</> Code with Papers by Syntology

Browse State-of-the-Art › Unusual Activity Localization

Unusual Activity Localization

1 paper with code · 0 benchmarks · 0 datasets archive 2025-07-28

Computer Vision

In the realm of real-world events and human behavior analysis, unusual activities are defined as behaviors, patterns, or events that deviate from expected norms or regular occurrences. This concept encompassestwo primary aspects: first, outcomes that contradict conventional expectations, exemplified by unintentional and humorous activities second, rare or infrequent occurrences, such as behaviors related to autism spectrum disorder (ASD), sudden road accidents, natural disasters, extreme weather , unusual public demonstrations like riot, observation of rare endangered species in urban environments, space events like unexpected meteor dropping etc.

An unusual activity localization model takes a video-query pair as input, where the video is a sequence of frames and the query consists of a sequence of words that describes the unusual activity.

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

No benchmark for this task in the archive.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

No dataset record in the archive lists this task.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Action Localization

Most implemented papers archive 2025-07-28

1 shown of 1 paper with code (1 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections