# Attention Flow: End-to-End Joint Attention Estimation

arXiv: https://arxiv.org/abs/2001.03960 · HTML: https://mlsanity.com/paper/2001.03960/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jan 2020.

## Built on by (most cited first, 11 of 11)

- [End-to-End Human-Gaze-Target Detection with Transformers](https://mlsanity.com/paper/2203.10433/) (2022)
- [Gaze-LLE: Gaze Target Estimation via Large-Scale Learned Encoders](https://mlsanity.com/paper/2412.09586/) (2024)
- [Modeling Multimodal Social Interactions: New Challenges and Baselines with Densely Aligned Representations](https://mlsanity.com/paper/2403.02090/) (2024)
- [Interaction-aware Joint Attention Estimation Using People Attributes](https://mlsanity.com/paper/2308.05382/) (2023)
- [Joint Gaze-Location and Gaze-Object Detection](https://mlsanity.com/paper/2308.13857/) (2023)
- [Multi-Modal Gaze Following in Conversational Scenarios](https://mlsanity.com/paper/2311.05669/) (2023)
- [A Novel Framework for Multi-Person Temporal Gaze Following and Social Gaze Prediction](https://mlsanity.com/paper/2403.10511/) (2024)
- [End-to-End Shared Attention Estimation via Group Detection with Feedback Refinement](https://mlsanity.com/paper/2604.01714/) (2026)
- [Automated Detection of Mutual Gaze and Joint Attention in Dual-Camera Settings via Dual-Stream Transformers](https://mlsanity.com/paper/2604.27105/) (2026)
- [Eyes on VLM: Benchmarking Gaze Following and Social Gaze Prediction in Vision Language Models](https://mlsanity.com/paper/2605.19859/) (2026)
- [Gaze-Anchored Social Net: Decoding Implicit Relations via Joint Modeling](https://mlsanity.com/paper/2607.22847/) (2026)

## Abstract (arXiv)

This paper addresses the problem of understanding joint attention in third-person social scene videos. Joint attention is the shared gaze behaviour of two or more individuals on an object or an area of interest and has a wide range of applications such as human-computer interaction, educational assessment, treatment of patients with attention disorders, and many more. Our method, Attention Flow, learns joint attention in an end-to-end fashion by using saliency-augmented attention maps and two novel convolutional attention mechanisms that determine to select relevant features and improve joint attention localization. We compare the effect of saliency maps and attention mechanisms and report quantitative and qualitative results on the detection and localization of joint attention in the VideoCoAtt dataset, which contains complex social scenes.