×
We define an Event Recognition Language (ERL) which allows the users to define the events of interest conveniently without interacting with the low level ...
This hierarchical event representation naturally leads to a language description of the events. We define an Event Recognition Language (ERL) which allows the ...
The events are abstracted into three hierarchies. Primitive events are defined directly from the mobile object properties. Single-thread composite events are a ...
The events are abstracted into three hierarchies. Primitive events are defined directly from the mobile object properties. Single-thread composite events are a ...
This paper describes a probabilistic framework for uncertainty handling in a description-based event recognition approach. The proposed approach allows the ...
Instead of using pure textual terms for annotation, Davis et al. [30] present an iconic vi- sual language-based video annotation system, Media Stream, which ...
Dec 1, 2023 · The event hierarchy is constructed by detecting prediction error peaks at different levels, where a detected boundary triggers a bottom-up ...
In this paper, we propose a novel representation of events in videos to bridge this gap, based on the CASE representation of natural languages. The proposed rep ...
It is able to effectively learn both the global and fine-grained representations for better alignment between visual and textual features. • We design a multi- ...
As an essential subfield, video-language representation learning aims to understand the relationship between videos and their asso- ciated textual descriptions.