Action Sequence Augmentation for Action Anticipation

Yihui Qiu, Deepu Rajan

Keywords: Sequence Augmentation, Action Anticipation, Context-free Grammar

Abstract: Action anticipation models require an understanding of temporal action patterns and dependencies to predict future actions from previous events. The key challenges arise from the vast number of possible action sequences, given the flexibility in action ordering and the interleaving of multiple goals. Since only a subset of such action sequences are present in action anticipation datasets, there is an inherent ordering bias in them. Another challenge is the presence of noisy input to the models due to erroneous action recognition or other upstream tasks. This paper addresses these challenges by introducing a novel data augmentation strategy that separately augments observed action sequences and next actions. To address biased action ordering, we introduce a grammar induction algorithm that derives a powerful context-free grammar from action sequence data. We also develop an efficient parser to generate plausible next-action candidates beyond the ground truth. For noisy input, we enhance model robustness by randomly deleting or replacing actions in observed sequences. Our experiments on the 50Salads, EGTEA Gaze+, and Epic-Kitchens-100 datasets demonstrate significant performance improvements over existing state-of-the-art methods.

Primary Area: applications to computer vision, audio, language, and other modalities

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 3512