Research map / Video / Video segmentation and tracking
GeoStyle: Discovering Fashion Trends and Events
Utkarsh Mall, Kevin Matzen, Bharath Hariharan, Noah Snavely, Kavita Bala
Read the paperCheck 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 the full parametric model (linear plus cyclic terms) instead of linear only (ablation) | trend model · Attribute trends, next 26 weeks | MAE: 0.0365 -> 0.0145 | Improved |
| use the full model instead of sinusoid only (ablation) | trend model · Attribute trends, next 26 weeks | MAE: 0.0163 -> 0.0145 | Improved |
| use the full model instead of cyclic only (ablation) | trend model · Attribute trends, next 26 weeks | MAE: 0.0165 -> 0.0145 | Improved |
| use the full model instead of linear+sinusoid (ablation) | trend model · Attribute trends, next 26 weeks | MAE: 0.0169 -> 0.0145 | Improved |
| use the full model instead of cyclic only (ablation) | trend model · Attribute trends, next week | MAE: 0.0129 -> 0.0119 | Improved |
| use parametric model instead of linear only (ablation) | trend model · Style-cluster trends, next 26 weeks | MAE: 0.0135 -> 0.0077 | Improved |
| use parametric model instead of autoregression (up to 12x more parameters) | trend model · Attribute trends, next 26 weeks | MAE: 0.0207 -> 0.0145 | Improved |
| use parametric model instead of exponential smoothing | trend model · Attribute trends, next 26 weeks | MAPE: 20.59 -> 15.73 | Improved |
| use parametric model instead of VAR | trend model · Style-cluster trends, next 26 weeks | MAPE: 27.97 -> 21.78 | Improved |
| longer forecast horizon (next week to next 26 weeks) widens gap to baselines | trend model · Attribute trends | MAE: 0.0152 -> 0.0231 | Improved |
| add full model on unseen city Barcelona vs sinusoid+linear (ablation) | trend model · Barcelona unseen city | MAE: 0.043 -> 0.043 | No clear effect |
| use parametric model instead of Autoregression on unseen city | trend model · Barcelona unseen city | MAE: 0.047 -> 0.043 | Improved |
Closest papers by meaning
- From Paris to Berlin: Discovering Fashion Style Influences Around the World (CVPR 2020 · similarity 0.92)
- From Culture to Clothing: Discovering the World Events Behind a Century of Fashion Images (ICCV 2021 · similarity 0.90)
- Fashion Forward: Forecasting Visual Style in Fashion (ICCV 2017 · similarity 0.89)
- Fashionpedia: Ontology, Segmentation, and an Attribute Localization Dataset (ECCV 2020 · similarity 0.85)
- TexFit: Text-Driven Fashion Image Editing with Diffusion Models (AAAI 2024 · similarity 0.83)
- AIpparel: A Multimodal Foundation Model for Digital Garments (CVPR 2025 · similarity 0.80)
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.
