You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
As for part 3: Curating OpenVid-1M, Motion Difference module, the paper says "We introduce UniMatch [27] to evaluate optical flow score as the motion difference score to select videos with smooth movement". However, UniMatch[27] is a image semantic segmentation method, how it can be used for optical flow?
[27]Lihe Yang, Lei Qi, Litong Feng, Wayne Zhang, and Yinghuan Shi. Revisiting weak-to-strong consistency in
semi-supervised semantic segmentation. In IEEE Conference on Computer Vision and Pattern Recognition.
IEEE, 2023.
The text was updated successfully, but these errors were encountered:
As for part 3: Curating OpenVid-1M, Motion Difference module, the paper says "We introduce UniMatch [27] to evaluate optical flow score as the motion difference score to select videos with smooth movement". However, UniMatch[27] is a image semantic segmentation method, how it can be used for optical flow?
[27]Lihe Yang, Lei Qi, Litong Feng, Wayne Zhang, and Yinghuan Shi. Revisiting weak-to-strong consistency in semi-supervised semantic segmentation. In IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 2023.
Thanks for your attention. We use UniMatch [27] to evaluate optical flow score. We have fixed it and added some new content in an updated version of paper, which will be released soon.
[27] Haofei Xu, Jing Zhang, Jianfei Cai, Hamid Rezatofighi, Fisher Yu, Dacheng Tao, and Andreas Geiger. Unifying flow, stereo and depth estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023. 10
As for part 3: Curating OpenVid-1M, Motion Difference module, the paper says "We introduce UniMatch [27] to evaluate optical flow score as the motion difference score to select videos with smooth movement". However, UniMatch[27] is a image semantic segmentation method, how it can be used for optical flow?
[27]Lihe Yang, Lei Qi, Litong Feng, Wayne Zhang, and Yinghuan Shi. Revisiting weak-to-strong consistency in
semi-supervised semantic segmentation. In IEEE Conference on Computer Vision and Pattern Recognition.
IEEE, 2023.
The text was updated successfully, but these errors were encountered: