# Argus++: Robust Real-time Activity Detection for Unconstrained Video Streams with Overlapping Cube Proposals

arXiv: https://arxiv.org/abs/2201.05290 · HTML: https://mlsanity.com/paper/2201.05290/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 30 references that are in the map.
- First posted on arXiv 14 Jan 2022.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [A Closer Look at Spatiotemporal Convolutions for Action Recognition](https://mlsanity.com/paper/1711.11248/) (2017)
- [Simple Online and Realtime Tracking with a Deep Association Metric](https://mlsanity.com/paper/1703.07402/) (2017)
- [Temporal Segment Networks: Towards Good Practices for Deep Action Recognition](https://mlsanity.com/paper/1608.00859/) (2016)
- [TSM: Temporal Shift Module for Efficient Video Understanding](https://mlsanity.com/paper/1811.08383/) (2018)
- [X3D: Expanding Architectures for Efficient Video Recognition](https://mlsanity.com/paper/2004.04730/) (2020)
- [R-FCN: Object Detection via Region-based Fully Convolutional Networks](https://mlsanity.com/paper/1605.06409/) (2016)
- [Towards Real-Time Multi-Object Tracking](https://mlsanity.com/paper/1909.12605/) (2019)
- [Flow-Guided Feature Aggregation for Video Object Detection](https://mlsanity.com/paper/1703.10025/) (2017)
- [Large-scale weakly-supervised pre-training for video action recognition](https://mlsanity.com/paper/1905.00561/) (2019)
- [ROAD: The ROad event Awareness Dataset for Autonomous Driving](https://mlsanity.com/paper/2102.11585/) (2021)
- [MEVA: A Large-Scale Multiview, Multimodal Video Dataset for Activity Detection](https://mlsanity.com/paper/2012.00914/) (2020)
- [TRECVID 2020: A comprehensive campaign for evaluating video retrieval tasks across multiple application domains](https://mlsanity.com/paper/2104.13473/) (2021)
- [Gabriella: An Online System for Real-Time Activity Detection in Untrimmed Security Videos](https://mlsanity.com/paper/2004.11475/) (2020)
- [Traffic Danger Recognition With Surveillance Cameras Without Training Data](https://mlsanity.com/paper/1811.11969/) (2018)
- [Training-free Monocular 3D Event Detection System for Traffic Surveillance](https://mlsanity.com/paper/2002.00137/) (2020)

## Built on by (most cited first, 6 of 6)

- [Video Action Detection: Analysing Limitations and Challenges](https://mlsanity.com/paper/2204.07892/) (2022)
- [MVP-SEG: Multi-View Prompt Learning for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2304.06957/) (2023)
- [RALACs: Action Recognition in Autonomous Vehicles using Interaction Encoding and Optical Flow](https://mlsanity.com/paper/2209.14408/) (2022)
- [LITE: A Paradigm Shift in Multi-Object Tracking with Efficient ReID Feature Integration](https://mlsanity.com/paper/2409.04187/) (2024)
- [ROAD-Waymo: A Large-Scale Action Awareness Dataset for Autonomous Driving](https://mlsanity.com/paper/2411.01683/) (2024)
- [MPT-PAR:Mix-Parameters Transformer for Panoramic Activity Recognition](https://mlsanity.com/paper/2408.00420/) (2024)

## Abstract (arXiv)

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.