Research map / Vision-language and multimodal / Human and embodied modeling
Discovering and Distinguishing Multiple Visual Senses for Polysemous Words
Yazhou Yao, Jian Zhang, Fumin Shen, Wankou Yang, Pu Huang, Zhenmin Tang
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 proposed sense discovery + MIL pipeline instead of SDCIT | visual sense classifiers · CMU-Poly-30 | classification accuracy: 0.839 -> 0.884 | Improved |
| use the proposed pipeline instead of SDCIT | visual sense classifiers · MIT-ISD | classification accuracy: 0.853 -> 0.897 | Improved |
| use the proposed pipeline instead of SDCIT for re-ranking | visual sense classifiers · bass and mouse re-ranking | average AUC: 0.636 -> 0.694 | Improved |
| use the proposed pipeline instead of SDCIT on the bass guitar sense | visual sense classifiers · bass guitar re-ranking | AUC: 0.773 -> 0.736 | Hurt |
Closest papers by meaning
- Vocabulary-free Image Classification (NeurIPS 2023 · similarity 0.84)
- Efficient Discovery and Effective Evaluation of Visual Perceptual Similarity: A Benchmark and Beyond (ICCV 2023 · similarity 0.84)
- Textual Knowledge Matters: Cross-Modality Co-Teaching for Generalized Visual Class Discovery (ECCV 2024 · similarity 0.84)
- Visual Word2Vec (vis-w2v): Learning Visually Grounded Word Embeddings Using Abstract Scenes (CVPR 2016 · similarity 0.84)
- The Many Senses of Visual Similarity: A Text-Prompted Image Perceptual Metric (NeurIPS 2026 · similarity 0.83)
- An Image is Worth Multiple Words: Discovering Object Level Concepts using Multi-Concept Prompt Learning (ICML 2024 · similarity 0.83)
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.
