Real-world data often have a long-tailed distribution, where the number ...
Deep neural networks (DNN) have been proved for its effectiveness in var...
We present a new paradigm named explore-and-match for video grounding, w...
Few-shot learning often involves metric learning-based classifiers, whic...
In this paper, we attack a few-shot open-set recognition (FSOSR) problem...
Although supervised person re-identification (Re-ID) methods have shown
...
To learn target discriminative representations, using pseudo-labels is a...
We introduce a novel unsupervised domain adaptation approach for object
...
We introduce a large-scale 3D shape understanding benchmark using data a...