Recently, MLP-based vision backbones have achieved promising performance...
This paper proposes a hybrid radiance field representation for unbounded...
Mobile task automation is an attractive technique that aims to enable
vo...
Applications that could benefit from automatic understanding of human-hu...
The recently proposed segment anything model (SAM) has made a significan...
Attention networks such as transformers have achieved state-of-the-art
p...
Hyperbolic space has been shown to produce superior low-dimensional
embe...
While large language models (LLMs) bring not only performance but also
c...
Face reenactment methods attempt to restore and re-animate portrait vide...
The neural radiance field (NeRF) achieved remarkable success in modeling...
Detailed 3D reconstruction and photo-realistic relighting of digital hum...
Modern image inpainting systems, despite the significant progress, often...
Background subtraction (BGS) aims to extract all moving objects in the v...
Graph neural networks (GNNs) have emerged as the state-of-the-art paradi...
This paper introduces the Unbeatable Team's submission to the ICASSP 202...
Large pretrained language models (LMs) have shown impressive In-Context
...
Performing inference on hundreds of thousands of samples with large lang...
We propose to realize visual cryptography in an indirect way with the he...
Sampling diverse programs from a code language model and reranking with ...
Large-scale vision-language models (VLMs) pre-trained on billion-level d...
FullSubNet has shown its promising performance on speech enhancement by
...
One of the key enablers for the realization of a variety of unmanned aer...
Recently, dataset-generation-based zero-shot learning has shown promisin...
The task of context-dependent text-to-SQL aims to convert multi-turn use...
Though end-to-end neural approaches have recently been dominating NLP ta...
Channel estimation and transmission constitute the most fundamental
func...
We develop NL2INTERFACE to explore the potential of generating usable
in...
As a core performance metric for green communications, the conventional
...
In this paper, we introduce MCTensor, a library based on PyTorch for
pro...
Single-image human relighting aims to relight a target human under new
l...
Multiple testing has been a popular topic in statistical research. Altho...
This paper studies distributed diffusion adaptation over clustered multi...
Image compression has raised widespread interest recently due to its
sig...
Predicting human motion is critical for assistive robots and AR/VR
appli...
Existing state-of-the-art novel view synthesis methods rely on either fa...
It is extremely challenging to create an animatable clothed human avatar...
Graph convolutional network (GCN) has achieved great success in single h...
Collecting and annotating task-oriented dialogues is time-consuming and
...
Light field disparity estimation is an essential task in computer vision...
There is a growing interest in dataset generation recently due to the
su...
Due to its geometric properties, hyperbolic space can support high-fidel...
Hyperdimensional computing (HDC) is an emerging learning paradigm that
c...
Augmented reality (AR) has drawn great attention in recent years. Howeve...
Unmanned aerial vehicles (UAVs)-based applications, such as surveillance...
UAV-based wireless systems, such as wireless relay and remote sensing, h...
A high performance multi-UAV communication system, which bridges multipl...
For deep reinforcement learning (RL) from pixels, learning effective sta...
In this paper, we introduce HDhuman, a method that addresses the challen...
We propose a novel neural rendering pipeline, Hybrid Volumetric-Textural...
In speech enhancement, complex neural network has shown promising perfor...