# Retro-Actions: Learning 'Close' by Time-Reversing 'Open' Videos

arXiv: https://arxiv.org/abs/1909.09422 · HTML: https://mlsanity.com/paper/1909.09422/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Sep 2019.

## Built on by (most cited first, 9 of 9)

- [Temporal-Relational CrossTransformers for Few-Shot Action Recognition](https://mlsanity.com/paper/2101.06184/) (2021)
- [Verbs in Action: Improving verb understanding in video-language models](https://mlsanity.com/paper/2304.06708/) (2023)
- [VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models](https://mlsanity.com/paper/2311.17404/) (2023)
- [Test of Time: Instilling Video-Language Models with a Sense of Time](https://mlsanity.com/paper/2301.02074/) (2023)
- [Seeing the Arrow of Time in Large Multimodal Models](https://mlsanity.com/paper/2506.03340/) (2025)
- [Chirality in Action: Time-Aware Video Representation Learning by Latent Straightening](https://mlsanity.com/paper/2509.08502/) (2025)
- [ArrowGEV: Grounding Events in Video via Learning the Arrow of Time](https://mlsanity.com/paper/2601.06559/) (2026)
- [Order Matters: On Parameter-Efficient Image-to-Video Probing for Recognizing Nearly Symmetric Actions](https://mlsanity.com/paper/2503.24298/) (2025)
- [Let's Split Up: Zero-Shot Classifier Edits for Fine-Grained Video Understanding](https://mlsanity.com/paper/2602.16545/) (2026)

## Abstract (arXiv)

We investigate video transforms that result in class-homogeneous label-transforms. These are video transforms that consistently maintain or modify the labels of all videos in each class. We propose a general approach to discover invariant classes, whose transformed examples maintain their label; pairs of equivariant classes, whose transformed examples exchange their labels; and novel-generating classes, whose transformed examples belong to a new class outside the dataset. Label transforms offer additional supervision previously unexplored in video recognition benefiting data augmentation and enabling zero-shot learning opportunities by learning a class from transformed videos of its counterpart. Amongst such video transforms, we study horizontal-flipping, time-reversal, and their composition. We highlight errors in naively using horizontal-flipping as a form of data augmentation in video. Next, we validate the realism of time-reversed videos through a human perception study where people exhibit equal preference for forward and time-reversed videos. Finally, we test our approach on two datasets, Jester and Something-Something, evaluating the three video transforms for zero-shot learning and data augmentation. Our results show that gestures such as zooming in can be learnt from zooming out in a zero-shot setting, as well as more complex actions with state transitions such as digging something out of something from burying something in something.