Recognizing human activities from video sequences or still images is a challenging task due
to problems, such as background clutter, partial occlusion, changes in scale, viewpoint …

With the recent renaissance of deep convolutional neural networks (CNNs), encouraging
breakthroughs have been achieved on the supervised recognition tasks, where each class …

Pre-trained vision-language models (VLMs) learn to align vision and language
representations on large-scale datasets, where each image-text pair usually contains a bag …

Visual recognition is recently learned via either supervised learning on human-annotated
image-label data or language-image contrastive learning with webly-crawled image-text …

We aim at advancing open-vocabulary object detection, which detects objects described by
arbitrary text inputs. The fundamental challenge is the availability of training data. It is costly …

Zero-shot semantic segmentation (ZS3) aims to segment the novel categories that have not
been seen in the training. Existing works formulate ZS3 as a pixel-level zero-shot …

Most machine-learning methods focus on classifying instances whose classes have already
been seen in training. In practice, many applications require classifying instances whose …

When labeled training data is scarce, a promising data augmentation approach is to
generate visual features of unknown classes using their attributes. To learn the class …

Due to the importance of zero-shot learning, ie, classifying images where there is a lack of
labeled training data, the number of proposed approaches has recently increased steadily …

We consider the problem of zero-shot recognition: learning a visual classifier for a category
with zero training examples, just using the word embedding of the category and its …