Learning to Recognize Actions on Objects in Egocentric Video with Attention Dictionaries

Swathikiran Sudhakaran, Sergio Escalera, Oswald Lanz

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

6 Citationer (Scopus)

Abstract

We present EgoACO, a deep neural architecture for video action recognition that learns to pool action-context-object descriptors from frame level features by leveraging the verb-noun structure of action labels in egocentric video datasets. The core component of EgoACO is class activation pooling (CAP), a differentiable pooling operation that combines ideas from bilinear pooling for fine-grained recognition and from feature learning for discriminative localization. CAP uses self-attention with a dictionary of learnable weights to pool from the most relevant feature regions. Through CAP, EgoACO learns to decode object and scene context descriptors from video frame features. For temporal modeling in EgoACO, we design a recurrent version of class activation pooling termed Long Short-Term Attention (LSTA). LSTA extends convolutional gated LSTM with built-in spatial attention and a re-designed output gate. Action, object and context descriptors are fused by a multi-head prediction that accounts for the inter-dependencies between noun-verb-action structured labels in egocentric video datasets. EgoACO features built-in visual explanations, helping learning and interpretation. Results on the two largest egocentric action recognition datasets currently available, EPIC-KITCHENS and EGTEA, show that by explicitly decoding action-context-object descriptors, EgoACO achieves state-of-the-art recognition performance.

OriginalsprogEngelsk
TidsskriftIEEE Transactions on Pattern Analysis and Machine Intelligence
ISSN0162-8828
DOI
StatusAccepteret/In press - 2021
Udgivet eksterntJa

Bibliografisk note

Publisher Copyright:
IEEE

Fingeraftryk

Dyk ned i forskningsemnerne om 'Learning to Recognize Actions on Objects in Egocentric Video with Attention Dictionaries'. Sammen danner de et unikt fingeraftryk.

Citationsformater