Detecting stereotypes and biases in Large Language Models (LLMs) can enh...
Currently, most speaker recognition backends, such as cosine, linear
dis...
We present a pipeline for printing interactive and always-on magnetophor...
EduChat (https://www.educhat.top/) is a large-scale language model
(LLM)...
In recent years, personality has been regarded as a valuable personal fa...
Existing offboard 3D detectors always follow a modular pipeline design t...
The actuation of a soft robot involves transforming its shape from an in...
Large language models have demonstrated remarkable performance across va...
Recently, making recommendations for ephemeral groups which contain dyna...
To benefit the complementary information between heterogeneous data, we
...
Theory of Mind (ToM) is the ability to attribute mental states to others...
We present a lightweight, decentralized algorithm for navigating multipl...
LiDAR-camera fusion methods have shown impressive performance in 3D obje...
Gradient-based explanation methods play an important role in the field o...
The deep learning models used for speaker verification are heavily depen...
Sequential Recommendation is a prominent topic in current research, whic...
Multi-modal 3D object detection has been an active research topic in
aut...
This paper presents the system description of the THUEE team for the NIS...
Unsupervised sentence embeddings learning has been recently dominated by...
Event argument extraction (EAE) aims to extract arguments with given rol...
Speech emotion recognition (SER) is an essential part of human-computer
...
Sound event detection (SED) is an interesting but challenging task due t...
Structured sentiment analysis, which aims to extract the complex semanti...
Previous studies about event-level sentiment analysis (SA) usually model...
Implicit event argument extraction (EAE) aims to identify arguments that...
Recent years have witnessed the progress of sequential recommendation in...
Visual grounding focuses on establishing fine-grained alignment between
...
Nowadays, with the explosive growth of multimodal reviews on social medi...
The document layout analysis (DLA) aims to decompose document images int...
Accurate prediction in session-based recommendation has achieved progres...
Understanding protein sequences is vital and urgent for biology, healthc...
The identification of active binding drugs for target proteins (termed a...
Inferring the substitutable and complementary products for a given produ...
Although research studies in pneumatic soft robots develop rapidly, most...
Document layout analysis (DLA) aims to divide a document image into diff...
Human-in-the-loop aims to train an accurate prediction model with minimu...
The document layout analysis (DLA) aims to split the document image into...
Cross-prompt automated essay scoring (AES) requires the system to use no...
This paper describes our system for SemEval-2020 Task 4: Commonsense
Val...
In recent years, knowledge graph embedding becomes a pretty hot research...
We present an algorithm for homogeneous, labeled, and disk-shaped multi-...
Automatic analysis of highly crowded people has attracted extensive atte...
This paper describes the systems submitted by the department of electron...
The accuracy of OCR is usually affected by the quality of the input docu...
The goal of acoustic (or sound) events detection (AED or SED) is to pred...
Texts from scene images typically consist of several characters and exhi...
Image deblurring is a fundamental and challenging low-level vision probl...
Crowd counting aims to count the number of instantaneous people in a cro...
In neural network based speaker verification, speaker embedding is expec...
Attention mechanism has been widely applied to various sound-related tas...