# Ego-Vehicle Action Recognition based on Semi-Supervised Contrastive Learning

arXiv: https://arxiv.org/abs/2303.00977 · HTML: https://mlsanity.com/paper/2303.00977/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 57 references that are in the map.
- First posted on arXiv 2 Mar 2023.

## Builds on (most cited first, 30 of 44)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [Graph Contrastive Learning with Augmentations](https://mlsanity.com/paper/2010.13902/) (2020)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (2019)
- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [Simple Online and Realtime Tracking](https://mlsanity.com/paper/1602.00763/) (2016)
- [Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results](https://mlsanity.com/paper/1703.01780/) (2017)
- [ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring](https://mlsanity.com/paper/1911.09785/) (2019)
- [Self-supervised Graph Learning for Recommendation](https://mlsanity.com/paper/2010.10783/) (2020)
- [Semi-Supervised Learning with Ladder Networks](https://mlsanity.com/paper/1507.02672/) (2015)
- [Learning with Pseudo-Ensembles](https://mlsanity.com/paper/1412.4864/) (2014)
- [Videos as Space-Time Region Graphs](https://mlsanity.com/paper/1806.01810/) (2018)
- [Quasi-Dense Similarity Learning for Multiple Object Tracking](https://mlsanity.com/paper/2006.06664/) (2020)
- [Parametric Contrastive Learning](https://mlsanity.com/paper/2107.12028/) (2021)
- [Graph Matching Networks for Learning the Similarity of Graph Structured Objects](https://mlsanity.com/paper/1904.12787/) (2019)
- [CoMatch: Semi-supervised Learning with Contrastive Graph Regularization](https://mlsanity.com/paper/2011.11183/) (2020)
- [ASAP: Adaptive Structure Aware Pooling for Learning Hierarchical Graph Representations](https://mlsanity.com/paper/1911.07979/) (2019)
- [End-to-end Learning of Driving Models from Large-scale Video Datasets](https://mlsanity.com/paper/1612.01079/) (2016)
- [Self-Driving Cars: A Survey](https://mlsanity.com/paper/1901.04407/) (2019)

## Built on by (most cited first, 8 of 8)

- [DQS3D: Densely-matched Quantization-aware Semi-supervised 3D Detection](https://mlsanity.com/paper/2304.13031/) (2023)
- [Driving through the Concept Gridlock: Unraveling Explainability Bottlenecks in Automated Driving](https://mlsanity.com/paper/2310.16639/) (2023)
- [BID: Boundary-Interior Decoding for Unsupervised Temporal Action Localization Pre-Trainin](https://mlsanity.com/paper/2403.07354/) (2024)
- [A Survey on Video Analytics in Cloud-Edge-Terminal Collaborative Systems](https://mlsanity.com/paper/2502.06581/) (2025)
- [Transfer-LMR: Heavy-Tail Driving Behavior Recognition in Diverse Traffic Scenarios](https://mlsanity.com/paper/2405.05354/) (2024)
- [Last Layer Hamiltonian Monte Carlo](https://mlsanity.com/paper/2507.08905/) (2025)
- [Driving behavior recognition via self-discovery learning](https://mlsanity.com/paper/2503.14194/) (2025)
- [Latent Uncertainty Representations for Video-based Driver Action and Intention Recognition](https://mlsanity.com/paper/2510.05006/) (2025)

## Abstract (arXiv)

In recent years, many automobiles have been equipped with cameras, which have accumulated an enormous amount of video footage of driving scenes. Autonomous driving demands the highest level of safety, for which even unimaginably rare driving scenes have to be collected in training data to improve the recognition accuracy for specific scenes. However, it is prohibitively costly to find very few specific scenes from an enormous amount of videos. In this article, we show that proper video-to-video distances can be defined by focusing on ego-vehicle actions. It is well known that existing methods based on supervised learning cannot handle videos that do not fall into predefined classes, though they work well in defining video-to-video distances in the embedding space between labeled videos. To tackle this problem, we propose a method based on semi-supervised contrastive learning. We consider two related but distinct contrastive learning: standard graph contrastive learning and our proposed SOIA-based contrastive learning. We observe that the latter approach can provide more sensible video-to-video distances between unlabeled videos. Next, the effectiveness of our method is quantified by evaluating the classification performance of the ego-vehicle action recognition using HDD dataset, which shows that our method including unlabeled data in training significantly outperforms the existing methods using only labeled data in training.