3D dense captioning requires a model to translate its understanding of a...
Unsupervised Domain Adaptation (UDA) is quite challenging due to the lar...
Deep learning methods have shown remarkable performance in image denoisi...
3D dense captioning aims to generate multiple captions localized with th...
Aspect Sentiment Triplet Extraction (ASTE) aims to extract the spans of
...
Deep models trained on source domain lack generalization when evaluated ...
Point cloud scene flow estimation is of practical importance for dynamic...
Learning dense point-wise semantics from unstructured 3D point clouds wi...
Learning from a sequence of tasks for a lifetime is essential for an age...
Unsupervised person re-identification (Re-ID) attracts increasing attent...
Humans' continual learning (CL) ability is closely related to Stability
...
Semantic segmentation is a crucial image understanding task, where each ...
Domain adaptation is critical for success when confronting with the lack...
Street Scene Change Detection (SSCD) aims to locate the changed regions
...
Recent studies try to build task-oriented dialogue system in an end-to-e...
Most existing crowd counting systems rely on the availability of the obj...
Most existing crowd counting methods require object location-level
annot...
Enabling a neural network to sequentially learn multiple tasks is of gre...
Distant Supervised Relation Extraction (DSRE) is usually formulated as a...
Recently, Fully Convolutional Network (FCN) seems to be the go-to
archit...
Semantic Scene Completion (SSC) aims to simultaneously predict the volum...
One key issue in managing a large scale 3D shape dataset is to identify ...