Computer vision (CV), a non-intrusive and cost-effective technology, has...
Based on the weight-sharing mechanism, one-shot NAS methods train a supe...
Large language models (LLMs), such as ChatGPT, are able to generate
huma...
In autonomous driving, the novel objects and lack of annotations challen...
Conventional clustering methods based on pairwise affinity usually suffe...
We introduce a lightweight network to improve descriptors of keypoints w...
We are interested in the problem of learning the directed acyclic graph ...
Deep neural networks (DNNs) have demonstrated their great potential in r...
For current object detectors, the scale of the receptive field of featur...
In this paper, we propose a novel deep learning architecture to improvin...
The task of multi-turn text-to-SQL semantic parsing aims to translate na...
In this paper, we propose a visual embedding approach to improving embed...
We present an improved version of PointRCNN for 3D object detection, in ...
Video prediction is a pixel-wise dense prediction task to infer future f...
We introduce a novel single-shot object detector to ease the imbalance o...
Clustering aims to separate observed data into different categories. The...
Sophisticated attackers find bugs in software, evaluate their exploitabi...
With pervasive applications of medical imaging in health-care, biomedica...
In this paper, we propose commonsense knowledge enhanced embeddings (KEE...
In this paper, we propose a new deep learning approach, called neural
as...
This paper proposes a model to learn word embeddings with weighted conte...
In this paper, we propose a novel neural network structure, namely
feedf...