Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Concepts Not Alone: Exploring Pairwise Relationships for Zero-Shot Video Activity Recognition
Read the paperCheck 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 reliability and discriminative concept filtering to word2vec concept selection (ablation) | Query interpretation · MED13test | mAP (%): 14.4 -> 16.9 | Helped |
| add reliability and discriminative concept filtering to word2vec concept selection (ablation) | Query interpretation · MED14test | mAP (%): 13.8 -> 16.5 | Helped |
| replace score averaging (Basic) with pairwise order matrix low-rank aggregation plus filtering (ablation) | zero-shot event detection · MED13test | mAP (%): 14.4 -> 16.9 | Helped |
| pairwise order aggregation under added random noise ranking (ablation) | zero-shot event detection · MED13test | mAP (%): Basic 14.4 -> 10.6; Ours 16.9 -> 15.7 | Helped |
| pairwise order aggregation under added random noise ranking (ablation) | zero-shot event detection · MED14test | mAP (%): Basic 13.8 -> 11.2; Ours 16.5 -> 15.2 | Helped |
| ours versus attribute-based approach on per-event AP | zero-shot event detection · MED14test per-event | AP: better on 18 of 20 events | Mixed |
Closest papers by meaning
- DECK: Discovering Event Composition Knowledge from Web Images for Zero-Shot Event Detection and Recounting in Videos (AAAI 2017 · similarity 0.88)
- Unified Embedding and Metric Learning for Zero-Exemplar Event Detection (CVPR 2017 · similarity 0.88)
- Dynamic Concept Composition for Zero-Example Event Detection (AAAI 2016 · similarity 0.87)
- Zero-Shot Event Detection by Multimodal Distributional Semantic Embedding of Videos (AAAI 2016 · similarity 0.87)
- VicTR: Video-conditioned Text Representations for Activity Recognition (CVPR 2024 · similarity 0.85)
- Text-Infused Attention and Foreground-Aware Modeling for Zero-Shot Temporal Action Detection (NeurIPS 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.