This paper presents an approach to detect out-of-context (OOC) objects i...
In this technical report, we present our approaches for the continual ob...
Humans can incrementally learn to do new visual detection tasks, which i...
In lifelong machine learning, a robotic agent must be incrementally upda...
Accurate eye segmentation can improve eye-gaze estimation and support
in...
We propose Visual Query Detection (VQD), a new visual grounding task. In...
Most counting questions in visual question answering (VQA) datasets are
...