Fahad Shahbaz Khan
25 papers · 1 citations
Most-cited papers
- Fine-tuned CLIP Models Are Efficient Video Learners2022 · 162 citations
- Composed Video Retrieval Via Enriched Context And Discriminative Embeddings2024 · 13 citations
- Beyond Simple Edits: Composed Video Retrieval With Dense Modifications2025
- Composed Object Retrieval: Object-level Retrieval Via Composed Expressions2025
- Come-vl: Scaling Complementary Multi-encoder Vision-language Learning2026
Top co-authors
Topics