Mohammed Bennamoun

Attribute-Relation Guided Compositional Alignment for Weakly Supervised Referring Expression Comprehension

Learning Explicit Semantic-Spatial Synergy for Weakly Supervised Referring Image Segmentation

AdaRD-Key: Adaptive Relevance-Diversity Keyframe Sampling for Long-form Video Understanding

Boosting Skeleton-based Zero-Shot Action Recognition with Training-Free Test-Time Adaptation

Watch and Listen: Understanding Audio-Visual-Speech Moments with Multimodal LLM

GeoPixel: Pixel Grounding Large Multimodal Model in Remote Sensing