Pedro H. V. Valois

According to our database, Pedro H. V. Valois authored at least 6 papers between 2024 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2025

From Punchlines to Predictions: A Metric to Assess LLM Performance in Identifying Humor in Stand-Up Comedy.

Adrianna Romanowski, Pedro H. V. Valois, Kazuhiro Fukui

CoRR, April, 2025

Leveraging self-supervised learning for scene classification in child sexual abuse imagery.

Pedro H. V. Valois, João Macedo, Leo Sampaio Ferraz Ribeiro, Jefersson A. dos Santos, Sandra Avila

Forensic Sci. Int. Digit. Investig., 2025

2024

Frame Representation Hypothesis: Multi-Token LLM Interpretability and Concept-Guided Text Generation.

Pedro H. V. Valois, Lincon S. Souza, Erica K. Shimomoto, Kazuhiro Fukui

CoRR, 2024

Second-order difference subspace.

Kazuhiro Fukui, Pedro H. V. Valois, Lincon S. Souza, Takumi Kobayashi

CoRR, 2024

Leveraging Self-Supervised Learning for Scene Recognition in Child Sexual Abuse Imagery.

Pedro H. V. Valois, João Macedo, Leo Sampaio Ferraz Ribeiro, Jefersson A. dos Santos, Sandra Avila

CoRR, 2024

Occlusion Sensitivity Analysis with Augmentation Subspace Perturbation in Deep Feature Space.

Pedro H. V. Valois, Koichiro Niinuma, Kazuhiro Fukui

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2024