Research map / Detection and segmentation / Open-set and few-shot detection
Goal-Oriented Gaze Estimation for Zero-Shot Learning
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Add goal-oriented attribute localization and gaze estimation (ablation) | GEM-ZSL · CUB | ZSL T1: 67.8 -> 77.8 | Helped |
| Add goal-oriented attribute localization and gaze estimation (ablation) | GEM-ZSL · SUN | ZSL T1: 54.7 -> 62.8 | Helped |
| Add goal-oriented attribute localization and gaze estimation (ablation) | GEM-ZSL · AWA2 | ZSL T1: 63.5 -> 67.3 | Helped |
| Add attribute MSE supervision (ablation) | GEM-ZSL · CUB | ZSL T1: 67.8 -> 69.9 | Helped |
| Add attribute MSE supervision (ablation) | GEM-ZSL · SUN | ZSL T1: 54.7 -> 56.1 | Helped |
| Add attribute MSE supervision (ablation) | GEM-ZSL · AWA2 | ZSL T1: 63.5 -> 64.3 | Helped |
| Add attention-map distance loss (ablation) | GEM-ZSL with MSE supervision · CUB | ZSL T1: 69.9 -> 70.5 | Helped |
| Add attention-map distance loss (ablation) | GEM-ZSL with MSE supervision · SUN | ZSL T1: 56.1 -> 56.9 | Helped |
| Add attention-map distance loss (ablation) | GEM-ZSL with MSE supervision · AWA2 | ZSL T1: 64.3 -> 64.6 | Helped |
| Use cosine similarity instead of dot product (ablation) | GEM-ZSL with attribute losses · CUB | ZSL T1: 70.5 -> 77.8 | Helped |
| Use cosine similarity instead of dot product (ablation) | GEM-ZSL with attribute losses · SUN | ZSL T1: 56.9 -> 62.8 | Helped |
| Use cosine similarity instead of dot product (ablation) | GEM-ZSL with attribute losses · AWA2 | ZSL T1: 64.6 -> 67.3 | Helped |
Closest papers by meaning
- Gaze Embeddings for Zero-Shot Image Classification (CVPR 2017 · similarity 0.90)
- ZeroMamba: Exploring Visual State Space Model for Zero-Shot Learning (AAAI 2025 · similarity 0.85)
- Gaze-LLE: Gaze Target Estimation via Large-Scale Learned Encoders (CVPR 2025 · similarity 0.84)
- ZeroDiff: Solidified Visual-semantic Correlation in Zero-Shot Learning (ICLR 2025 · similarity 0.84)
- Learning from Observer Gaze: Zero-Shot Attention Prediction Oriented by Human-Object Interaction Recognition (CVPR 2024 · similarity 0.84)
- Toward Semantic Gaze Target Detection (NeurIPS 2024 · similarity 0.84)
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.