The ability to decompose complex natural scenes into meaningful object-centric abstractions
lies at the core of human perception and reasoning. In the recent culmination of …

Contrastive learning has recently demonstrated great potential for unsupervised pre-training
in 3D scene understanding tasks. However, most existing work randomly selects point …

DETR-based object detectors have achieved remarkable performance but are sample-
inefficient and exhibit slow convergence. Unsupervised pretraining has been found to be …

Contrastive learning has recently demonstrated great potential for unsupervised pre-training
in 3D scene understanding tasks. However, most existing work randomly selects point …

Without accurate transcription of numerical data in scientific documents, a scientist cannot
draw accurate conclusions. Unfortunately, the process of copying numerical data from one …

Event understanding is one of the most fundamental problems in artificial intelligence and
computer vision. Rooted in the field of neuroscience, the study and analysis of human …

Recent progress in self-supervised representation learning has shown that self-supervised
pre-training can leverage unlabeled data to learn generalizable representations that benefit …

Object detectors are often trained by first training the backbone in a self-supervised manner
and then fine-tuning the whole model on annotated data. An unsupervised detector …