Current deep networks are very data-hungry and benefit from training on
...
Weakly supervised object localization (WSOL) remains challenging when
le...
Public large-scale text-to-image diffusion models, such as Stable Diffus...
Diffusion models have recently dominated image synthesis and other relat...
Collecting and annotating images with pixel-wise labels is time-consumin...
The insurance industry is shifting their sales mode from offline to onli...
Model binarization can significantly compress model size, reduce energy
...
Generally pre-training and long-time training computation are necessary ...
Binary neural network leverages the Sign function to binarize real value...
Data-free quantization is a task that compresses the neural network to l...
Recent video text spotting methods usually require the three-staged pipe...
While large scale pre-training has achieved great achievements in bridgi...
Although a polygon is a more accurate representation than an upright bou...
Deep learning-based scene text detection can achieve preferable performa...
Question Answering (QA) systems are used to provide proper responses to
...
In this paper, we propose a pixel-wise detector named TextCohesion for s...