# Egocentric Activity Recognition and Localization on a 3D Map

arXiv: https://arxiv.org/abs/2105.09544 · HTML: https://mlsanity.com/paper/2105.09544/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 70 references that are in the map.
- First posted on arXiv 20 May 2021.

## Builds on (most cited first, 29 of 29)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection](https://mlsanity.com/paper/1711.06396/) (2017)
- [The Replica Dataset: A Digital Replica of Indoor Spaces](https://mlsanity.com/paper/1906.05797/) (2019)
- [Multi-View 3D Object Detection Network for Autonomous Driving](https://mlsanity.com/paper/1611.07759/) (2016)
- [PointConv: Deep Convolutional Networks on 3D Point Clouds](https://mlsanity.com/paper/1811.07246/) (2018)
- [NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding](https://mlsanity.com/paper/1905.04757/) (2019)
- [PIXOR: Real-time 3D Object Detection from Point Clouds](https://mlsanity.com/paper/1902.06326/) (2019)
- [Resolving 3D Human Pose Ambiguities with 3D Scene Constraints](https://mlsanity.com/paper/1908.06963/) (2019)
- [3D Scene Graph: A Structure for Unified Semantics, 3D Space, and Camera](https://mlsanity.com/paper/1910.02527/) (2019)
- [EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition](https://mlsanity.com/paper/1908.08498/) (2019)
- [The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines](https://mlsanity.com/paper/2005.00343/) (2020)
- [Generating 3D People in Scenes without People](https://mlsanity.com/paper/1912.02923/) (2019)
- [Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Images](https://mlsanity.com/paper/1511.02300/) (2015)
- [EGO-TOPO: Environment Affordances from Egocentric Video](https://mlsanity.com/paper/2001.04583/) (2020)
- [What Would You Expect? Anticipating Egocentric Actions with Rolling-Unrolling LSTMs and Modality Attention](https://mlsanity.com/paper/1905.09035/) (2019)
- [You2Me: Inferring Body Pose in Egocentric Video via First and Second Person Interactions](https://mlsanity.com/paper/1904.09882/) (2019)
- [Predicting Gaze in Egocentric Video by Learning Task-dependent Attention Transition](https://mlsanity.com/paper/1803.09125/) (2018)
- [Vote3Deep: Fast Object Detection in 3D Point Clouds Using Efficient Convolutional Neural Networks](https://mlsanity.com/paper/1609.06666/) (2016)
- [Going Deeper into First-Person Activity Recognition](https://mlsanity.com/paper/1605.03688/) (2016)
- [4D Human Body Capture from Egocentric Video via 3D Scene Grounding](https://mlsanity.com/paper/2011.13341/) (2020)
- [First-Person Activity Forecasting with Online Inverse Reinforcement Learning](https://mlsanity.com/paper/1612.07796/) (2016)
- [Unsupervised Reinforcement Learning of Transferable Meta-Skills for Embodied Navigation](https://mlsanity.com/paper/1911.07450/) (2019)
- [SplitNet: Sim2Sim and Task2Task Transfer for Embodied Visual Navigation](https://mlsanity.com/paper/1905.07512/) (2019)
- [Generative Hybrid Representations for Activity Forecasting with No-Regret Learning](https://mlsanity.com/paper/1904.06250/) (2019)
- [Trespassing the Boundaries: Labeling Temporal Bounds for Object Interactions in Egocentric Video](https://mlsanity.com/paper/1703.09026/) (2017)
- [Forecasting Human-Object Interaction: Joint Prediction of Motor Attention and Actions in First Person Video](https://mlsanity.com/paper/1911.10967/) (2019)
- [Learning Action Maps of Large Environments via First-Person Vision](https://mlsanity.com/paper/1605.01679/) (2016)

## Abstract (arXiv)

Given a video captured from a first person perspective and the environment context of where the video is recorded, can we recognize what the person is doing and identify where the action occurs in the 3D space? We address this challenging problem of jointly recognizing and localizing actions of a mobile user on a known 3D map from egocentric videos. To this end, we propose a novel deep probabilistic model. Our model takes the inputs of a Hierarchical Volumetric Representation (HVR) of the 3D environment and an egocentric video, infers the 3D action location as a latent variable, and recognizes the action based on the video and contextual cues surrounding its potential locations. To evaluate our model, we conduct extensive experiments on the subset of Ego4D dataset, in which both human naturalistic actions and photo-realistic 3D environment reconstructions are captured. Our method demonstrates strong results on both action recognition and 3D action localization across seen and unseen environments. We believe our work points to an exciting research direction in the intersection of egocentric vision, and 3D scene understanding.