Recognizing human activities from video sequences or still images is a challenging task due
to problems, such as background clutter, partial occlusion, changes in scale, viewpoint …

The potential for agents, whether embodied or software, to learn by observing other agents
performing procedures involving objects and actions is rich. Current research on automatic …

Our paper presents a new approach for temporal detection of human actions in long,
untrimmed video sequences. We introduce Single-Stream Temporal Action Proposals (SST) …

Current state-of-the-art approaches for spatio-temporal action localization rely on detections
at the frame level that are then linked or tracked across time. In this paper, we leverage the …

Object proposals have contributed significantly to recent advances in object understanding
in images. Inspired by the success of this approach, we introduce Deep Action Proposals …

Training a generic objectness measure to produce a small set of candidate object windows,
has been shown to speed up the classical sliding window object detection paradigm. We …

Abstract Human Action Recognition (HAR) has achieved a remarkable milestone in the field
of computer vision. Apart from its varied applications in human–computer interactions …

Human action analytics has attracted a lot of attention for decades in computer vision. It is
important to extract discriminative spatio-temporal features to model the spatial and temporal …

In many large-scale video analysis scenarios, one is interested in localizing and recognizing
human activities that occur in short temporal intervals within long untrimmed videos. Current …

In this paper, we introduce SoccerNet, a benchmark for action spotting in soccer videos. The
dataset is composed of 500 complete soccer games from six main European leagues …