# OmViD: Omni-supervised active learning for video action detection

arXiv: https://arxiv.org/abs/2508.13983 · HTML: https://mlsanity.com/paper/2508.13983/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 54 of its 82 references that are in the map.
- First posted on arXiv 19 Aug 2025.

## Builds on (most cited first, 30 of 54)

- [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)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [YOLO9000: Better, Faster, Stronger](https://mlsanity.com/paper/1612.08242/) (2016)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?](https://mlsanity.com/paper/1711.09577/) (2017)
- [AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions](https://mlsanity.com/paper/1705.08421/) (2017)
- [BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning](https://mlsanity.com/paper/1906.08158/) (2019)
- [Video Instance Segmentation](https://mlsanity.com/paper/1905.04804/) (2019)
- [ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1604.05144/) (2016)
- [End-to-End Semi-Supervised Object Detection with Soft Teacher](https://mlsanity.com/paper/2106.09018/) (2021)
- [In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning](https://mlsanity.com/paper/2101.06329/) (2021)
- [Simple Does It: Weakly Supervised Instance and Semantic Segmentation](https://mlsanity.com/paper/1603.07485/) (2016)
- [Cost-Effective Active Learning for Deep Image Classification](https://mlsanity.com/paper/1701.03551/) (2017)
- [Learning Active Learning from Data](https://mlsanity.com/paper/1703.03365/) (2017)
- [Active Learning for Deep Object Detection via Probabilistic Modeling](https://mlsanity.com/paper/2103.16130/) (2021)
- [Action Tubelet Detector for Spatio-Temporal Action Localization](https://mlsanity.com/paper/1705.01861/) (2017)
- [Multiple instance active learning for object detection](https://mlsanity.com/paper/2104.02324/) (2021)
- [Superpixel Segmentation with Fully Convolutional Networks](https://mlsanity.com/paper/2003.12929/) (2020)
- [Asynchronous Interaction Aggregation for Action Detection](https://mlsanity.com/paper/2004.07485/) (2020)
- [Active Learning for Deep Detection Neural Networks](https://mlsanity.com/paper/1911.09168/) (2019)
- [Points as Queries: Weakly Semi-supervised Object Detection by Points](https://mlsanity.com/paper/2104.07434/) (2021)
- [Online Real-time Multiple Spatiotemporal Action Localisation and Prediction](https://mlsanity.com/paper/1611.08563/) (2016)
- [Cross-Domain Self-supervised Multi-task Feature Learning using Synthetic Imagery](https://mlsanity.com/paper/1711.09082/) (2017)

## Built on by (most cited first, 3 of 3)

- [RobustGait: Robustness Analysis for Appearance Based Gait Recognition](https://mlsanity.com/paper/2511.13065/) (2025)
- [VISTA: Video Interaction Spatio-Temporal Analysis Benchmark](https://mlsanity.com/paper/2605.01391/) (2026)
- [IMPACT-Scribe: Interactive Temporal Action Segmentation with Boundary Scribbles and Query Planning](https://mlsanity.com/paper/2605.01668/) (2026)

## Abstract (arXiv)

Video action detection requires dense spatio-temporal annotations, which are both challenging and expensive to obtain. However, real-world videos often vary in difficulty and may not require the same level of annotation. This paper analyzes the appropriate annotation types for each sample and their impact on spatio-temporal video action detection. It focuses on two key aspects: 1) how to obtain varying levels of annotation for videos, and 2) how to learn action detection from different annotation types. The study explores video-level tags, points, scribbles, bounding boxes, and pixel-level masks. First, a simple active learning strategy is proposed to estimate the necessary annotation type for each video. Then, a novel spatio-temporal 3D-superpixel approach is introduced to generate pseudo-labels from these annotations, enabling effective training. The approach is validated on UCF101-24 and JHMDB-21 datasets, significantly cutting annotation costs with minimal performance loss.