Picture for Burak Satar

Burak Satar

Towards Debiasing Frame Length Bias in Text-Video Retrieval via Causal Intervention

Add code
Sep 17, 2023
Figure 1 for Towards Debiasing Frame Length Bias in Text-Video Retrieval via Causal Intervention
Figure 2 for Towards Debiasing Frame Length Bias in Text-Video Retrieval via Causal Intervention
Figure 3 for Towards Debiasing Frame Length Bias in Text-Video Retrieval via Causal Intervention
Figure 4 for Towards Debiasing Frame Length Bias in Text-Video Retrieval via Causal Intervention
Viaarxiv icon

An Overview of Challenges in Egocentric Text-Video Retrieval

Jun 07, 2023
Figure 1 for An Overview of Challenges in Egocentric Text-Video Retrieval
Figure 2 for An Overview of Challenges in Egocentric Text-Video Retrieval
Figure 3 for An Overview of Challenges in Egocentric Text-Video Retrieval
Figure 4 for An Overview of Challenges in Egocentric Text-Video Retrieval
Viaarxiv icon

Exploiting Semantic Role Contextualized Video Features for Multi-Instance Text-Video Retrieval EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2022

Jun 29, 2022
Figure 1 for Exploiting Semantic Role Contextualized Video Features for Multi-Instance Text-Video Retrieval EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2022
Figure 2 for Exploiting Semantic Role Contextualized Video Features for Multi-Instance Text-Video Retrieval EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2022
Viaarxiv icon

Semantic Role Aware Correlation Transformer for Text to Video Retrieval

Jun 26, 2022
Figure 1 for Semantic Role Aware Correlation Transformer for Text to Video Retrieval
Figure 2 for Semantic Role Aware Correlation Transformer for Text to Video Retrieval
Viaarxiv icon

RoME: Role-aware Mixture-of-Expert Transformer for Text-to-Video Retrieval

Jun 26, 2022
Figure 1 for RoME: Role-aware Mixture-of-Expert Transformer for Text-to-Video Retrieval
Figure 2 for RoME: Role-aware Mixture-of-Expert Transformer for Text-to-Video Retrieval
Figure 3 for RoME: Role-aware Mixture-of-Expert Transformer for Text-to-Video Retrieval
Figure 4 for RoME: Role-aware Mixture-of-Expert Transformer for Text-to-Video Retrieval
Viaarxiv icon

Deep Learning Based Vehicle Make-Model Classification

Aug 23, 2018
Figure 1 for Deep Learning Based Vehicle Make-Model Classification
Figure 2 for Deep Learning Based Vehicle Make-Model Classification
Figure 3 for Deep Learning Based Vehicle Make-Model Classification
Figure 4 for Deep Learning Based Vehicle Make-Model Classification
Viaarxiv icon