Predicting the Next Action by Modeling the Abstract Goal

12 Sep 2022  ·  Debaditya Roy, Basura Fernando ·

The problem of anticipating human actions is an inherently uncertain one. However, we can reduce this uncertainty if we have a sense of the goal that the actor is trying to achieve. Here, we present an action anticipation model that leverages goal information for the purpose of reducing the uncertainty in future predictions. Since we do not possess goal information or the observed actions during inference, we resort to visual representation to encapsulate information about both actions and goals. Through this, we derive a novel concept called abstract goal which is conditioned on observed sequences of visual features for action anticipation. We design the abstract goal as a distribution whose parameters are estimated using a variational recurrent network. We sample multiple candidates for the next action and introduce a goal consistency measure to determine the best candidate that follows from the abstract goal. Our method obtains impressive results on the very challenging Epic-Kitchens55 (EK55), EK100, and EGTEA Gaze+ datasets. We obtain absolute improvements of +13.69, +11.24, and +5.19 for Top-1 verb, Top-1 noun, and Top-1 action anticipation accuracy respectively over prior state-of-the-art methods for seen kitchens (S1) of EK55. Similarly, we also obtain significant improvements in the unseen kitchens (S2) set for Top-1 verb (+10.75), noun (+5.84) and action (+2.87) anticipation. Similar trend is observed for EGTEA Gaze+ dataset, where absolute improvement of +9.9, +13.1 and +6.8 is obtained for noun, verb, and action anticipation. It is through the submission of this paper that our method is currently the new state-of-the-art for action anticipation in EK55 and EGTEA Gaze+ https://competitions.codalab.org/competitions/20071#results Code available at https://github.com/debadityaroy/Abstract_Goal

PDF Abstract
No code implementations yet. Submit your code now
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Action Anticipation EGTEA Abstract Goal Top-1 Accuracy 49.8 # 2
Action Anticipation EPIC-KITCHENS-100 (test) Abstract Goal recall@5 14.29 # 4
Action Anticipation EPIC-KITCHENS-55 (Seen test set (S1)) Abstract Goal Top 1 Accuracy - Verb 35.34 # 2
Top 1 Accuracy - Noun 51.56 # 1
Top 1 Accuracy - Act. 22.03 # 1
Top 5 Accuracy - Verb 82.56 # 1
Top 5 Accuracy - Noun 58.01 # 1
Top 5 Accuracy - Act. 38.29 # 1
Action Anticipation EPIC-KITCHENS-55 (Unseen test set (S2) Abstract Goal Top 1 Accuracy - Verb 41.41 # 1
Top 1 Accuracy - Noun 22.36 # 1
Top 1 Accuracy - Act. 13.28 # 1
Top 5 Accuracy - Verb 73.10 # 1
Top 5 Accuracy - Noun 41.62 # 1
Top 5 Accuracy - Act. 24.24 # 2

Methods


No methods listed for this paper. Add relevant methods here