120 papers with code • 0 benchmarks • 3 datasets
Action Localization is finding the spatial and temporal co ordinates for an action in a video. An action localization model will identify which frame an action start and ends in video and return the x,y coordinates of an action. Further the co ordinates will change when the object performing action undergoes a displacement.
These leaderboards are used to track progress in Action Localization
The AVA dataset densely annotates 80 atomic visual actions in 430 15-minute video clips, where actions are localized in space and time, resulting in 1. 58M action labels with multiple labels per person occurring frequently.
In this work, we propose instead to learn such embeddings from video data with readily available natural language annotations in the form of automatically transcribed narrations.
YOWO is a single-stage architecture with two branches to extract temporal and spatial information concurrently and predict bounding boxes and action probabilities directly from video clips in one evaluation.
Recognition of surgical activity is an essential component to develop context-aware decision support for the operating room.
Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action Localization
We propose `Hide-and-Seek', a weakly-supervised framework that aims to improve object localization in images and action localization in videos.
We propose a weakly supervised temporal action localization algorithm on untrimmed videos using convolutional neural networks.
We propose to explicitly model the Actor-Context-Actor Relation, which is the relation between two actors based on their interactions with the context.
Temporal action detection (TAD) aims to detect all action boundaries and their corresponding categories in an untrimmed video.
We propose the ACtion Tubelet detector (ACT-detector) that takes as input a sequence of frames and outputs tubelets, i. e., sequences of bounding boxes with associated scores.