search

MedChaabane / DEFT

Joint detection and tracking model named DEFT, or ``Detection Embeddings for Tracking." Our approach relies on an appearance-based object matching network jointly-learned with an underlying object detection network. An LSTM is also added to capture motion constraints.
MIT License
269 stars 43 forks source link

Inference #2

Closed AlexeySrus closed 3 years ago

AlexeySrus commented 3 years ago

Could you provide model inference example (on frames series or video)?

Best regards

MedChaabane commented 3 years ago

Thanks for you request. That's good suggestion. We will work on adding a code for demo on any video. Thanks,