AI Paper Atlas

Research map / Video / Action recognition

Action Sequence Augmentation for Action Anticipation

Yihui Qiu, Deepu Rajan

ICLR 2025 · Video › Action recognition · approach: Action anticipation and latent actions

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes augmenting training action sequences to improve action anticipation models by covering action orderings absent from datasets.

Problem

Action anticipation models must predict future actions from past events, but datasets contain only a subset of the vast space of possible action sequences (flexible ordering and interleaved goals), creating an ordering bias.

Approach

Augment training data with synthetic action sequences that cover plausible orderings and goal interleavings not present in the original datasets, to reduce reliance on observed ordering patterns.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy