Safcar: Structured attention fusion for compositional action recognition

Tae Soo Kim, Gregory D. Hager

Research output: Contribution to journalArticlepeer-review

Abstract

We present a general framework for compositional action recognition – i.e. action recognition where the labels are composed out of simpler components such as subjects, atomic-actions and objects. The main challenge in compositional action recognition is that there is a combinatorially large set of possible actions that can be composed using basic components. However, compositionality also provides a structure that can be exploited. To do so, we develop and test a novel Structured Attention Fusion (SAF) self-attention mechanism to combine information from object detections, which capture the time-series structure of an action, with visual cues that capture contextual information. We show that our approach recognizes novel verb-noun compositions more effectively than current state of the art systems, and it generalizes to unseen action categories quite efficiently from only a few labeled examples. We validate our approach on the challenging Something-Else tasks from the Something-Something-V2 dataset. We further show that our framework is flexible and can generalize to a new domain by showing competitive results on the Charades-Fewshot dataset.

Original languageEnglish (US)
JournalUnknown Journal
StatePublished - Dec 3 2020

ASJC Scopus subject areas

  • General

Fingerprint Dive into the research topics of 'Safcar: Structured attention fusion for compositional action recognition'. Together they form a unique fingerprint.

Cite this