Temporally localizing actions in a video is a fundamental challenge in video understanding.
Most existing approaches have often drawn inspiration from image object detection and …

Due to the large memory footprint of untrimmed videos, current state-of-the-art video
localization methods operate atop precomputed video clip features. These features are …

We describe a latent approach that learns to detect actions in long sequences given training
videos with only whole-video class labels. Our approach makes use of two innovations to …

We address the problem of localizing a specific moment described by a natural language
query. Existing works interact the query with either video frame or moment proposal, and …

Temporal action localization is a recently-emerging task, aiming to localize video segments
from untrimmed videos which contain specific actions. This work proposes a novel …

Abstract Generic Event Boundary Detection (GEBD) is a newly suggested video
understanding task that aims to find one level deeper semantic boundaries of events …

Video action detectors are usually trained using datasets with fully-supervised temporal
annotations. Building such datasets is an expensive task. To alleviate this problem, recent …