Recent advances in 2D zero-shot and few-shot recognition often leverage ...
Object-centric learning aims to represent visual data with a set of obje...
We introduce Breaking Bad, a large-scale dataset of fractured objects. O...
Recent advances in deep learning significantly boost the performance of
...
Accurate inference of fine-grained traffic flow from coarse-grained one ...
In this paper, we propose an instance similarity learning (ISL) method f...
Metro origin-destination prediction is a crucial yet challenging task fo...
Point cloud is an important 3D data representation widely used in many
e...
In this paper, we propose a binarized neural network learning method cal...
In this paper, we propose a novel heart segmentation pipeline Combining
...