Gamaleldin F. Elsayed — accepted AI-conference papers

2024

Affective Visual Dialog: A Large-Scale Benchmark for Emotional Reasoning Based on Visually Grounded Conversations

Kilichbek Haydarov*, Xiaoqian Shen, Avinash Madasu, Mahmoud Salem, Li-Jia Li, Gamaleldin F Elsayed +1

ECCV 2024poster

"We introduce Affective Visual Dialog, an emotion explanation and reasoning task as a testbed for research on understanding constructed emotions in response to visually grounded conversations. The task involves three skills: (1) Dialog-based Question Answering (2) Dialog-based Emotion Prediction and…

Cited by 4 Source ↗PDF ↗Scholar ↗

2023

Teacher-Generated Spatial-Attention Labels Boost Robustness and Accuracy of Contrastive Models

Yushi Yao, Chang Ye, Junfeng He, Gamaleldin F. Elsayed

CVPR 2023poster

Human spatial attention conveys information about theregions of visual scenes that are important for perform-ing visual tasks. Prior work has shown that the informa-tion about human attention can be leveraged to benefit var-ious supervised vision tasks. Might providing this weakform of supervision b…

Cited by 2 Source ↗PDF ↗code ↗Scholar ↗

2019

Adversarial Reprogramming of Neural Networks

Gamaleldin F. Elsayed, Ian Goodfellow, Jascha Sohl-Dickstein

ICLR 2019poster

Deep neural networks are susceptible to adversarial attacks. In computer vision, well-crafted perturbations to images can cause neural networks to make mistakes such as confusing a cat with a computer. Previous adversarial attacks have been designed to degrade performance of models or cause machine…

Cited by 227 Source ↗PDF ↗Scholar ↗