Alert button
Picture for Santiago Castro

Santiago Castro

Alert button

CLoVe: Encoding Compositional Language in Contrastive Vision-Language Models

Mar 01, 2024
Santiago Castro, Amir Ziai, Avneesh Saluja, Zhuoning Yuan, Rada Mihalcea

Viaarxiv icon

Human Action Co-occurrence in Lifestyle Vlogs using Graph Link Prediction

Sep 22, 2023
Oana Ignat, Santiago Castro, Weiji Li, Rada Mihalcea

Figure 1 for Human Action Co-occurrence in Lifestyle Vlogs using Graph Link Prediction
Figure 2 for Human Action Co-occurrence in Lifestyle Vlogs using Graph Link Prediction
Figure 3 for Human Action Co-occurrence in Lifestyle Vlogs using Graph Link Prediction
Figure 4 for Human Action Co-occurrence in Lifestyle Vlogs using Graph Link Prediction
Viaarxiv icon

Scalable Performance Analysis for Vision-Language Models

May 31, 2023
Santiago Castro, Oana Ignat, Rada Mihalcea

Figure 1 for Scalable Performance Analysis for Vision-Language Models
Figure 2 for Scalable Performance Analysis for Vision-Language Models
Figure 3 for Scalable Performance Analysis for Vision-Language Models
Figure 4 for Scalable Performance Analysis for Vision-Language Models
Viaarxiv icon

A PhD Student's Perspective on Research in NLP in the Era of Very Large Language Models

May 21, 2023
Oana Ignat, Zhijing Jin, Artem Abzaliev, Laura Biester, Santiago Castro, Naihao Deng, Xinyi Gao, Aylin Gunal, Jacky He, Ashkan Kazemi, Muhammad Khalifa, Namho Koh, Andrew Lee, Siyang Liu, Do June Min, Shinka Mori, Joan Nwatu, Veronica Perez-Rosas, Siqi Shen, Zekun Wang, Winston Wu, Rada Mihalcea

Viaarxiv icon

Phenaki: Variable Length Video Generation From Open Domain Textual Description

Oct 05, 2022
Ruben Villegas, Mohammad Babaeizadeh, Pieter-Jan Kindermans, Hernan Moraldo, Han Zhang, Mohammad Taghi Saffar, Santiago Castro, Julius Kunze, Dumitru Erhan

Figure 1 for Phenaki: Variable Length Video Generation From Open Domain Textual Description
Figure 2 for Phenaki: Variable Length Video Generation From Open Domain Textual Description
Figure 3 for Phenaki: Variable Length Video Generation From Open Domain Textual Description
Figure 4 for Phenaki: Variable Length Video Generation From Open Domain Textual Description
Viaarxiv icon

WildQA: In-the-Wild Video Question Answering

Sep 14, 2022
Santiago Castro, Naihao Deng, Pingxuan Huang, Mihai Burzo, Rada Mihalcea

Figure 1 for WildQA: In-the-Wild Video Question Answering
Figure 2 for WildQA: In-the-Wild Video Question Answering
Figure 3 for WildQA: In-the-Wild Video Question Answering
Figure 4 for WildQA: In-the-Wild Video Question Answering
Viaarxiv icon

FitCLIP: Refining Large-Scale Pretrained Image-Text Models for Zero-Shot Video Understanding Tasks

Mar 24, 2022
Santiago Castro, Fabian Caba Heilbron

Figure 1 for FitCLIP: Refining Large-Scale Pretrained Image-Text Models for Zero-Shot Video Understanding Tasks
Figure 2 for FitCLIP: Refining Large-Scale Pretrained Image-Text Models for Zero-Shot Video Understanding Tasks
Figure 3 for FitCLIP: Refining Large-Scale Pretrained Image-Text Models for Zero-Shot Video Understanding Tasks
Figure 4 for FitCLIP: Refining Large-Scale Pretrained Image-Text Models for Zero-Shot Video Understanding Tasks
Viaarxiv icon

When Did It Happen? Duration-informed Temporal Localization of Narrated Actions in Vlogs

Feb 21, 2022
Oana Ignat, Santiago Castro, Yuhang Zhou, Jiajun Bao, Dandan Shan, Rada Mihalcea

Figure 1 for When Did It Happen? Duration-informed Temporal Localization of Narrated Actions in Vlogs
Figure 2 for When Did It Happen? Duration-informed Temporal Localization of Narrated Actions in Vlogs
Figure 3 for When Did It Happen? Duration-informed Temporal Localization of Narrated Actions in Vlogs
Figure 4 for When Did It Happen? Duration-informed Temporal Localization of Narrated Actions in Vlogs
Viaarxiv icon