# CARLOR @ Ego4D Step Grounding Challenge: Bayesian temporal-order priors for test time refinement

arXiv: https://arxiv.org/abs/2406.09575 · HTML: https://mlsanity.com/paper/2406.09575/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 10 references that are in the map.
- First posted on arXiv 13 Jun 2024.

## Builds on (most cited first, 8 of 8)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [InternVideo: General Video Foundation Models via Generative and Discriminative Learning](https://mlsanity.com/paper/2212.03191/) (2022)
- [Span-based Localizing Network for Natural Language Video Localization](https://mlsanity.com/paper/2004.13931/) (2020)
- [NaQ: Leveraging Narrations as Queries to Supervise Episodic Memory](https://mlsanity.com/paper/2301.00746/) (2023)
- [EgoEnv: Human-centric environment representations from egocentric video](https://mlsanity.com/paper/2207.11365/) (2022)
- [GroundNLQ @ Ego4D Natural Language Queries Challenge 2023](https://mlsanity.com/paper/2306.15255/) (2023)
- [An Efficient COarse-to-fiNE Alignment Framework @ Ego4D Natural Language Queries Challenge 2022](https://mlsanity.com/paper/2211.08776/) (2022)

## Built on by (most cited first, 3 of 3)

- [Object-Shot Enhanced Grounding Network for Egocentric Video](https://mlsanity.com/paper/2505.04270/) (2025)
- [OSGNet @ Ego4D Episodic Memory Challenge 2025](https://mlsanity.com/paper/2506.03710/) (2025)
- [HiERO-StepG @ Ego4D Step Grounding Challenge: hierarchical activity understanding enables zero-shot step grounding](https://mlsanity.com/paper/2605.31227/) (2026)

## Abstract (arXiv)

The goal of the Step Grounding task is to locate temporal boundaries of activities based on natural language descriptions. This technical report introduces a Bayesian-VSLNet to address the challenge of identifying such temporal segments in lengthy, untrimmed egocentric videos. Our model significantly improves upon traditional models by incorporating a novel Bayesian temporal-order prior during inference, enhancing the accuracy of moment predictions. This prior adjusts for cyclic and repetitive actions within videos. Our evaluations demonstrate superior performance over existing methods, achieving state-of-the-art results on the Ego4D Goal-Step dataset with a 35.18 Recall Top-1 at 0.3 IoU and 20.48 Recall Top-1 at 0.5 IoU on the test set.