EUVIMEDEUVIMED entdecken
Crossref

Transition-aware Path and Direction Variation Modeling for Gaze Target Detection in Video

Xingming Yang, Jing Jin, Kewei Wu, Zhao Xie, Chongjia Zhu, Dan Guo

ACM Transactions on Multimedia Computing, Communications, and Applications · 31.05.2026 · 22 (5) · 1-23

DOI: 10.1145/3799429 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Multimedia Computing, Communications, and Applications, online erschienen am 21.04.2026. Verfasst von Xingming Yang und 5 weiteren Autor:innen. Die Arbeit nennt 58 Literaturangaben. Gefördert von: Natural Science Foundation of China, University Synergy Innovation Program of Anhui Province, Anhui Natural Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Gaze target detection aims to localize a person’s gaze target. During gaze transition in video, the absence of accurate temporal variation modeling (TVM) may lead to errors in gaze target localization. In this work, we propose a Transition-aware Gaze Model (TGM), which focuses on analyzing temporal differences to achieve accurate location variation modeling. The TGM contains four key components: a frame gaze model, and three transition-aware modules (path variation, direction variation, and fusion). First , the frame Transformer extracts gaze location and direction features. Second , to analyze the feature difference among transition frames, we introduce TVM guided by transition-aware loss. TVM analyzes the location features to capture the moving trajectory of targets (defined as path variation ), which facilitates the search for target locations near the path. Third , TVM also analyzes the direction features to capture the transition-aware direction area (defined as direction variation ), which facilitates the search for target locations within this area. Fourth , since gaze directions dynamically adjust to track gaze targets, path variation, and direction variation are inherently aligned with the natural movement of a person’s gaze. Thus, these two variations are fused into a unified transition-aware feature, which helps cover all potential target locations. To search for accurate target locations, we embed this transition-aware feature into frame features with cross-attention, which can enhance gaze target detection in transition frames. Extensive experiments demonstrate that our method achieves state-of-the-art performance on two datasets, namely VideoAttentionTarget and VideoCoAtt.

Förderung

  • Natural Science Foundation of China
  • University Synergy Innovation Program of Anhui Province
  • Anhui Natural Science Foundation

Zitieren

APA

Yang, X., Jin, J., Wu, K., Xie, Z., Zhu, C., & Guo, D. (2026). Transition-aware Path and Direction Variation Modeling for Gaze Target Detection in Video. ACM Transactions on Multimedia Computing, Communications, and Applications, 22(5), 1-23. https://doi.org/10.1145/3799429

Vancouver

Yang X, Jin J, Wu K, Xie Z, Zhu C, Guo D. Transition-aware Path and Direction Variation Modeling for Gaze Target Detection in Video. ACM Transactions on Multimedia Computing, Communications, and Applications. 2026;22(5):1-23. doi:10.1145/3799429

BibTeX
@article{Yang2026,
  author = {Yang, Xingming and Jin, Jing and Wu, Kewei and Xie, Zhao and Zhu, Chongjia and Guo, Dan},
  title = {Transition-aware Path and Direction Variation Modeling for Gaze Target Detection in Video},
  journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
  year = {2026},
  volume = {22},
  number = {5},
  pages = {1--23},
  doi = {10.1145/3799429}
}
Kostenlos starten →