Research map / Detection and segmentation / CNN features
End-to-End Human-Gaze-Target Detection With Transformers
Danyang Tu, Xiongkuo Min, Huiyu Duan, Guodong Guo, Guangtao Zhai, Wei Shen
Check your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use HGTTR with ResNet-50 instead of VideoAttention | GazeFollowing (Real) · GazeFollowing (Real) | mAP: 6.4 mAP gain | Improved |
| use HGTTR instead of VideoAttention | VideoAttentionTarget · VideoAttentionTarget | mAP: 10.3 mAP gain | Improved |
| use HGTTR with ResNet-101 instead of DAM | VideoAttentionTarget (Real) · VideoAttentionTarget (Real) | L2 Dist.: 0.108 -> 0.126 | Hurt |
| set matching weights to β1=2, β2=1, β3=1, β4=2 rather than equal weights (ablation) | HGTTR · VideoAttentionTarget | AUC: 0.864 -> 0.893 | Improved |
| set matching weights to β1=2, β2=1, β3=1, β4=2 rather than equal weights (ablation) | HGTTR · VideoAttentionTarget | L2 Dist.: 0.142 -> 0.137 | Improved |
| set matching weights to β1=2, β2=1, β3=1, β4=2 rather than equal weights (ablation) | HGTTR · VideoAttentionTarget | mAP: 0.492 -> 0.514 | Improved |
| increase classification matching-cost weights relative to localization (ablation) | HGTTR · VideoAttentionTarget | AUC: 0.893 -> 0.857 | Hurt |
| increase classification matching-cost weights relative to localization (ablation) | HGTTR · VideoAttentionTarget | L2 Dist.: 0.137 -> 0.148 | Hurt |
| increase classification matching-cost weights relative to localization (ablation) | HGTTR · VideoAttentionTarget | mAP: 0.514 -> 0.487 | Hurt |
| increase the number of decoder layers (ablation) | HGTTR · VideoAttentionTarget | AUC | Improved |
| increase the number of decoder layers (ablation) | HGTTR · VideoAttentionTarget | L2 Dist. | Improved |
| fine-tune the head detector with distortion-augmented training data (ablation) | HGTTR · VideoAttentionTarget (Blur) | AUC: 0.806 -> 0.872 | Improved |
Closest papers by meaning
- Gaze Target Detection by Merging Human Attention and Activity Cues (AAAI 2024 · similarity 0.89)
- Toward Semantic Gaze Target Detection (NeurIPS 2024 · similarity 0.89)
- MTGS: A Novel Framework for Multi-Person Temporal Gaze Following and Social Gaze Prediction (NeurIPS 2024 · similarity 0.88)
- Gaze-LLE: Gaze Target Estimation via Large-Scale Learned Encoders (CVPR 2025 · similarity 0.87)
- Sharingan: A Transformer Architecture for Multi-Person Gaze Following (CVPR 2024 · similarity 0.87)
- TransGOP: Transformer-Based Gaze Object Prediction (AAAI 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
