Argus++: Robust Real-time Activity Detection for Unconstrained Video Streams with Overlapping Cube Proposals
This addresses the need for efficient activity detection in surveillance and driving scenarios, though it appears incremental as it builds on existing proposal-based methods with optimizations for real-time processing.
The authors tackled the problem of real-time activity detection in unconstrained video streams, which are untrimmed and have large fields-of-view, by proposing Argus++, a system that uses overlapping spatio-temporal cubes for robust detection and achieves superior performance on multiple benchmarks like ActivityNet ActEV 2021 and TRECVID ActEV 2020/2021.
Activity detection is one of the attractive computer vision tasks to exploit the video streams captured by widely installed cameras. Although achieving impressive performance, conventional activity detection algorithms are usually designed under certain constraints, such as using trimmed and/or object-centered video clips as inputs. Therefore, they failed to deal with the multi-scale multi-instance cases in real-world unconstrained video streams, which are untrimmed and have large field-of-views. Real-time requirements for streaming analysis also mark brute force expansion of them unfeasible. To overcome these issues, we propose Argus++, a robust real-time activity detection system for analyzing unconstrained video streams. The design of Argus++ introduces overlapping spatio-temporal cubes as an intermediate concept of activity proposals to ensure coverage and completeness of activity detection through over-sampling. The overall system is optimized for real-time processing on standalone consumer-level hardware. Extensive experiments on different surveillance and driving scenarios demonstrated its superior performance in a series of activity detection benchmarks, including CVPR ActivityNet ActEV 2021, NIST ActEV SDL UF/KF, TRECVID ActEV 2020/2021, and ICCV ROAD 2021.