Search Results for author: Ofri Kleinfeld

Found 3 papers, 1 papers with code

Text2Topic: Multi-Label Text Classification System for Efficient Topic Detection in User Generated Content with Zero-Shot Capabilities

no code implementations23 Oct 2023 Fengjun Wang, Moran Beladev, Ofri Kleinfeld, Elina Frayerman, Tal Shachar, Eran Fainman, Karen Lastmann Assaraf, Sarai Mizrachi, Benjamin Wang

We propose Text to Topic (Text2Topic), which achieves high multi-label classification performance by employing a Bi-Encoder Transformer architecture that utilizes concatenation, subtraction, and multiplication of embeddings on both text and topic.

Decision Making Multi-Label Classification +3

Learning Object Permanence from Video

1 code implementation ECCV 2020 Aviv Shamsian, Ofri Kleinfeld, Amir Globerson, Gal Chechik

The fourth subtask, where a target object is carried by a containing object, is particularly challenging because it requires a system to reason about a moving location of an invisible object.

Object Video Object Tracking

Cannot find the paper you are looking for? You can Submit a new open access paper.