mlsanityData to 7 Oct 2026

Most Important Person-guided Dual-branch Cross-Patch Attention for Group Affect Recognition

arXiv 2212.07055 ↗First posted 14 Dec 2022cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Group affect refers to the subjective emotion that is evoked by an external stimulus in a group, which is an important factor that shapes group behavior and outcomes. Recognizing group affect involves identifying important individuals and salient objects among a crowd that can evoke emotions. However, most existing methods lack attention to affective meaning in group dynamics and fail to account for the contextual relevance of faces and objects in group-level images. In this work, we propose a solution by incorporating the psychological concept of the Most Important Person (MIP), which represents the most noteworthy face in a crowd and has affective semantic meaning. We present the Dual-branch Cross-Patch Attention Transformer (DCAT) which uses global image and MIP together as inputs. Specifically, we first learn the informative facial regions produced by the MIP and the global context separately. Then, the Cross-Patch Attention module is proposed to fuse the features of MIP and global context together to complement each other. Our proposed method outperforms state-of-the-art methods on GAF 3.0, GroupEmoW, and HECO datasets. Moreover, we demonstrate the potential for broader applications by showing that our proposed model can be transferred to another group affect task, group cohesion, and achieve comparable results.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 33 of its 51 references that are in the map. First posted on arXiv 14 Dec 2022.

Builds on

33 of 51 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  5. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  6. 2017Squeeze-and-Excitation Networkscited by 4,763
  7. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
  8. 2021DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsificationcited by 849
  9. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  10. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 731
  11. 2021CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windowscited by 526
  12. 2016R-FCN: Object Detection via Region-based Fully Convolutional Networkscited by 414
21 more
  1. 2022Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizationscited by 359
  2. 2021DeepViT: Towards Deeper Vision Transformercited by 288
  3. 2021Focal Self-attention for Local-Global Interactions in Vision Transformerscited by 286
  4. 2021Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformercited by 175
  5. 2021Conformer: Local Features Coupling Global Representations for Visual Recognitioncited by 164
  6. 2019PPDM: Parallel Point Detection and Matching for Real-time Human-Object Interaction Detectioncited by 143
  7. 2021Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognitioncited by 143
  8. 2021TransFG: A Transformer Architecture for Fine-grained Recognitioncited by 131
  9. 2021RegionViT: Regional-to-Local Attention for Vision Transformerscited by 126
  10. 2020SER-FIQ: Unsupervised Estimation of Face Image Quality Based on Stochastic Embedding Robustnesscited by 111
  11. 2019Context-Aware Emotion Recognition Networkscited by 99
  12. 2022Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformercited by 99
  13. 2021P2T: Pyramid Pooling Transformer for Scene Understandingcited by 84
  14. 2022Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identificationcited by 78
  15. 2022Dual Vision Transformercited by 29
  16. 2015Detecting events and key actors in multi-person videoscited by 26
  17. 2019Graph Neural Networks for Image Understanding Based on Multiple Cues: Group Emotion Recognition and Event Recognition as Use Casescited by 11
  18. 2019Learning to Learn Relation for Important People Detection in Still Imagescited by 10
  19. 2020Learning to Detect Important People in Unlabelled Images for Semi-supervised Important People Detectioncited by 8
  20. 2017PersonRank: Detecting Important People in Imagescited by 5
  21. 2018Predicting Group Cohesiveness in Imagescited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 1; 2026: 1.

5 papers.

  1. 2024EmoVIT: Revolutionizing Emotion Insights with Visual Instruction Tuningcited by 42
  2. 2024A Survey of Deep Learning for Group-level Emotion Recognitioncited by 3
  3. 2024MIP-GAF: A MLLM-annotated Benchmark for Most Important Person Localization and Group Context Understandingcited by 3
  4. 2025Incorporating Scene Context and Semantic Labels for Enhanced Group-level Emotion Recognitioncited by 1
  5. 2026LG-GER: Language-Guided Group Emotion Recognition via Multimodal Evidence Distillationcited by 0