Vision-language models (VLMs) pre-trained on large-scale image-text pairs have
demonstrated impressive transferability on various visual tasks. Transferring knowledge …

Transferring knowledge from task-agnostic pre-trained deep models for downstream tasks is
an important topic in computer vision research. Along with the growth of computational …

As an important yet challenging task in Earth observation, change detection (CD) is
undergoing a technological revolution, given the broadening application of deep learning …

We study unsupervised video representation learning that seeks to learn both motion and
appearance features from unlabeled video only, which can be reused for downstream tasks …

Transferring knowledge from pre-trained deep models for downstream tasks, particularly
with limited labeled samples, is a fundamental problem in computer vision research. Recent …

Few-shot classification is a promising approach to solving the problem of classifying novel
classes with only limited annotated data for training. Existing methods based on meta …

Frame sampling is a fundamental problem in video action recognition due to the essential
redundancy in time and limited computation resources. The existing sampling strategy often …

Currently, efficient spatio-temporal information modeling is one of the key research
components to solve the action recognition problem. Previous approaches focus on …

We study self-supervised video representation learning, which is a challenging task due to
1) sufficient labels for supervision; 2) unstructured and noisy visual information. Existing …

Video action recognition is a fundamental task for video understanding. Action recognition in
complex spatio-temporal contexts generally requires fusing of different multi-granularity …