Image steganography is the art of concealing secret information in image...
As AI systems have obtained significant performance to be deployed widel...
Recent advancements in recommendation systems have shifted towards more
...
Recommendation systems aim to provide users with relevant suggestions, b...
Structural re-parameterization is a general training scheme for Convolut...
RAW files are the initial measurement of scene radiance widely used in m...
The widespread use of face retouching filters on short-video platforms h...
In this study, we introduce PharmacyGPT, a novel framework to assess the...
With the widespread applications of the deep neural network (DNN), how t...
This paper explores new frontiers in agricultural natural language proce...
We present a new task, speech dialogue translation mediating speakers of...
Generative steganography (GS) is a new data hiding manner, featuring dir...
Generative steganography (GS) is an emerging technique that generates st...
Recently, the Segment Anything Model (SAM) has gained significant attent...
Artificial general intelligence (AGI) has gained global recognition as a...
Recent advancements in foundation models (FMs), such as GPT-4 and LLaMA,...
Artificial General Intelligence (AGI) is poised to revolutionize a varie...
In response to innovations in machine learning (ML) models, production
w...
Existing video recognition algorithms always conduct different training
...
The era of big data has witnessed an increasing availability of observat...
Steganography is a technique for covert communication between two partie...
Federated learning is a technique that enables a centralized server to l...
Tackling unfairness in graph learning models is a challenging task, as t...
Anomaly detection and localization of visual data, including images and
...
Causal inference has numerous real-world applications in many domains, s...
A further understanding of cause and effect within observational data is...
Wild images on the web are vulnerable to backdoor (also called trojan)
p...
Face manipulation detection has been receiving a lot of attention for th...
The pretraining-finetuning paradigm has demonstrated great success in NL...
Local clustering problem aims at extracting a small local structure insi...
To let the state-of-the-art end-to-end ASR model enjoy data efficiency, ...
Digital images are vulnerable to nefarious tampering attacks such as con...
Recently, sparse training has emerged as a promising paradigm for effici...
Marketing campaigns are a set of strategic activities that can promote a...
Steganography usually modifies cover media to embed secret data. A new
s...
Online social networks have stimulated communications over the Internet ...
Videos are prone to tampering attacks that alter the meaning and deceive...
Edge computing is a popular target for accelerating machine learning
alg...
Artificial neural networks (ANNs), originally inspired by biological neu...
Image cropping is an inexpensive and effective operation of maliciously
...
Videos can be easily tampered, copied and redistributed by attackers for...
Multimodal fake news detection has attracted many research interests in
...
We participated in the mean opinion score (MOS) prediction challenge, 20...
Low resource speech recognition has been long-suffering from insufficien...
Estimating treatment effects from observational data provides insights a...
The foremost challenge to causal inference with real-world data is to ha...
Deep learning has achieved enormous success in various industrial
applic...
Action prediction aims to infer the forthcoming human action with
partia...
Accurate and efficient point cloud registration is a challenge because t...
Face anonymization with generative models have become increasingly preva...