GECS-Net: Geometric Embedding and Cross-Stage Network for Two-View Correspondence Learning This repository provides the official PyTorch implementation of GECS-Net (Geometric Embedding and Cross-Stage ...
Conversation Tracker A local desktop prototype: real AMI meeting transcripts become a growing, curved semantic thread. The default Future-aware thread uses token-budgeted passage context behind and ...
A speaker embedding model: audio in, a 256-dimensional voice print out. It is the WeSpeaker ResNet293 model, fine-tuned on short speech windows from the TV show "Survivor". It tells apart people in ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results