Seeing What You're Told: Sentence-Guided Activity Recognition In Video
This work addresses the challenge of multi-modal integration between vision and language for video analysis, offering a novel framework for tasks like guided attention and search, though it appears incremental in combining existing concepts.
The paper tackles the problem of integrating compositional language structures with video activity recognition, demonstrating a system that uses sentence descriptions to guide attention, generate descriptions, and enable query-based search in multi-activity videos.
We present a system that demonstrates how the compositional structure of events, in concert with the compositional structure of language, can interplay with the underlying focusing mechanisms in video action recognition, thereby providing a medium, not only for top-down and bottom-up integration, but also for multi-modal integration between vision and language. We show how the roles played by participants (nouns), their characteristics (adjectives), the actions performed (verbs), the manner of such actions (adverbs), and changing spatial relations between participants (prepositions) in the form of whole sentential descriptions mediated by a grammar, guides the activity-recognition process. Further, the utility and expressiveness of our framework is demonstrated by performing three separate tasks in the domain of multi-activity videos: sentence-guided focus of attention, generation of sentential descriptions of video, and query-based video search, simply by leveraging the framework in different manners.