Online Action Representation using Change Detection and Symbolic Programming
Vishnu S Nair, Sneha Sree, Jayaraj Joseph, Mohanasankar Sivaprakasam

TL;DR
This paper introduces an online action representation method that uses change detection and symbolic programming to segment, interpret, and count repetitions of human actions in streaming videos, outperforming some existing offline methods.
Contribution
It presents a novel online approach combining change detection and symbolic primitives for action segmentation and interpretation, enabling real-time repetition counting.
Findings
Effective online segmentation of actions using change detection.
Higher-level semantic representation through symbolic primitives.
Competitive or superior performance compared to offline methods.
Abstract
This paper addresses the critical need for online action representation, which is essential for various applications like rehabilitation, surveillance, etc. The task can be defined as representation of actions as soon as they happen in a streaming video without access to video frames in the future. Most of the existing methods use predefined window sizes for video segments, which is a restrictive assumption on the dynamics. The proposed method employs a change detection algorithm to automatically segment action sequences, which form meaningful sub-actions and subsequently fit symbolic generative motion programs to the clipped segments. We determine the start time and end time of segments using change detection followed by a piece-wise linear fit algorithm on joint angle and bone length sequences. Domain-specific symbolic primitives are fit to pose keypoint trajectories of those…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTime Series Analysis and Forecasting · Artificial Intelligence in Games
