# Evidential Active Recognition: Intelligent and Prudent Open-World Embodied Perception

arXiv: https://arxiv.org/abs/2311.13793 · HTML: https://mlsanity.com/paper/2311.13793/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 57 references that are in the map.
- First posted on arXiv 23 Nov 2023.

## Builds on (most cited first, 30 of 36)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [Video Swin Transformer](https://mlsanity.com/paper/2106.13230/) (2021)
- [Evidential Deep Learning to Quantify Classification Uncertainty](https://mlsanity.com/paper/1806.01768/) (2018)
- [Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI](https://mlsanity.com/paper/2109.08238/) (2021)
- [Habitat 2.0: Training Home Assistants to Rearrange their Habitat](https://mlsanity.com/paper/2106.14405/) (2021)
- [Object Goal Navigation using Goal-Oriented Semantic Exploration](https://mlsanity.com/paper/2007.00643/) (2020)
- [Deep Evidential Regression](https://mlsanity.com/paper/1910.02600/) (2019)
- [Fast Online Object Tracking and Segmentation: A Unifying Approach](https://mlsanity.com/paper/1812.05050/) (2018)
- [Beyond Short Snippets: Deep Networks for Video Classification](https://mlsanity.com/paper/1503.08909/) (2015)
- [Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks](https://mlsanity.com/paper/2002.10118/) (2020)
- [Efficient and Scalable Bayesian Neural Nets with Rank-1 Factors](https://mlsanity.com/paper/2005.07186/) (2020)
- [Trusted Multi-View Classification with Dynamic Evidential Fusion](https://mlsanity.com/paper/2204.11423/) (2022)
- [Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference](https://mlsanity.com/paper/1506.02158/) (2015)
- [Evidential Deep Learning for Open Set Action Recognition](https://mlsanity.com/paper/2107.10161/) (2021)
- [Revisiting Active Perception](https://mlsanity.com/paper/1603.02729/) (2016)
- [Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning](https://mlsanity.com/paper/1812.00971/) (2018)
- [An Exploration of Embodied Visual Exploration](https://mlsanity.com/paper/2001.02192/) (2020)
- [A Dataset for Developing and Benchmarking Active Vision](https://mlsanity.com/paper/1702.08272/) (2017)
- [Continuous Scene Representations for Embodied AI](https://mlsanity.com/paper/2203.17251/) (2022)
- [Zero-shot object goal visual navigation](https://mlsanity.com/paper/2206.07423/) (2022)
- [Interactron: Embodied Adaptive Object Detection](https://mlsanity.com/paper/2202.00660/) (2022)
- [Geometry-Aware Recurrent Neural Networks for Active Visual Recognition](https://mlsanity.com/paper/1811.01292/) (2018)

## Built on by (most cited first, 15 of 15)

- [Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI](https://mlsanity.com/paper/2407.06886/) (2024)
- [World-in-World: World Models in a Closed-Loop World](https://mlsanity.com/paper/2510.18135/) (2025)
- [A Comprehensive Survey on Evidential Deep Learning and Its Applications](https://mlsanity.com/paper/2409.04720/) (2024)
- [A Survey on Agentic Multimodal Large Language Models](https://mlsanity.com/paper/2510.10991/) (2025)
- [GenEx: Generating an Explorable World](https://mlsanity.com/paper/2412.09624/) (2024)
- [Generative World Explorer](https://mlsanity.com/paper/2411.11844/) (2024)
- [WoMAP: World Models For Embodied Open-Vocabulary Object Localization](https://mlsanity.com/paper/2506.01600/) (2025)
- [Percept, Chat, and then Adapt: Multimodal Knowledge Transfer of Foundation Models for Open-World Video Recognition](https://mlsanity.com/paper/2402.18951/) (2024)
- [Observe Then Act: Asynchronous Active Vision-Action Model for Robotic Manipulation](https://mlsanity.com/paper/2409.14891/) (2024)
- [3D Gaussian Map with Open-Set Semantic Grouping for Vision-Language Navigation](https://mlsanity.com/paper/2605.26500/) (2026)
- [Embodied Domain Adaptation for Object Detection](https://mlsanity.com/paper/2506.21860/) (2025)
- [Towards Next-Generation Healthcare: A Survey of Medical Embodied AI for Perception, Decision-Making, and Action](https://mlsanity.com/paper/2606.15647/) (2026)
- [Open Set Face Forgery Detection via Dual-Level Evidence Collection](https://mlsanity.com/paper/2512.04331/) (2025)
- [See, Act, Adapt: Active Perception for Unsupervised Cross-Domain Visual Adaptation via Personalized VLM-Guided Agent](https://mlsanity.com/paper/2602.23806/) (2026)
- [PInVerify: An Offline Embodied Benchmark for Active Instance Verification](https://mlsanity.com/paper/2605.30639/) (2026)

## Abstract (arXiv)

Active recognition enables robots to intelligently explore novel observations, thereby acquiring more information while circumventing undesired viewing conditions. Recent approaches favor learning policies from simulated or collected data, wherein appropriate actions are more frequently selected when the recognition is accurate. However, most recognition modules are developed under the closed-world assumption, which makes them ill-equipped to handle unexpected inputs, such as the absence of the target object in the current observation. To address this issue, we propose treating active recognition as a sequential evidence-gathering process, providing by-step uncertainty quantification and reliable prediction under the evidence combination theory. Additionally, the reward function developed in this paper effectively characterizes the merit of actions when operating in open-world environments. To evaluate the performance, we collect a dataset from an indoor simulator, encompassing various recognition challenges such as distance, occlusion levels, and visibility. Through a series of experiments on recognition and robustness analysis, we demonstrate the necessity of introducing uncertainties to active recognition and the superior performance of the proposed method.