Thanh Nguyen

@hangxu124 I have not tried this so far. Hope having time to try it later.

@qiushenjie Just replace the B (in RGB) channel by D (depth image). Or pass RGB and DDD to 2 separate Networks, then concatenate the 2 feature maps which then are...

@ceng1027 Please read Sec. V. Experiments and evaluation/A. Grasp detection. You can use the rectangle metric: ". .. consider a predicted grasp to be correct if both: 1) within 30...

@VisionaryKai I assume that your robot arm has a vision system (a camera) either eye in hand or eye to hand. You should do calibration first, then you can transform...

Hi @sujitbiswas , Any update on this issue?

@zhunzhong07 If the algo requires q_q_dist, then it is not practical? In real-world application query is a track of images (multi-shot) and each person in the gallery also contains a...

Have you guys obtained the pretrained model as well as the test dataset yet? Can anyone share on OneDrive?

Hi @nodiz , Any progress on this?

Dear @jahongir7174 , Thanks for your information. Would you mind sharing your checkpoint so that I can check its (`tensorflow` to [OpenVINO](https://github.com/openvinotoolkit/openvino)) performance when converting to [OpenVINO](https://github.com/openvinotoolkit/openvino):, because I face...

Hi @gw-alibaba , Are you going to publish a paper about your methods?