What Would You Expect? Anticipating Egocentric Actions with Rolling-Unrolling LSTMs and Modality Attention

Egocentric action anticipation consists in understanding which objects the camera wearer will interact with in the near future and which actions they will perform. We tackle the problem proposing an architecture able to anticipate actions at multiple temporal scales using two LSTMs to 1) summarize the past, and 2) formulate predictions about the future. The input video is processed considering three complimentary modalities: appearance (RGB), motion (optical flow) and objects (object-based features). Modality-specific predictions are fused using a novel Modality ATTention (MATT) mechanism which learns to weigh modalities in an adaptive fashion. Extensive evaluations on two large-scale benchmark datasets show that our method outperforms prior art by up to +7% on the challenging EPIC-Kitchens dataset including more than 2500 actions, and generalizes to EGTEA Gaze+. Our approach is also shown to generalize to the tasks of early action recognition and action recognition. Our method is ranked first in the public leaderboard of the EPIC-Kitchens egocentric action anticipation challenge 2019. Please see our web pages for code and examples: http://iplab.dmi.unict.it/rulstm - https://github.com/fpv-iplab/rulstm.

PDF Abstract ICCV 2019 PDF ICCV 2019 Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Egocentric Activity Recognition EPIC-KITCHENS-55 RULSTM Actions Top-1 (S2) 19.49 # 4
Actions Top-1 (S1) 33.06 # 3

Results from Other Papers


Task Dataset Model Metric Name Metric Value Rank Source Paper Compare
Action Anticipation EPIC-KITCHENS-55 (Seen test set (S1)) RULSTM [24, 23] Top 1 Accuracy - Verb 33.04 # 3
Top 1 Accuracy - Noun 22.78 # 2
Top 1 Accuracy - Act. 14.39 # 3
Top 5 Accuracy - Verb 79.55 # 3
Top 5 Accuracy - Noun 50.95 # 3
Top 5 Accuracy - Act. 33.73 # 3
Action Anticipation EPIC-KITCHENS-55 (Unseen test set (S2) RULSTM [24, 23] Top 1 Accuracy - Verb 27.01 # 3
Top 1 Accuracy - Noun 15.19 # 3
Top 1 Accuracy - Act. 8.16 # 3
Top 5 Accuracy - Verb 69.55 # 3
Top 5 Accuracy - Noun 34.38 # 3
Top 5 Accuracy - Act. 21.10 # 3

Methods


No methods listed for this paper. Add relevant methods here