In general, videos are powerful at recording physical patterns (eg, spatial layout) while texts
are great at describing abstract symbols (eg, emotion). When video and text are used in …

Dynamic expression recognition in the wild is a challenging task due to various obstacles,
including low light condition, non-positive face, and face occlusion. Purely vision-based …

With the increasing number of remote sensing ship images, it's vitally important to search for
the ship objects that users are interested in from the remote sensing image big data. The …

With the large chunks of social media data being created daily and the parallel rise of
realistic multimedia tampering methods, detecting and localising tampering in images and …

Image-text matching is a fundamental task to bridge vision and language. The critical
challenge lies in accurately learning the semantic similarity between these two …

We present a framework for learning cross-modal video representations by directly pre-
training on raw data to facilitate various downstream video-text tasks. Our main contributions …

Video data refers to digital information in the form of a series of frames or images
representing continuous motion captured by a video recording device. In various domains …

Due to high labeling cost, it is inevitable to introduce a certain proportion of noisy
correspondence into visual-text datasets, resulting in poor model robustness for cross-modal …

Understanding human intentions (eg, emotions) from videos has received considerable
attention recently. Video streams generally constitute a blend of temporal data stemming …

Prompt tuning, an emerging parameter-efficient strategy, leverages the powerful knowledge
of large-scale pre-trained image-text models (eg, CLIP) to swiftly adapt to downstream tasks …