insailab commited on
Commit
2464222
·
verified ·
1 Parent(s): 0ed778d

docs: add direct collection links to organization card

Browse files
Files changed (1) hide show
  1. README.md +19 -0
README.md CHANGED
@@ -81,6 +81,25 @@ hf download InSAI-Lab/Trans4PASS --local-dir ./workdirs
81
 
82
  ---
83
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
84
  ## 🔬 Recent Selected Publications
85
  - **IEEE T-PAMI 2026:** *OneBEV++: Towards Unifying Bird’s-Eye-View Semantic Mapping with Panoramas*
86
  - **CVPR 2026:** *More than the Sum: Panorama-Language Models for Adverse Omni-Scenes*
 
81
 
82
  ---
83
 
84
+ ### 3. [📚 Collection: ISSAFE & EDCNet (IROS 2021 & T-ITS 2021)](https://huggingface.co/collections/InSAI-Lab/issafe-and-edcnet-iros-2021-and-t-its-2021-6ad1b2429101a4c06509e4cb)
85
+ > **Event-based Semantic Segmentation in Accident Scenes**
86
+
87
+ Dynamic event-driven semantic segmentation for traffic accident scenes under extreme dynamics and motion blur, featuring the pixel-annotated DADA-seg benchmark.
88
+
89
+ | Resource | Hugging Face Repository | Description |
90
+ | :--- | :--- | :--- |
91
+ | 📦 **Dataset** | [`InSAI-Lab/DADA-seg`](https://huggingface.co/datasets/InSAI-Lab/DADA-seg) | Multimodal accident scene segmentation benchmark (448 MB) |
92
+ | 🤖 **Model Zoo** | [`InSAI-Lab/ISSAFE`](https://huggingface.co/InSAI-Lab/ISSAFE) | EDCNet and ISSAFE trained checkpoints |
93
+ | 📄 **Papers** | [arXiv:2008.08974](https://arxiv.org/abs/2008.08974) / [arXiv:2112.05006](https://arxiv.org/abs/2112.05006) | IROS 2021 & IEEE T-ITS 2021 |
94
+
95
+ ```bash
96
+ # Quick download via Hugging Face CLI
97
+ hf download InSAI-Lab/DADA-seg DADA-seg.tar.gz --type dataset --local-dir ./dataset
98
+ hf download InSAI-Lab/ISSAFE run/cityscapesevent/test_EDCNet_r18/model_best.pth --local-dir .
99
+ ```
100
+
101
+ ---
102
+
103
  ## 🔬 Recent Selected Publications
104
  - **IEEE T-PAMI 2026:** *OneBEV++: Towards Unifying Bird’s-Eye-View Semantic Mapping with Panoramas*
105
  - **CVPR 2026:** *More than the Sum: Panorama-Language Models for Adverse Omni-Scenes*