Research map / Vision-language and multimodal / CLIP and zero-shot
Zero-Shot Event Detection by Multimodal Distributional Semantic Embedding of Videos
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 |
|---|---|---|---|
| use GoogleNews embedding instead of Wikipedia embedding (ablation) | EDiSE · MED13 concept set G1 | MAP (%): 3.14% -> 4.29 | Helped |
| use max pooling instead of average pooling (ablation) | EDiSE · MED13 concept set G1 | MAP (%): 2.39% -> 4.29 | Helped |
| use sum-pooled cosine s_p instead of Hausdorff s_t (ablation) | EDiSE · MED13 concept set G1 | MAP (%): 3.94% -> 4.29 | Helped |
| use semantic embedding instead of string matching for OCR (ablation) | EDiSE · MED13 | MAP: 1.8% -> 4.81% | Helped |
| use semantic embedding instead of string matching for ASR (ablation) | EDiSE · MED13 | MAP: 3.77% -> 4.23% | Helped |
| add action and scene concepts to Overfeat object concepts (ablation) | EDiSE · MED13 full concept set | MAP: 2.43% -> 8.36% | Helped |
| fuse concepts with ASR and OCR (ablation) | EDiSE · MED13 | MAP: 8.36% -> 13.1% | Helped |
| fuse concepts with ASR and OCR (ablation) | EDiSE · MED13 | ROC-AUC: 0.834 -> 0.830 | No clear effect |
| add SPaR reranking on top of EDiSE (ablation) | EDiSE · MED13 | MAP: 13.1% -> 13.5% | Helped |
| add SPaR reranking on top of EDiSE (ablation) | EDiSE · MED13 | ROC-AUC: 0.83 -> 0.79 | Hurt |
| use audio concepts trained on MFCC features (ablation) | EDiSE · MED13 | MAP: approx 1% MAP | Hurt |
Closest papers by meaning
- Streaming Detection of Queried Event Start (NeurIPS 2024 · similarity 0.87)
- Text-Infused Attention and Foreground-Aware Modeling for Zero-Shot Temporal Action Detection (NeurIPS 2024 · similarity 0.86)
- EZSR: Event-based Zero-Shot Recognition (CVPR 2025 · similarity 0.85)
- Does Video-Text Pretraining Help Open-Vocabulary Online Action Detection? (NeurIPS 2024 · similarity 0.85)
- Beyond Grounding: Extracting Fine-Grained Event Hierarchies across Modalities (AAAI 2024 · similarity 0.85)
- Building a Multi-modal Spatiotemporal Expert for Zero-shot Action Recognition with CLIP (AAAI 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.