Enhancing Object Detection with Active Exploration and Spatiotemporal Aggregation
ACM Transactions on Multimedia Computing, Communications, and Applications · 31.08.2026 · 22 (8) · 1-20
DOI: 10.1145/3816703 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Multimedia Computing, Communications, and Applications, online erschienen am 22.07.2026. Verfasst von Peiwei Li und 6 weiteren Autor:innen. Die Arbeit nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Anhui Province, National Natural Science Foundation of China, Youth Innovation Promotion Association CAS.
Abstract (Originalsprache)
Classic object detectors are fundamentally limited by their reliance on a single, static viewpoint, which often suffers from occlusions, challenging scales, and ambiguous perspectives. Video-based object detectors can partially mitigate this problem by aggregating information from multiple views, but they usually work with passively gathered sequences and are in no means guaranteed to provide sufficient information for all objects of interest. On the other hand, active vision methods can seek out better views, yet existing active object detectors typically only try to search for a single optimal perspective and discard valuable information gathered along their path. In this article, we introduce a new paradigm for object detection that unifies active exploration with cumulative spatiotemporal aggregation. We train an embodied agent to intelligently explore its environment, guided by a novel, detection-aware reward function that directly encourages seeking out views that resolve visual ambiguities. To leverage this active exploration, we introduce a robust aggregation pipeline that adeptly harnesses SAM 2’s temporal reasoning capabilities to fuse information from the agent’s entire trajectory into a single, coherent set of detections. Through extensive experiments on AI2-THOR, we demonstrate that our framework provides a consistent and substantial performance uplift when applied to a wide range of state-of-the-art detectors, establishing a strong and versatile new baseline for the next generation of active vision systems.
Förderung
- Natural Science Foundation of Anhui Province
- National Natural Science Foundation of China
- Youth Innovation Promotion Association CAS
Zitieren
APA
Li, P., Wang, M., Zhou, W., Yin, Y., Bao, Y., Shen, G., & Li, H. (2026). Enhancing Object Detection with Active Exploration and Spatiotemporal Aggregation. ACM Transactions on Multimedia Computing, Communications, and Applications, 22(8), 1-20. https://doi.org/10.1145/3816703
Vancouver
Li P, Wang M, Zhou W, Yin Y, Bao Y, Shen G, et al. Enhancing Object Detection with Active Exploration and Spatiotemporal Aggregation. ACM Transactions on Multimedia Computing, Communications, and Applications. 2026;22(8):1-20. doi:10.1145/3816703
BibTeX
@article{Li2026,
author = {Li, Peiwei and Wang, Min and Zhou, Wengang and Yin, Yufei and Bao, Yebo and Shen, Guodong and Li, Houqiang},
title = {Enhancing Object Detection with Active Exploration and Spatiotemporal Aggregation},
journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
year = {2026},
volume = {22},
number = {8},
pages = {1--20},
doi = {10.1145/3816703}
}
EUVIMED