Yong Z
Yong Z
Dear author, It seems these codes don't work for multiple GPUs. ``` nn.parallel.data_parallel(netG.sample_videos, st_inputs, self.gpus) nn.parallel.data_parallel(netG.sample_images, im_inputs, self.gpus) ``` It prompts `AttributeError: 'function' object has no attribute 'parameters'`. (There is...
## ❓ Questions and Help Hi, is the code for visualizing the feature space (Figure 4) in this repo? I didn't see it. Thanks.
``` sng_parser.tprint(sng_parser.parse('the chair is in front of the desk')) Entities: +--------+-----------+-------------+ | Head | Span | Modifiers | |--------+-----------+-------------| | chair | the chair | the | | desk |...
## ❓ Questions and Help Dear author, thanks for your attention. I compared the reported results here https://github.com/KaihuaTang/Scene-Graph-Benchmark.pytorch/blob/master/METRICS.md with your nice paper, and got confused for two observations: 1. Why...
Dear Dr. Sun, I’ve read your paper “PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume”. I am wandering how the pre-trained PWC-Net is compared to traditional method...
Dear author, I feel confused when seeing this results. Does it mean that those complex models using contextualization cannot even beat the simple statistical freq model?
 in file https://github.com/coldmanck/VidHOI/blob/master/vidor_eval.ipynb. We should not just skip these triplets. Instead, ap for these triplets should be set as 0.
Thanks for sharing the nice work! But I find the performance presented in the paper is very different with methods in "Action Genome: Actions as Compositions of Spatio-temporal Scene Graphs"...
I noticed that you manually added captions for KTH dataset. It still needs a lot of work. Could you please share the captions? Thank you very much!