Paola Cascante-Bonilla

33 papers A* 9A 1Journal 19Unranked 4
YearRankTypeTitle / Venue / Authors
2026 J jnl
Do VLMs Need Vision Transformers? Evaluating State Space Models as Vision Encoders.
CoRR
Shang-Jui Ray Kuo, Paola Cascante-Bonilla
2026 J jnl
EgoGroups: A Benchmark For Detecting Social Groups of People in the Wild.
CoRR
Jeffri Murrugarra-Llerena, Pranav Chitale, Zicheng Liu, Kai Ao, Yujin Ham, Guha Balakrishnan, Paola Cascante-Bonilla
2025 J jnl
Beyond Blanket Masking: Examining Granularity for Privacy Protection in Images Captured by Blind and Low Vision Users.
CoRR
Jeffri Murrugarra-Llerena, Haoran Niu, K. Suzanne Barber, Hal Daumé III, Yang Trista Cao, Paola Cascante-Bonilla
2025 — conf
Can Hallucination Correction Improve Video-Language Alignment?
ACL (Findings)
Lingjun Zhao, Mingyang Xie, Paola Cascante-Bonilla, Hal Daumé III, Kwonjoon Lee
2025 J jnl
Can Hallucination Correction Improve Video-Language Alignment?
CoRR
Lingjun Zhao, Mingyang Xie, Paola Cascante-Bonilla, Hal Daumé III, Kwonjoon Lee
2025 A* conf
Natural Language Inference Improves Compositionality in Vision-Language Models.
ICLR
Paola Cascante-Bonilla, Yu Hou, Yang Trista Cao, Hal Daumé III, Rachel Rudinger
2024 — conf
Grounding Language Models for Visual Entity Recognition.
ECCV (11)
Zilin Xiao, Ming Gong, Paola Cascante-Bonilla, Xingyao Zhang, Jie Wu, Vicente Ordonez
2024 J jnl
Grounding Language Models for Visual Entity Recognition.
CoRR
Zilin Xiao, Ming Gong, Paola Cascante-Bonilla, Xingyao Zhang, Jie Wu, Vicente Ordonez
2024 A* conf
Improved Visual Grounding through Self-Consistent Explanations.
CVPR
Ruozhen He, Paola Cascante-Bonilla, Ziyan Yang, Alexander C. Berg, Vicente Ordonez
2024 J jnl
Learning from Models and Data for Visual Grounding.
CoRR
Ruozhen He, Paola Cascante-Bonilla, Ziyan Yang, Alexander C. Berg, Vicente Ordonez
2024 J jnl
Natural Language Inference Improves Compositionality in Vision-Language Models.
CoRR
Paola Cascante-Bonilla, Yu Hou, Yang Trista Cao, Hal Daumé III, Rachel Rudinger
2024 — conf
PropTest: Automatic Property Testing for Improved Visual Programming.
EMNLP (Findings)
Jaywon Koo, Ziyan Yang, Paola Cascante-Bonilla, Baishakhi Ray, Vicente Ordonez
2024 J jnl
PropTest: Automatic Property Testing for Improved Visual Programming.
CoRR
Jaywon Koo, Ziyan Yang, Paola Cascante-Bonilla, Baishakhi Ray, Vicente Ordonez
2023 A* conf
CODA-Prompt: COntinual Decomposed Attention-Based Prompting for Rehearsal-Free Continual Learning.
CVPR
James Seale Smith, Leonid Karlinsky, Vyshnavi Gutta, Paola Cascante-Bonilla, Donghyun Kim, Assaf Arbelle, Rameswar Panda, Rogério Feris, Zsolt Kira
2023 A* conf
ConStruct-VL: Data-Free Continual Structured VL Concepts Learning.
CVPR
James Seale Smith, Paola Cascante-Bonilla, Assaf Arbelle, Donghyun Kim, Rameswar Panda, David D. Cox, Diyi Yang, Zsolt Kira, Rogério Feris, Leonid Karlinsky
2023 A* conf
Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models.
NeurIPS
Sivan Doveh, Assaf Arbelle, Sivan Harary, Roei Herzig, Donghyun Kim, Paola Cascante-Bonilla, Amit Alfassy, Rameswar Panda, Raja Giryes, Rogério Feris, Shimon Ullman, Leonid Karlinsky
2023 J jnl
Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models.
CoRR
Sivan Doveh, Assaf Arbelle, Sivan Harary, Roei Herzig, Donghyun Kim, Paola Cascante-Bonilla, Amit Alfassy, Rameswar Panda, Raja Giryes, Rogério Feris, Shimon Ullman, Leonid Karlinsky
2023 A* conf
Going Beyond Nouns With Vision & Language Models Using Synthetic Data.
ICCV
Paola Cascante-Bonilla, Khaled Shehada, James Seale Smith, Sivan Doveh, Donghyun Kim, Rameswar Panda, Gül Varol, Aude Oliva, Vicente Ordonez, Rogério Feris, Leonid Karlinsky
2023 J jnl
Going Beyond Nouns With Vision & Language Models Using Synthetic Data.
CoRR
Paola Cascante-Bonilla, Khaled Shehada, James Seale Smith, Sivan Doveh, Donghyun Kim, Rameswar Panda, Gül Varol, Aude Oliva, Vicente Ordonez, Rogério Feris, Leonid Karlinsky
2023 J jnl
Improved Visual Grounding through Self-Consistent Explanations.
CoRR
Ruozhen He, Paola Cascante-Bonilla, Ziyan Yang, Alexander C. Berg, Vicente Ordonez
2022 J jnl
CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning.
CoRR
James Seale Smith, Leonid Karlinsky, Vyshnavi Gutta, Paola Cascante-Bonilla, Donghyun Kim, Assaf Arbelle, Rameswar Panda, Rogério Feris, Zsolt Kira
2022 J jnl
ConStruct-VL: Data-Free Continual Structured VL Concepts Learning.
CoRR
James Seale Smith, Paola Cascante-Bonilla, Assaf Arbelle, Donghyun Kim, Rameswar Panda, David D. Cox, Diyi Yang, Zsolt Kira, Rogério Feris, Leonid Karlinsky
2022 J jnl
On the Transferability of Visual Features in Generalized Zero-Shot Learning.
CoRR
Paola Cascante-Bonilla, Leonid Karlinsky, James Seale Smith, Yanjun Qi, Vicente Ordonez
2022 A* conf
Sim VQA: Exploring Simulated Environments for Visual Question Answering.
CVPR
Paola Cascante-Bonilla, Hui Wu, Letao Wang, Rogério Feris, Vicente Ordonez
2022 J jnl
SimVQA: Exploring Simulated Environments for Visual Question Answering.
CoRR
Paola Cascante-Bonilla, Hui Wu, Letao Wang, Rogério Feris, Vicente Ordonez
2021 A* conf
Curriculum Labeling: Revisiting Pseudo-Labeling for Semi-Supervised Learning.
AAAI
Paola Cascante-Bonilla, Fuwen Tan, Yanjun Qi, Vicente Ordonez
2021 A conf
Evolving Image Compositions for Feature Representation Learning.
BMVC
Paola Cascante-Bonilla, Arshdeep Sekhon, Yanjun Qi, Vicente Ordonez
2021 J jnl
Evolving Image Compositions for Feature Representation Learning.
CoRR
Paola Cascante-Bonilla, Arshdeep Sekhon, Yanjun Qi, Vicente Ordonez
2020 J jnl
Curriculum Labeling: Self-paced Pseudo-Labeling for Semi-Supervised Learning.
CoRR
Paola Cascante-Bonilla, Fuwen Tan, Yanjun Qi, Vicente Ordonez
2019 — conf
Chat-crowd: A Dialog-based Platform for Visual Layout Composition.
NAACL-HLT (Demonstrations)
Paola Cascante-Bonilla, Xuwang Yin, Vicente Ordonez, Song Feng
2019 A* conf
Drill-down: Interactive Retrieval of Complex Scenes using Natural Language Queries.
NeurIPS
Fuwen Tan, Paola Cascante-Bonilla, Xiaoxiao Guo, Hui Wu, Song Feng, Vicente Ordonez
2019 J jnl
Drill-down: Interactive Retrieval of Complex Scenes using Natural Language Queries.
CoRR
Fuwen Tan, Paola Cascante-Bonilla, Xiaoxiao Guo, Hui Wu, Song Feng, Vicente Ordonez
2019 J jnl
Moviescope: Large-scale Analysis of Movies using Multiple Modalities.
CoRR
Paola Cascante-Bonilla, Kalpathy Sitaraman, Mengjia Luo, Vicente Ordonez