For robots to be generally useful, they must be able to find arbitrary objects described by
people (ie, be language-driven) even without expensive navigation training on in-domain …

In this paper, we consider the problem of simultaneously detecting objects and inferring their
visual attributes in an image, even for those with no manual annotations provided at the …

Object detection has achieved a huge breakthrough with deep neural networks and massive
annotated data. However, current detection methods cannot be directly transferred to the …

With the emergence of foundation models, deep learning-based object detectors have
shown practical usability in closed set scenarios. However, for real-world tasks, object …

Video anomaly detection (VAD) under weak supervision aims to temporally locate abnormal
clips using the easy-to-obtain video-level labels. In this brief, we introduce the underlying …

Zero-shot object detection aims to localize and recognize objects of unseen classes. Most of
existing works face two problems: the low recall of RPN in unseen classes and the confusion …

Weakly Supervised Anomaly Detection (WSAD) in surveillance videos is a complex task
since usually only video-level annotations are available. Previous work treated it as a …

The success of large-scale contextual language models has attracted great interest in
probing what is encoded in their representations. In this work, we consider a new question …

Zero-shot detection (ZSD) is a challenging task where we aim to recognize and localize
objects simultaneously, even when our model has not been trained with visual samples of a …

Object detection with weak annotations has attracted much attention recently. Weakly
supervised object detection (WSOD) methods which only use image-level labels to train a …