Audio-visual zero-shot learning aims to classify samples consisting of a...
Hyperbolic geometry, a Riemannian manifold endowed with constant section...
Scene text image super-resolution (STISR) aims to simultaneously increas...
This paper studies the problem of measuring and predicting how memorable...
Current NLP techniques have been greatly applied in different domains. I...
Learning a latent embedding to understand the underlying nature of data
...
This work studies the joint rain and haze removal problem. In real-life
...
In this paper, we present and study a new image segmentation task, calle...
Automated real-time evaluation of counselor-client interaction is import...
We present You Only Cut Once (YOCO) for performing data augmentations. Y...
Learning and generalizing to novel concepts with few samples (Few-Shot
L...
Learning and generalizing from limited examples, i,e, few-shot learning,...
The explanation for deep neural networks has drawn extensive attention i...
We present and study a novel task named Blind Image Decomposition (BID),...
Few-shot class incremental learning (FSCIL) portrays the problem of lear...
Modern video person re-identification (re-ID) machines are often trained...
Full attention, which generates an attention value per element of the in...
Deep neural networks need to make robust inference in the presence of
oc...