Although Deep Reinforcement Learning (DRL) has achieved notable success ...
Current diffusion-based image restoration methods feed degraded input im...
Prompt tuning and adapter tuning have shown great potential in transferr...
The explosive growth of rumors with text and images on social media plat...
Fine-tuning pre-trained language models (PLMs), e.g., SciBERT, generally...
Program synthesis has been long studied with recent approaches focused o...
Efficient inference for object detection networks is a major challenge o...
With the end of Moore's Law, there is a growing demand for rapid
archite...
Large-scale language models (LLMs) have demonstrated outstanding perform...
Abnormal event detection, which refers to mining unusual interactions am...
As a combination of visual and audio signals, video is inherently
multi-...
Post-training quantization (PTQ) is a popular method for compressing dee...
Recent years have witnessed huge successes in 3D object detection to
rec...
Deep Learning (DL) is prevalently used in various industries to improve
...
BACKGROUND: Recent neural language models have taken a significant step
...
As a neural network compression technique, post-training quantization (P...
Neural text ranking models have witnessed significant advancement and ar...
Deep-learning (DL) compilers such as TVM and TensorRT are increasingly u...
The algorithms of one-shot neural architecture search(NAS) have been wid...
Fake news spreads at an unprecedented speed, reaches global audiences an...
Federated learning (FL) has been proposed as a popular learning framewor...
RGB-infrared person re-identification is an emerging cross-modality
re-i...
Generalizable person re-identification aims to learn a model with only
s...
Existing disentangled-based methods for generalizable person
re-identifi...
Despite the fact that deep neural networks (DNNs) have achieved prominen...
Chatbot is increasingly thriving in different domains, however, because ...
Estimating human pose is an important yet challenging task in multimedia...
A graph is an abstract model that represents relations among entities, f...
Occluded person re-identification (ReID) aims to match person images wit...
Confidence-aware learning is proven as an effective solution to prevent
...
Although existing person re-identification (Re-ID) methods have shown
im...
Video-based person re-identification aims to match pedestrians from vide...
Compared with expensive pixel-wise annotations, image-level labels make ...
Semi-supervised learning on graphs is an important problem in the machin...
Is chatbot able to completely replace the human agent? The short answer ...
In the computer-aided diagnosis of cervical precancerous lesions, it is
...
Video-based person re-identification aims to match a specific pedestrian...
Most of existing clustering algorithms are proposed without considering ...
We present a spectral co-design of a statistical
multiple-input-multiple...
Regular expression is important for many natural language processing tas...
Person re-identification aims at identifying a certain pedestrian across...
Current state-of-art feature-engineered and end-to-end Automated Essay S...
Person re-identification aims to identify the same pedestrian across
non...
We are in the dawn of deep learning explosion for smartphones. To bridge...
Deep learning (DL) is a game-changing technique in mobile scenarios, as
...
In this paper, we propose three novel models to enhance word embedding b...