Picture for Mahmoud Azab

Mahmoud Azab

CompCap: Improving Multimodal Large Language Models with Composite Captions

Add code
Dec 06, 2024
Viaarxiv icon

Normalized Contrastive Learning for Text-Video Retrieval

Add code
Nov 30, 2022
Viaarxiv icon

Fighting FIRe with FIRE: Assessing the Validity of Text-to-Video Retrieval Benchmarks

Add code
Oct 10, 2022
Figure 1 for Fighting FIRe with FIRE: Assessing the Validity of Text-to-Video Retrieval Benchmarks
Figure 2 for Fighting FIRe with FIRE: Assessing the Validity of Text-to-Video Retrieval Benchmarks
Figure 3 for Fighting FIRe with FIRE: Assessing the Validity of Text-to-Video Retrieval Benchmarks
Figure 4 for Fighting FIRe with FIRE: Assessing the Validity of Text-to-Video Retrieval Benchmarks
Viaarxiv icon

A Comparative Analysis of Content-based Geolocation in Blogs and Tweets

Add code
Nov 19, 2018
Figure 1 for A Comparative Analysis of Content-based Geolocation in Blogs and Tweets
Figure 2 for A Comparative Analysis of Content-based Geolocation in Blogs and Tweets
Figure 3 for A Comparative Analysis of Content-based Geolocation in Blogs and Tweets
Figure 4 for A Comparative Analysis of Content-based Geolocation in Blogs and Tweets
Viaarxiv icon

Speaker Naming in Movies

Add code
Sep 24, 2018
Figure 1 for Speaker Naming in Movies
Figure 2 for Speaker Naming in Movies
Figure 3 for Speaker Naming in Movies
Figure 4 for Speaker Naming in Movies
Viaarxiv icon