Research map / Video / Video-language understanding
Video2vec Embeddings Recognize Events When Examples Are Scarce
Amirhossein Habibian, Thomas Mensink, Cees G. M. Snoek
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 VideoStory embedding instead of low-level features | event classifier · MED 2013 | mAP: 28.1 -> 32.4 | Improved |
| use VideoStory embedding instead of ImageNet attributes | event classifier · MED 2014 | mAP: 17.2 -> 24.2 | Improved |
| use VideoStory embedding instead of term attributes (no embedding) (ablation) | few-example recognition · MED 2013, 2014, CCV10 | mAP | Improved |
| use VideoStory instead of CCA or description embedding (ablation) | embedding · MED 2013, 2014, CCV10 | mAP | Improved |
| add motion then audio modalities to VideoStoryF (ablation) | VideoStoryF · CCV10 | mAP: 54.8 -> 58.2 -> 59.3 | Improved |
| learn embedding jointly over modalities (VideoStoryF) instead of late fusion (ablation) | VideoStory · MED 2013 | mAP: 33.6 -> 37.1 | Improved |
| learn embedding jointly over modalities (VideoStoryF) instead of early fusion on low-level features (ablation) | VideoStory · CCV10 | mAP: 56.3 -> 59.3 | Improved |
| add term sensitive descriptiveness loss (ablation) | VideoStory0 · MED 2013 | zero-example mAP: 15.9 -> 18.3 | Improved |
| add multimodal predictability loss on top of term sensitive loss (ablation) | VideoStoryF0 · MED 2013 | zero-example mAP: 18.3 -> 20.0 | Improved |
| add multimodal predictability loss on top of term sensitive loss (ablation) | VideoStoryF0 · MED 2014 | zero-example mAP: 6.8 -> 8.0 | Improved |
| use plain VideoStory (LSI loss) instead of term attributes-f for zero examples (ablation) | VideoStory · MED 2014 | zero-example mAP: 5.0 -> 5.2 | No clear effect |
| increase positive training examples from 10 to 100 (ablation) | VideoStory vs low-level · MED 2013, CCV10 | mAP | Mixed |
Closest papers by meaning
- Unified Embedding and Metric Learning for Zero-Exemplar Event Detection (CVPR 2017 · similarity 0.90)
- They Are Not Equally Reliable: Semantic Event Search Using Differentiated Concept Classifiers (CVPR 2016 · similarity 0.89)
- Leveraging Weak Semantic Relevance for Complex Video Event Classification (ICCV 2017 · similarity 0.88)
- Zero-Shot Event Detection by Multimodal Distributional Semantic Embedding of Videos (AAAI 2016 · similarity 0.88)
- Dynamic Concept Composition for Zero-Example Event Detection (AAAI 2016 · similarity 0.87)
- Event-Equalized Dense Video Captioning (CVPR 2025 · similarity 0.85)
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.
