile communication standards were developed for enhancing transmission...
Federated learning (FL) over mobile devices has fostered numerous intrig...
We investigate the coexistence of task-oriented and data-oriented
commun...
Semi-supervised domain adaptation (SSDA) aims to apply knowledge learned...