The recent surge of utilizing deep neural networks for geometric process...
We propose a method, named DualMesh-UDF, to extract a surface from unsig...
The self-media era provides us tremendous high quality videos. Unfortuna...
Recent years have witnessed great progress in creating vivid audio-drive...
This paper proposes a hybrid radiance field representation for unbounded...
Cloud-native architecture is becoming increasingly crucial for today's c...
Neural implicit representations are known to be more compact for depicti...
Model fairness (a.k.a., bias) has become one of the most critical proble...
Recent strides in Text-to-3D techniques have been propelled by distillin...
3D human generation from 2D images has achieved remarkable progress thro...
Classic BFT consensus protocols guarantee safety and liveness for all cl...
Data heterogeneity across clients is one of the key challenges in Federa...
Multimodal Sentiment Analysis leverages multimodal signals to detect the...
Zero Redundancy Optimizer (ZeRO) has been used to train a wide range of ...
Synthesizing high-fidelity head avatars is a central problem for compute...
Calibrating the extrinsic parameters of sensory devices is crucial for f...
Image retrieval plays an important role in the Internet world. Usually, ...
With the increasing prevalence of robots in daily life, it is crucial to...
Medical artificial general intelligence (MAGI) enables one foundation mo...
Despite the success of deep learning in video understanding tasks, proce...
Synthetic data has emerged as a promising source for 3D human research a...
As it is hard to calibrate single-view RGB images in the wild, existing ...
Existing Human NeRF methods for reconstructing 3D humans typically rely ...
While most recent autonomous driving system focuses on developing percep...
Human skin can accurately sense the self-decoupled normal and shear forc...
With the growing popularity of smartphone photography in recent years, w...
Amateurs working on mini-films and short-form videos usually spend lots ...
Recent advances in modeling 3D objects mostly rely on synthetic datasets...
We design and analyze an iterative two-grid algorithm for the finite ele...
Time-series anomaly detection is an important task and has been widely
a...
Point-of-care ultrasound (POCUS) is one of the most commonly applied too...
Video copy localization aims to precisely localize all the copied segmen...
Collaborative edge computing (CEC) is an emerging paradigm enabling shar...
The explosion of user-generated videos stimulates a great demand for
no-...
Audio driven talking head synthesis is a challenging task that attracts
...
3D human pose and shape estimation (a.k.a. "human mesh recovery") has
ac...
Understanding dynamic hand motions and actions from egocentric RGB video...
3D Multi-object tracking (MOT) ensures consistency during continuous dyn...
In dermatological disease diagnosis, the private data collected by mobil...
Creating 3D shapes from 2D drawings is an important problem with applica...
Amphibious ground-aerial vehicles fuse flying and driving modes to enabl...
Monocular 3D object detection is an essential perception task for autono...
This paper addresses an important problem of ranking the pre-trained dee...
Understanding human intentions during interactions has been a long-lasti...
Accurately segmenting temporal frames of cine magnetic resonance imaging...
High-throughput blockchains require efficient transaction broadcast
mech...
Decoupling consensus from transaction verification and execution is an
i...
With the advent of convolutional neural networks, stereo matching algori...
This paper proposes a simple baseline framework for video-based 2D/3D hu...
In this paper, we introduce VCSL (Video Copy Segment Localization), a ne...