4 accepted papers
We introduce spatio-temporal omni-object video grounding, dubbed $\textbf{OmniSTVG}$, a new STVG task aiming to localize spatially and temporally all targets mentioned in the textual query within videos. Compared to classic STVG locating only a single target, OmniSTVG enables localization of not onl…
"Current multi-object tracking (MOT) aims to predict trajectories of targets (, “where”) in videos. Yet, knowing merely “where” is insufficient in many crucial applications. In comparison, semantic understanding such as fine-grained behaviors, interactions, and overall summarized captions (, “what”)…
Phones are critical components in various computational linguistic fields, for example, phone distributions could be helpful in speech recognition and speech synthesis. Traditional approaches to estimate phone distributions typically involve G2P systems which are either manually designed by linguist…
Multilingual models can improve language processing, particularly for low resource situations, by sharing parameters across languages. Multilingual acoustic models, however, generally ignore the difference between phonemes (sounds that can support lexical contrasts in a particular language) and thei…