EUVIMEDEUVIMED entdecken
Crossref

Data-And Knowledge-Driven Visual Abductive Reasoning

Chen Liang, Wenguan Wang, Ling Chen, Yi Yang

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026

DOI: 10.1109/tpami.2025.3613712 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026. Verfasst von Chen Liang und 3 weiteren Autor:innen. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted. Die Arbeit nennt 133 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Abductive reasoning seeks the likeliest possible explanation for partial observations. Although being frequently employed in human daily reasoning, abduction is rarely explored in computer vision literature. In this article, we propose a new task, Visual Abductive Reasoning (VAR), that underpins the machine intelligence study of abductive reasoning in everyday visual situations. Given an incomplete set of visual events, AI systems are required to not only describe what is observed, but also infer the hypothesis that can best explain the observed premise. We create the first large-scale VAR dataset, which contains a total of 9K examples. We further devise a transformer-based VAR model - Reasonerv2 - for knowledge-driven, causal-and-cascaded reasoning. Reasonerv2 first adopts a contextualized directional position embedding strategy in the encoder, to capture the causal-related temporal structure of the observations, and yield discriminative representations for the premises and hypotheses. Then, Reasonerv2 extracts condensed causal knowledge from external knowledge bases, for reasoning beyond observation. Finally, Reasonerv2 cascades multiple decoders so as to generate and progressively refine the premise and hypothesis sentences. The prediction scores of the sentences are used to guide cross-sentence information flow in the cascaded reasoning procedure. Our VAR benchmarking results show that Reasonerv2 surpasses many famous video-language models, while still being far behind human performance.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Image Processing, Computer-AssistedHumansArtificial IntelligenceKnowledge BasesAlgorithmsPattern Recognition, Automated

Zitieren

APA

Liang, C., Wang, W., Chen, L., & Yang, Y. (2026). Data-And Knowledge-Driven Visual Abductive Reasoning. IEEE Transactions on Pattern Analysis and Machine Intelligence. https://doi.org/10.1109/tpami.2025.3613712

Vancouver

Liang C, Wang W, Chen L, Yang Y. Data-And Knowledge-Driven Visual Abductive Reasoning. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026. doi:10.1109/tpami.2025.3613712

BibTeX
@article{Liang2026,
  author = {Liang, Chen and Wang, Wenguan and Chen, Ling and Yang, Yi},
  title = {Data-And Knowledge-Driven Visual Abductive Reasoning},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2026},
  doi = {10.1109/tpami.2025.3613712}
}
Kostenlos starten →