# Attention is All We Need: Nailing Down Object-centric Attention for Egocentric Activity Recognition

arXiv: https://arxiv.org/abs/1807.11794 · HTML: https://mlsanity.com/paper/1807.11794/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Jul 2018.

## Built on by (most cited first, 28 of 28)

- [An Outlook into the Future of Egocentric Vision](https://mlsanity.com/paper/2308.07123/) (2023)
- [With a Little Help from my Temporal Context: Multimodal Egocentric Action Recognition](https://mlsanity.com/paper/2111.01024/) (2021)
- [Learning to Anticipate Egocentric Actions by Imagination](https://mlsanity.com/paper/2101.04924/) (2021)
- [Trear: Transformer-based RGB-D Egocentric Action Recognition](https://mlsanity.com/paper/2101.03904/) (2021)
- [Domain Generalization through Audio-Visual Relative Norm Alignment in First Person Action Recognition](https://mlsanity.com/paper/2110.10101/) (2021)
- [Self-Regulated Learning for Egocentric Video Activity Anticipation](https://mlsanity.com/paper/2111.11631/) (2021)
- [Group Contextualization for Video Recognition](https://mlsanity.com/paper/2203.09694/) (2022)
- [EgoPCA: A New Framework for Egocentric Hand-Object Interaction Understanding](https://mlsanity.com/paper/2309.02423/) (2023)
- [Attention in Attention: Modeling Context Correlation for Efficient Video Classification](https://mlsanity.com/paper/2204.09303/) (2022)
- [Gaze-VLM:Bridging Gaze and VLMs through Attention Regularization for Egocentric Understanding](https://mlsanity.com/paper/2510.21356/) (2025)
- [Cross-Domain First Person Audio-Visual Action Recognition through Relative Norm Alignment](https://mlsanity.com/paper/2106.01689/) (2021)
- [SOS! Self-supervised Learning Over Sets Of Handled Objects In Egocentric Action Recognition](https://mlsanity.com/paper/2204.04796/) (2022)
- [GPT4Ego: Unleashing the Potential of Pre-trained Models for Zero-Shot Egocentric Action Recognition](https://mlsanity.com/paper/2401.10039/) (2024)
- [Learning to Recognize Actions on Objects in Egocentric Video with Attention Dictionaries](https://mlsanity.com/paper/2102.08065/) (2021)
- [Stacked Temporal Attention: Improving First-person Action Recognition by Emphasizing Discriminative Clips](https://mlsanity.com/paper/2112.01038/) (2021)
- [Modeling long-term interactions to enhance action recognition](https://mlsanity.com/paper/2104.11520/) (2021)
- [THORN: Temporal Human-Object Relation Network for Action Recognition](https://mlsanity.com/paper/2204.09468/) (2022)
- [BON: An extended public domain dataset for human activity recognition](https://mlsanity.com/paper/2209.05077/) (2022)
- [EgoViT: Pyramid Video Transformer for Egocentric Action Recognition](https://mlsanity.com/paper/2303.08920/) (2023)
- [Three-stream network for enriched Action Recognition](https://mlsanity.com/paper/2104.13051/) (2021)
- [Human Gaze Guided Attention for Surgical Activity Recognition](https://mlsanity.com/paper/2203.04752/) (2022)
- [A Survey on Human Action Recognition](https://mlsanity.com/paper/2301.06082/) (2022)
- [An End-to-End Two-Stream Network Based on RGB Flow and Representation Flow for Human Action Recognition](https://mlsanity.com/paper/2411.18002/) (2024)
- [Efficient Egocentric Action Recognition with Multimodal Data](https://mlsanity.com/paper/2506.01757/) (2025)
- [Egocentric Gaze Estimation via Neck-Mounted Camera](https://mlsanity.com/paper/2602.11669/) (2026)
- [Gaze-Regularized VLMs for Ego-Centric Behavior Understanding](https://mlsanity.com/paper/2603.23190/) (2026)
- [SAGE: Synchronized Action-Gaze Recognition and Anticipation for Human Behavior Understanding](https://mlsanity.com/paper/2607.04017/) (2026)
- [G3Ego: Gaze-Guided Graphs for Egocentric Action Understanding](https://mlsanity.com/paper/2608.20157/) (2026)

## Abstract (arXiv)

In this paper we propose an end-to-end trainable deep neural network model for egocentric activity recognition. Our model is built on the observation that egocentric activities are highly characterized by the objects and their locations in the video. Based on this, we develop a spatial attention mechanism that enables the network to attend to regions containing objects that are correlated with the activity under consideration. We learn highly specialized attention maps for each frame using class-specific activations from a CNN pre-trained for generic image recognition, and use them for spatio-temporal encoding of the video with a convolutional LSTM. Our model is trained in a weakly supervised setting using raw video-level activity-class labels. Nonetheless, on standard egocentric activity benchmarks our model surpasses by up to +6% points recognition accuracy the currently best performing method that leverages hand segmentation and object location strong supervision for training. We visually analyze attention maps generated by the network, revealing that the network successfully identifies the relevant objects present in the video frames which may explain the strong recognition performance. We also discuss an extensive ablation analysis regarding the design choices.