# Distance-Aware Occlusion Detection with Focused Attention

arXiv: https://arxiv.org/abs/2208.11122 · HTML: https://mlsanity.com/paper/2208.11122/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 33 references that are in the map.
- First posted on arXiv 23 Aug 2022.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [Image Transformer](https://mlsanity.com/paper/1802.05751/) (2018)
- [Deep Hough Voting for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/1904.09664/) (2019)
- [Understanding the Effective Receptive Field in Deep Convolutional Neural Networks](https://mlsanity.com/paper/1701.04128/) (2017)
- [Attention Augmented Convolutional Networks](https://mlsanity.com/paper/1904.09925/) (2019)
- [Adaptively Sparse Transformers](https://mlsanity.com/paper/1909.00015/) (2019)
- [QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information](https://mlsanity.com/paper/2103.05399/) (2021)
- [End-to-End Human Object Interaction Detection with HOI Transformer](https://mlsanity.com/paper/2103.04503/) (2021)
- [Visual Translation Embedding Network for Visual Relation Detection](https://mlsanity.com/paper/1702.08319/) (2017)
- [Semantic Amodal Segmentation](https://mlsanity.com/paper/1509.01329/) (2015)
- [Mining the Benefits of Two-stage and One-stage HOI Detection](https://mlsanity.com/paper/2108.05077/) (2021)
- [Detecting Visual Relationships with Deep Relational Networks](https://mlsanity.com/paper/1704.03114/) (2017)
- [Self-Supervised Scene De-occlusion](https://mlsanity.com/paper/2004.02788/) (2020)
- [Reformulating HOI Detection as Adaptive Set Prediction](https://mlsanity.com/paper/2103.05983/) (2021)
- [Explicit Sparse Transformer: Concentrated Attention Through Explicit Selection](https://mlsanity.com/paper/1912.11637/) (2019)
- [Deformable Part Models are Convolutional Neural Networks](https://mlsanity.com/paper/1409.5403/) (2014)
- [YouRefIt: Embodied Reference Understanding with Language and Gesture](https://mlsanity.com/paper/2109.03413/) (2021)
- [PQ-Transformer: Jointly Parsing 3D Objects and Layouts from Point Clouds](https://mlsanity.com/paper/2109.05566/) (2021)
- [Towards Context-aware Interaction Recognition](https://mlsanity.com/paper/1703.06246/) (2017)
- [2.5D Visual Relationship Detection](https://mlsanity.com/paper/2104.12727/) (2021)

## Built on by (most cited first, 6 of 6)

- [ADAPT: Action-aware Driving Caption Transformer](https://mlsanity.com/paper/2302.00673/) (2023)
- [LODE: Locally Conditioned Eikonal Implicit Scene Completion from Sparse LiDAR](https://mlsanity.com/paper/2302.14052/) (2023)
- [TOIST: Task Oriented Instance Segmentation Transformer with Noun-Pronoun Distillation](https://mlsanity.com/paper/2210.10775/) (2022)
- [Reusing Attention for One-stage Lane Topology Understanding](https://mlsanity.com/paper/2507.17617/) (2025)
- [GPT-4 for Occlusion Order Recovery](https://mlsanity.com/paper/2509.22383/) (2025)
- [Occlusion-Ordered Semantic Instance Segmentation](https://mlsanity.com/paper/2504.14054/) (2025)

## Abstract (arXiv)

For humans, understanding the relationships between objects using visual signals is intuitive. For artificial intelligence, however, this task remains challenging. Researchers have made significant progress studying semantic relationship detection, such as human-object interaction detection and visual relationship detection. We take the study of visual relationships a step further from semantic to geometric. In specific, we predict relative occlusion and relative distance relationships. However, detecting these relationships from a single image is challenging. Enforcing focused attention to task-specific regions plays a critical role in successfully detecting these relationships. In this work, (1) we propose a novel three-decoder architecture as the infrastructure for focused attention; 2) we use the generalized intersection box prediction task to effectively guide our model to focus on occlusion-specific regions; 3) our model achieves a new state-of-the-art performance on distance-aware relationship detection. Specifically, our model increases the distance F1-score from 33.8% to 38.6% and boosts the occlusion F1-score from 34.4% to 41.2%. Our code is publicly available.