# Learning from Video and Text via Large-Scale Discriminative Clustering

arXiv: https://arxiv.org/abs/1707.09074 · HTML: https://mlsanity.com/paper/1707.09074/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jul 2017.

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

- [Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models](https://mlsanity.com/paper/2305.19595/) (2023)
- [Space-Time Crop & Attend: Improving Cross-modal Video Representation Learning](https://mlsanity.com/paper/2103.10211/) (2021)
- [FETA: Towards Specializing Foundation Models for Expert Task Applications](https://mlsanity.com/paper/2209.03648/) (2022)
- [Sarah Frank-Wolfe: Methods for Constrained Optimization with Best Rates and Practical Features](https://mlsanity.com/paper/2304.11737/) (2023)
- [A multimodal deep learning framework for scalable content based visual media retrieval](https://mlsanity.com/paper/2105.08665/) (2021)
- [Creating Multimedia Summaries Using Tweets and Videos](https://mlsanity.com/paper/2203.08931/) (2022)

## Abstract (arXiv)

Discriminative clustering has been successfully applied to a number of weakly-supervised learning tasks. Such applications include person and action recognition, text-to-video alignment, object co-segmentation and colocalization in videos and images. One drawback of discriminative clustering, however, is its limited scalability. We address this issue and propose an online optimization algorithm based on the Block-Coordinate Frank-Wolfe algorithm. We apply the proposed method to the problem of weakly supervised learning of actions and actors from movies together with corresponding movie scripts. The scaling up of the learning problem to 66 feature length movies enables us to significantly improve weakly supervised action recognition.