Mohsen Fayyaz

3

Papers

31

Total Citations

Papers (3)

MRAG-Bench: Vision-Centric Evaluation for Retrieval-Augmented Multimodal Models

Enhancing Temporal Understanding in Video-LLMs through Stacked Temporal Attention in Vision Encoders

Occlusion Handling in 3D Human Pose Estimation with Perturbed Positional Encoding