Deep neural networks have exhibited promising performance in image super-resolution
(SR) by learning a nonlinear map** function from low-resolution (LR) images to high …

For person re-identification (re-id), attention mechanisms have become attractive as they
aim at strengthening discriminative features and suppressing irrelevant ones, which …

We address the problem of video grounding from natural language queries. The key
challenge in this task is that one training video might only contain a few annotated …

To understand human behaviors, action recognition based on videos is a common
approach. Compared with image-based action recognition, videos provide much more …

Open-world object detection (OWOD), as a more general and challenging goal, requires the
model trained from data on known objects to detect both known and unknown objects and …

The temporal action localization research aims to discover action instances from untrimmed
videos, representing a fundamental step in the field of intelligent video understanding. With …

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 …

Online action detection has attracted increasing research interests in recent years. Current
works model historical dependencies and anticipate the future to perceive the action …

Action localization networks are often structured as a feature encoder sub-network and a
localization sub-network, where the feature encoder learns to transform an input video to …

How to learn discriminative video representation from unlabeled videos is challenging but
crucial for video analysis. The latest attempts seek to learn a representation model by …