Daniel A. P. Oliveira

Daniel A. P. Oliveira

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 September 2025 in Information
Verified
Journal Article
Open access
PDF file
DODaniel A. P. Oliveira
Daniel A. P. Oliveira
EREugénio Ribeiro
Eugénio Ribeiro
David Martins de MatosDavid Martins de Matos
David Martins de Matos
Creating engaging narratives from visual data is crucial for automated digital media consumption, assistive technologies, and interactive entertainment. This survey covers methodologies used in the generation of these narratives, focusing on their principles, strengths, and limitations. The survey also covers tasks related to automatic story generation, such as image and video captioning, and Visual Question Answering. These tasks share common challenges with Visual Story Generation (VSG) and have served as inspiration for the techniques used in the field. We analyze the main datasets and evaluation metrics, providing a critical perspective on their limitations.

12 April 2026 in Pattern Recognition
Verified
Journal Article
Open access
DODaniel A. P. Oliveira
Daniel A. P. Oliveira
LTLourenço Teodoro
Lourenço Teodoro
David Martins de MatosDavid Martins de Matos
David Martins de Matos

11 July 2025 in arXiv
Verified
Preprint
Open access
PDF file
DODaniel A. P. Oliveira
Daniel A. P. Oliveira
David Martins de MatosDavid Martins de Matos
David Martins de Matos
Visual storytelling systems, particularly large vision-language models, struggle to maintain character and object identity across frames, often failing to recognize when entities in different images represent the same individuals or objects, leading to inconsistent references and referential hallucinations. This occurs because models lack explicit training on when to establish entity connections across frames. We propose a contrastive reinforcement learning approach that trains models to discriminate between coherent image sequences and stories from unrelated images. We extend the Story Reasoning dataset with synthetic negative examples to teach appropriate entity connection behavior. We employ Direct Preference Optimization with a dual-component reward function that promotes grounding and re-identification of entities in real stories while penalizing incorrect entity connections in synthetic contexts. Using this contrastive framework, we fine-tune Qwen Storyteller (based on Qwen2.5-VL 7B). Evaluation shows improvements in grounding mAP from 0.27 to 0.31 (+14.8%), F1 from 0.35 to 0.41 (+17.1%). Pronoun grounding accuracy improved across all pronoun types except "its", and cross-frame character and object persistence increased across all frame counts, with entities appearing in 5 or more frames advancing from 29.3% to 33.3% (+13.7%). Well-structured stories, containing the chain-of-thought and grounded story, increased from 79.1% to 97.5% (+23.3%).

3 October 2026 in Pattern Recognition
Verified
Journal Article
Open access
DODaniel A. P. Oliveira
Daniel A. P. Oliveira
DMDavid Martins de Matos
David Martins de Matos