We propose a novel unsupervised object localization method that allows u...
Contrastive Language-Image Pre-training (CLIP) stands as one of the most...
Loss of packets in video conferencing often results in poor quality and ...
Machine learning models often perform poorly on subgroups that are
under...
Generative modeling and representation learning are two key tasks in com...
Real-world data often exhibit imbalanced label distributions. Existing
s...
Indiscriminate data poisoning attacks are quite effective against superv...
The ability to generalize learned representations across significantly
d...
Real-world data often exhibit imbalanced distributions, where certain ta...
This paper aims to caption daily life –i.e., to create a textual descrip...
Existing domain adaptation focuses on transferring knowledge between dom...
Person Re-Identification (ReID) aims to recognize a person-of-interest a...
Finding an embedding space for a linear approximation of a nonlinear
dyn...
Value-based methods constitute a fundamental methodology in planning and...
Understanding people's actions and interactions typically depends on see...
Deep neural networks are vulnerable to adversarial attacks. The literatu...
We consider the problem of inferring the values of an arbitrary set of
v...