Research map / Continual learning / Online and replay-based
Structural Entropy Guided Incremental Learning for Open-World Multimodal Social Event Detection
Zhiwei Yang, Haimei Qin, Xiaoyan Yu, Hao Peng, Lei Jiang, Li Sun, Zhiqin Yang
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 SeInEvent instead of CLIP in closed-world MSED | CLIP · CrisisMMD closed world | ARI: .79 -> .80 | Improved |
| use SeInEvent instead of strongest baselines in open-world MSED | CLIP / HISEvent · NED open world M1-M7 | ARI: .64 -> .95 on M1 | Improved |
| use SeInEvent instead of CLIP on block M5 | CLIP · NED open world M5 | ARI: .86 -> .82 | Hurt |
| add PSE-based noise filter (ablation) | SeInEvent · NED open world (avg over blocks) | ARI/NMI/AMI | Improved |
| add bidirectional cross-attention between text and image (ablation) | SeInEvent ME-Encoder · NED open world (avg) | ARI/NMI/AMI | Improved |
| use learnable fusion instead of simple averaging (ablation) | SeInEvent ME-Encoder · NED open world (avg) | ARI/NMI/AMI | Improved |
| add incremental learning versus training only on initial block M0 (ablation) | SeEvent · NED open world over blocks | ARI/NMI/AMI | Improved |
| use Qwen2-VL (7B) instead of InstructBLIP (7B) to make positives (ablation) | SeInEvent · NED open world M7 | ARI: .32 -> .34 | No clear effect |
| use smaller MiniCPM-V2 (3B) instead of InstructBLIP (7B) to make positives (ablation) | SeInEvent · NED open world M1 | ARI: .95 -> .91 | Hurt |
| vary beta (distillation weight) and mu (filter strength) (ablation) | SeInEvent · NED open world | accuracy | Mixed |
Closest papers by meaning
- Hierarchical and Incremental Structural Entropy Minimization for Unsupervised Social Event Detection (AAAI 2024 · similarity 0.88)
- Towards Effective, Efficient and Unsupervised Social Event Detection in the Hyperbolic Space (AAAI 2025 · similarity 0.84)
- Beyond Grounding: Extracting Fine-Grained Event Hierarchies across Modalities (AAAI 2024 · similarity 0.82)
- Learning Complex Heterogeneous Multimodal Fake News via Social Latent Network Inference (AAAI 2025 · similarity 0.82)
- Reinforced Adaptive Knowledge Learning for Multimodal Fake News Detection (AAAI 2024 · similarity 0.82)
- Ghidorah: Towards Robust Multi-Scale Information Diffusion Prediction via Test-Time Training (AAAI 2025 · similarity 0.81)
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.
