# DiscrimNet: Semi-Supervised Action Recognition from Videos using Generative Adversarial Networks

arXiv: https://arxiv.org/abs/1801.07230 · HTML: https://mlsanity.com/paper/1801.07230/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jan 2018.

## Built on by (most cited first, 14 of 14)

- [My View is the Best View: Procedure Learning from Egocentric Videos](https://mlsanity.com/paper/2207.10883/) (2022)
- [Unsupervised Action Segmentation by Joint Representation Learning and Online Clustering](https://mlsanity.com/paper/2105.13353/) (2021)
- [Learning by Aligning Videos in Time](https://mlsanity.com/paper/2103.17260/) (2021)
- [Boundary-aware Self-supervised Learning for Video Scene Segmentation](https://mlsanity.com/paper/2201.05277/) (2022)
- [United We Stand, Divided We Fall: UnityGraph for Unsupervised Procedure Learning from Videos](https://mlsanity.com/paper/2311.03550/) (2023)
- [Context-Aware Sequence Alignment using 4D Skeletal Augmentation](https://mlsanity.com/paper/2204.12223/) (2022)
- [Joint Self-Supervised Video Alignment and Action Segmentation](https://mlsanity.com/paper/2503.16832/) (2025)
- [Learning Human Action Recognition Representations Without Real Humans](https://mlsanity.com/paper/2311.06231/) (2023)
- [Procedure Learning via Regularized Gromov-Wasserstein Optimal Transport](https://mlsanity.com/paper/2507.15540/) (2025)
- [Learning by Aligning 2D Skeleton Sequences and Multi-Modality Fusion](https://mlsanity.com/paper/2305.19480/) (2023)
- [A Comprehensive Methodological Survey of Human Activity Recognition Across Divers Data Modalities](https://mlsanity.com/paper/2409.09678/) (2024)
- [GOCA: Guided Online Cluster Assignment for Self-Supervised Video Representation Learning](https://mlsanity.com/paper/2207.10158/) (2022)
- [REMAP: Regularized Matching and Partial Alignment of Video Embeddings](https://mlsanity.com/paper/2509.24382/) (2025)
- [Multi Activity Sequence Alignment via Implicit Clustering](https://mlsanity.com/paper/2503.12519/) (2025)

## Abstract (arXiv)

We propose an action recognition framework using Gen- erative Adversarial Networks. Our model involves train- ing a deep convolutional generative adversarial network (DCGAN) using a large video activity dataset without la- bel information. Then we use the trained discriminator from the GAN model as an unsupervised pre-training step and fine-tune the trained discriminator model on a labeled dataset to recognize human activities. We determine good network architectural and hyperparameter settings for us- ing the discriminator from DCGAN as a trained model to learn useful representations for action recognition. Our semi-supervised framework using only appearance infor- mation achieves superior or comparable performance to the current state-of-the-art semi-supervised action recog- nition methods on two challenging video activity datasets: UCF101 and HMDB51.