Yunzhong Hou

Results 10 comments of Yunzhong Hou
trafficstars

Hi, Thank you for your interest. However, we have no official support for digits datasets using ADDA. The current [discriminator architecture](https://github.com/hou-yz/DA_visualization/blob/main/SFIT/models/classifier_shot.py#L143) in ADDA is designed for stronger classifiers like ResNet50...

thank you for your interest! please check out our other repo [MVDeTr](https://github.com/hou-yz/MVDeTr#architectures) and specify to use the conv architecture `python main.py -d wildtrack --world_feat conv`. this should return similar results...

please use the [MVDeTr](https://github.com/hou-yz/MVDeTr) repo instead of this one. this line `python main.py -d wildtrack --world_feat conv` refers to the `main.py` file in that repo.

thank you for your interest. yes, you can think of the color palette as representative colors for the image. please see [code](https://github.com/hou-yz/color_distillation/blob/4293206d1deb10540920e284159d430e041f5a50/color_distillation/models/color_cnn.py#L34) on how to reconstruct the RGB image using...

> 对了,我还有个问题就是,是直接将color_palette *255,就可以得到真实可视化的调色板吗?还是需要其他操作呢? 可以

Hi, Thank you for your question. In essence, the camera~.txt files provide 3d bounding boxes in both 3d coordinates and their 2d correspondences, both generated from unity. Sorry, but I...

thank you for your interest. this project was a while ago so I'm not 100% sure about the details. if I recall correctly, in Fig. 3 and Fig. 4, the...

Hi, Thank you for the feedback. For even a single frame, I would still use the MODA, MODP, precision, and recall metrics. Just make sure that your `gt.txt` only includes...

Hi, Thank you for your interest. The link seems to be alive from my computer. But if you still cannot access it, please try this [link](https://1drv.ms/u/c/dfb1b9d32643ecdc/EdzsQybTubEggN99QwEAAAABD7_rL25ylWBvflP441bLmw?e=GA3rLn). Let me know if...