mohammed guermal - Academia.edu (original) (raw)

mohammed guermal

Related Authors

Steven Pinker

Maurizio Forte

Armando Marques-Guedes

Fabio Cuzzolin

Roshan Chitrakar

Lev Manovich

Lev Manovich

Graduate Center of the City University of New York

Ferhat Bozkurt

Munish Jindal

Eduard Babulak

Dr GURNADHA GUPTA KOPPURAVURI

Uploads

Papers by mohammed guermal

Research paper thumbnail of THORN: Temporal Human-Object Relation Network for Action Recognition

ArXiv, 2022

Most action recognition models treat human activities as unitary events. However, human activitie... more Most action recognition models treat human activities as unitary events. However, human activities often follow a certain hierarchy. In fact, many human activities are compositional. Also, these actions are mostly human-object interactions. In this paper we propose to recognize human action by leveraging the set of interactions that define an action. In this work, we present an end-to-end network: THORN, that can leverage important human-object and object-object interactions to predict actions. This model is built on top of a 3D backbone network. The key components of our model are: 1) An object representation filter for modeling object. 2) An object relation reasoning module to capture object relations. 3) A classification layer to predict the action labels. To show the robustness of THORN, we evaluate it on EPIC-Kitchen55 and EGTEA Gaze+, two of the largest and most challenging first-person and human-object interaction datasets. THORN achieves state-of-the-art performance on both ...

Research paper thumbnail of THORN: Temporal Human-Object Relation Network for Action Recognition

ArXiv, 2022

Most action recognition models treat human activities as unitary events. However, human activitie... more Most action recognition models treat human activities as unitary events. However, human activities often follow a certain hierarchy. In fact, many human activities are compositional. Also, these actions are mostly human-object interactions. In this paper we propose to recognize human action by leveraging the set of interactions that define an action. In this work, we present an end-to-end network: THORN, that can leverage important human-object and object-object interactions to predict actions. This model is built on top of a 3D backbone network. The key components of our model are: 1) An object representation filter for modeling object. 2) An object relation reasoning module to capture object relations. 3) A classification layer to predict the action labels. To show the robustness of THORN, we evaluate it on EPIC-Kitchen55 and EGTEA Gaze+, two of the largest and most challenging first-person and human-object interaction datasets. THORN achieves state-of-the-art performance on both ...

Log In