Open-world object counting in videos

Conference item

We introduce a new task of open-world object counting in videos: given a text description, or an image example, that specifies the target object, the objective is to enumerate all the unique instances of the target objects in the video. This task is especially challenging in crowded scenes with occlusions and objects of similar appearance, where avoiding double counting and identifying reappearances is crucial. To this end, we make the following contributions: we introduce a model, COUNTVID, for this task. It leverages an imagebased counting model, and a promptable video segmentation and tracking model, to enable automated open-world object counting across video frames. To evaluate its performance, we introduce VIDEOCOUNT, a new dataset for this novel task built from the TAO and MOT20 tracking datasets, as well as from videos of penguins and metal alloy crystallization captured by x-rays. Using this dataset, we demonstrate that COUNTVID provides accurate object counts, and significantly outperforms strong baselines.

Authors: Amini-Naieni, N; Zisserman, A

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: American Association for the Advancement of Science
• Host title: Proceedings of the 40th Annual AAAI Conference on Artificial Intelligence
• Journal: Proceedings of the AAAI Conference on Artificial Intelligence
• Volume: 40
• Issue: 4
• Pages: 2300-2308
• Publication date: 2026-03-14
• Acceptance date: 2025-11-07
• Event title: 40th Annual AAAI Conference on Artificial Intelligence (AAAI 2026)
• Event location: Singapore
• Event website: https://aaai.org/conference/aaai/aaai-26/
• Event start date: 2026-01-20
• Event end date: 2026-01-27
• DOI: 10.1609/aaai.v40i4.37214
• ISSN: 2159-5399
• ISBN-10: 1577359062
• ISBN-13: 9781577359067
• Language: English