# InfoGCN++: Learning Representation by Predicting the Future for Online Human Skeleton-based Action Recognition Source: [InfoGCN++: Learning Representation by Predicting the Future for Online Human Skeleton-based Action Recognition]() Collection index: [llms.txt]() Data updated: 2025-10-27T06:41:59.710Z Authors: Seunggeun Chi, Hyung-gun Chi, Qixing Huang, Karthik Ramani Published: 2023-10-16T16:15:11.000Z ## Abstract Skeleton-based action recognition has made significant advancements recently, with models like InfoGCN showcasing remarkable accuracy. However, these models exhibit a key limitation: they necessitate complete action observation prior to classification, which constrains their applicability in real-time situations such as surveillance and robotic systems. To overcome this barrier, we introduce InfoGCN++, an innovative extension of InfoGCN, explicitly developed for online skeleton-based action recognition. InfoGCN++ augments the abilities of the original InfoGCN model by allowing real-time categorization of action types, independent of the observation sequence's length. It transcends conventional approaches by learning from current and anticipated future movements, thereby creating a more thorough representation of the entire sequence. Our approach to prediction is managed as an extrapolation issue, grounded on observed actions. To enable this, InfoGCN++ incorporates Neural Ordinary Differential Equations, a concept that lets it effectively model the continuous evolution of hidden states. Following rigorous evaluations on three skeleton-based action recognition benchmarks, InfoGCN++ demonstrates exceptional performance in online action recognition. It consistently equals or exceeds existing techniques, highlighting its significant potential to reshape the landscape of real-time action recognition applications. Consequently, this work represents a major leap forward from InfoGCN, pushing the limits of what's possible in online, skeleton-based action recognition. The code for InfoGCN++ is publicly available at https://github.com/stnoah1/infogcn2 for further exploration and validation. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Non-verbal body pose communication (classification + generation) on Non-verbal body pose communication dataset (test)](): Non-verbal body pose communication (classification + generation); Non-verbal body pose communication dataset (test); Latency (ms): 10.925. - [Action Recognition on BABEL 25% OR](): Action Recognition; BABEL 25% OR; Accuracy: 44.51. - [Action Recognition on BABEL 100% OR](): Action Recognition; BABEL 100% OR; Accuracy: 55.96. - [Action Recognition on BABEL 75% OR](): Action Recognition; BABEL 75% OR; Accuracy: 55.22. - [Action Recognition on BABEL 50% OR](): Action Recognition; BABEL 50% OR; Accuracy: 49.22. ## Original sources and implementation [Original paper]() [PDF]()