# Dual-Glance Model for Deciphering Social Relationships

arXiv: https://arxiv.org/abs/1708.00634 · HTML: https://mlsanity.com/paper/1708.00634/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Aug 2017.

## Built on by (most cited first, 21 of 21)

- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models](https://mlsanity.com/paper/2503.06749/) (2025)
- [A study on the distribution of social biases in self-supervised learning visual models](https://mlsanity.com/paper/2203.01854/) (2022)
- [Fairness and Bias Mitigation in Computer Vision: A Survey](https://mlsanity.com/paper/2408.02464/) (2024)
- [Face-Human-Bench: A Comprehensive Benchmark of Face and Human Understanding for Multi-modal Assistants](https://mlsanity.com/paper/2501.01243/) (2025)
- [Multiverse Through Deepfakes: The MultiFakeVerse Dataset of Person-Centric Visual and Conceptual Manipulations](https://mlsanity.com/paper/2506.00868/) (2025)
- [Pairwise Emotional Relationship Recognition in Drama Videos: Dataset and Benchmark](https://mlsanity.com/paper/2109.11243/) (2021)
- [DRAG: Dynamic Region-Aware GCN for Privacy-Leaking Image Detection](https://mlsanity.com/paper/2203.09121/) (2022)
- [Seeing the Intangible: Survey of Image Classification into High-Level and Abstract Categories](https://mlsanity.com/paper/2308.10562/) (2023)
- [Looking Beyond the Obvious: A Survey on Abstract Concept Recognition for Video Understanding](https://mlsanity.com/paper/2508.20765/) (2025)
- [My Body My Choice: Human-Centric Full-Body Anonymization](https://mlsanity.com/paper/2406.09553/) (2024)
- [Interaction-GCN: A Graph Convolutional Network based framework for social interaction recognition in egocentric videos](https://mlsanity.com/paper/2104.14007/) (2021)
- [Stitching Gaps: Fusing Situated Perceptual Knowledge with Vision Transformers for High-Level Image Classification](https://mlsanity.com/paper/2402.19339/) (2024)
- [SocialFusion: Addressing Social Degradation in Pre-trained Vision-Language Models](https://mlsanity.com/paper/2512.01148/) (2025)
- [Enhancing Social Relation Inference with Concise Interaction Graph and Discriminative Scene Representation](https://mlsanity.com/paper/2107.14425/) (2021)
- [Face Clustering for Connection Discovery from Event Images](https://mlsanity.com/paper/2309.01092/) (2023)
- [GRITv2: Efficient and Light-weight Social Relation Recognition](https://mlsanity.com/paper/2403.06895/) (2024)
- [From a Social Cognitive Perspective: Context-aware Visual Social Relationship Recognition](https://mlsanity.com/paper/2406.08358/) (2024)
- [CloSE: A Geometric Shape-Agnostic Cloth State Representation](https://mlsanity.com/paper/2504.05033/) (2025)
- [Street View Sociability: Interpretable Analysis of Urban Social Behavior Across 15 Cities](https://mlsanity.com/paper/2508.06342/) (2025)
- [FriendBench: Benchmarking Dyadic Familiarity Inference in Humans and Multimodal Large Language Models](https://mlsanity.com/paper/2607.29602/) (2026)

## Abstract (arXiv)

Since the beginning of early civilizations, social relationships derived from each individual fundamentally form the basis of social structure in our daily life. In the computer vision literature, much progress has been made in scene understanding, such as object detection and scene parsing. Recent research focuses on the relationship between objects based on its functionality and geometrical relations. In this work, we aim to study the problem of social relationship recognition, in still images. We have proposed a dual-glance model for social relationship recognition, where the first glance fixates at the individual pair of interest and the second glance deploys attention mechanism to explore contextual cues. We have also collected a new large scale People in Social Context (PISC) dataset, which comprises of 22,670 images and 76,568 annotated samples from 9 types of social relationship. We provide benchmark results on the PISC dataset, and qualitatively demonstrate the efficacy of the proposed model.