# Contrastive Language Video Time Pre-training

arXiv: https://arxiv.org/abs/2406.02631 · HTML: https://mlsanity.com/paper/2406.02631/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 12 references that are in the map.
- First posted on arXiv 4 Jun 2024.

## Builds on (most cited first, 11 of 11)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [Egocentric Video-Language Pretraining](https://mlsanity.com/paper/2206.01670/) (2022)
- [Learning Video Representations from Large Language Models](https://mlsanity.com/paper/2212.04501/) (2022)
- [EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone](https://mlsanity.com/paper/2307.05463/) (2023)
- [Charades-Ego: A Large-Scale Dataset of Paired Third and First Person Videos](https://mlsanity.com/paper/1804.09626/) (2018)
- [GPT4Ego: Unleashing the Potential of Pre-trained Models for Zero-Shot Egocentric Action Recognition](https://mlsanity.com/paper/2401.10039/) (2024)

## Abstract (arXiv)

We introduce LAVITI, a novel approach to learning language, video, and temporal representations in long-form videos via contrastive learning. Different from pre-training on video-text pairs like EgoVLP, LAVITI aims to align language, video, and temporal features by extracting meaningful moments in untrimmed videos. Our model employs a set of learnable moment queries to decode clip-level visual, language, and temporal features. In addition to vision and language alignment, we introduce relative temporal embeddings (TE) to represent timestamps in videos, which enables contrastive learning of time. Significantly different from traditional approaches, the prediction of a particular timestamp is transformed by computing the similarity score between the predicted TE and all TEs. Furthermore, existing approaches for video understanding are mainly designed for short videos due to high computational complexity and memory footprint. Our method can be trained on the Ego4D dataset with only 8 NVIDIA RTX-3090 GPUs in a day. We validated our method on CharadesEgo action recognition, achieving state-of-the-art results.