-
ICCV21, Change is Everywhere: Single-Temporal Supervised Object Change Detection in Remote Sensing Imagery
RSE21, Building Damage Assessment for Rapid Disaster Response with a Deep Object-based Sem…
-
Congratulations on your new work!
I think the idea of iteratively refining the fusion using Recurrent Modulation Unit in RM-Depth is similar to the Recurrent Multi-Scale Feature Modulation in R-MS…
-
Thanks for sharing this great work. I am curious about the evaluation on EPFL fountain and Herzjesu dataset. It seems that you use this [script](https://github.com/jzhangbs/DTUeval-python) to evaluate…
-
Hello!
Could you please tell me which train/test split you used when reporting results in the paper.
I see hardcoded using of jsfusion split in AllInOne/datasets/msrvtt.py. So did you use only jsf…
-
大佬，你好，我最近在做插帧的工作，觉得RIFE效果很好，想问两个问题：
1）我在测试运动幅度较大的视频时，发现RIFE往往插不出运动大的物体部分，视频播放起来比较奇怪，不知道你对运动大的视频有什么处理建议吗？
2）我在测试XVFI算法时，看到他对运动大的物体插帧效果比较类似cv2.addweighted的效果，视频看起来连续些，不知道你用他的数据集[X4K1000FPS]做过训练finetun…
-
I've read your ICCV21 paper about "MOTSynth", I would like to know how to extract human mask from ScriptHookV?
-
hello，we re-implement your code and we can't reach the performance you show in the paper (example, 86.0 in ST-NM), can you show more detail between feature mapping and loss function which we find the …
-
@lamblin @eleniTriantafillou @vdumoulin Can you help to add these results to the leaderboard? Thanks!
### ***tri*-M**
```
triM_all_df = pd.DataFrame(
columns=['mean (%)', '95% CI', '# ep…
-
Hi, I test the result on classic5 and live1 in **gray** with pre-trained weight
However, I find some mistakes caused by **rgb2ycbcr** function
Here is my offline test result
![image](https:/…
-
Hi!
When I use for my own ViT model, the following problem has occurred:
torch.nn.modules.module.ModuleAttributeError: 'Linear' object has no attribute 'X'
I don't know why😢Could you please help …