Unsupervised sentence representation learning aims to transform input
se...
Sparse Mixture-of-Experts models (MoEs) have recently gained popularity ...
Large language models (LLMs) have shown remarkable capacity for in-conte...
Stance detection predicts attitudes towards targets in texts and has gai...
Human models play a crucial role in human-robot interaction (HRI), enabl...
Heterogeneous graphs offer powerful data representations for traffic, gi...
State-of-the-art video-text retrieval (VTR) methods usually fully fine-t...
Separation logic and its variants can describe various properties on poi...
Stance detection refers to the task of extracting the standpoint (Favor,...
The quality and size of training sets often limit the performance of man...
In this work, we focus on the problem of safe policy transfer in
reinfor...
Recent studies have shown that the benefits provided by self-supervised
...
Each year, underwater remotely operated vehicles (ROVs) collect thousand...
Deep learning has been widely adopted for channel state information
(CSI...
Retinal implants have the potential to treat incurable blindness, yet th...
Despite the tantalizing success in a broad of vision tasks, transformers...
The long-tailed class distribution in visual recognition tasks poses gre...
In learning action recognition, models are typically pre-trained on obje...
The recently proposed FixMatch achieved state-of-the-art results on most...
We investigate ways to compose complex concepts in texts from primitive ...
We analyze the grounded SCAN (gSCAN) benchmark, which was recently propo...
Hyperspectral (HS) images contain detailed spectral information that has...
Clinical case reports are written descriptions of the unique aspects of ...
We propose a simple yet effective framework for instance and panoptic
se...
Identifying a short segment in a long video that semantically matches a ...
We formulate the problem of online temporal action detection in live
str...
Learning to fuse vision and language information and representing them i...
Adversarial examples represent a great security threat for deep learning...
As the indispensable trading platforms of the ecosystem, hundreds of
cry...
A driver's gaze is critical for determining the driver's attention level...
We propose a learning model for the task of visual storytelling. The mai...
In this paper, we study the vulnerability of anti-spoofing methods based...
Convolutional neural networks require numerous data for training. Consid...
Steady progress has been made in abstractive summarization with
attentio...
Owing to the massive growth in the storage demands of big data, Cloud St...
Web parameter injection attacks are common and powerful. In this kind of...
Visual data and text data are composed of information at multiple
granul...
Deep learning has made remarkable achievement in many fields. However,
l...
Traditional feature encoding scheme (e.g., Fisher vector) with local
des...
This paper presents the method that underlies our submission to the untr...
The deep two-stream architecture exhibited excellent performance on vide...