Search Results for author:
Found 5 papers, 3 papers with code
Boosting Box-supervised Instance Segmentation with Pseudo Depth
This innovative approach empowers the network to simultaneously predict masks and depth, enhancing its ability to capture nuanced depth-related information during the instance segmentation process.
De novo protein design using geometric vector field networks
Most prior encoders rely on atom-wise features, such as angles and distances between atoms, which are not available in this context.
CTVIS: Consistent Training for Online Video Instance Segmentation
The discrimination of instance embeddings plays a vital role in associating instances across time for online video instance segmentation (VIS).
Ranked #2 on
Video Instance Segmentation
on Youtube-VIS 2022 Validation
(using extra training data)
Asymmetric Cross-Scale Alignment for Text-Based Person Search
To implement this task, one needs to extract multi-scale features from both image and text domains, and then perform the cross-modal alignment.
T-Person-GAN: Text-to-Person Image Generation with Identity-Consistency and Manifold Mix-Up
Our architecture is orthogonal to StackGAN++ , and focuses on person image generation, with all of them together to enrich the spectrum of GANs for the image generation task.
