Browse > Computer Vision > Action Localization

# Action Localization Edit

26 papers with code · Computer Vision

You can find evaluation results in the subtasks. You can also submitting evaluation metrics for this task.

# Weakly-Supervised Action Localization with Expectation-Maximization Multi-Instance Learning

31 Mar 2020

These models use attention to generate the bag's representation from instances and then train it via bag's classification.

# Action Localization through Continual Predictive Learning

26 Mar 2020

It does not require any training annotations in terms of frame-level bounding boxes.

# A Novel Online Action Detection Framework from Untrimmed Video Streams

17 Mar 2020

Online temporal action localization from an untrimmed video stream is a challenging problem in computer vision.

# SF-Net: Single-Frame Supervision for Temporal Action Localization

15 Mar 2020

First, we propose to predict an actionness score for each video frame.

# Constraining Temporal Relationship for Action Localization

18 Feb 2020

To alleviate this problem, we add extra constraints to these curves, e. g., the probability of ''action continues'' should be relatively high between probability peaks of ''action starts'' and ''action ends'', so that the entire framework is aware of these latent constraints during an end-to-end optimization process.

# Weakly-Supervised Multi-Person Action Recognition in 360$^{\circ}$ Videos

9 Feb 2020

To enable research in this direction, we introduce 360Action, the first omnidirectional video dataset for multi-person action recognition.

# Action Graphs: Weakly-supervised Action Localization with Graph Convolution Networks

4 Feb 2020

We present a method for weakly-supervised action localization based on graph convolutions.

# A Proposed Artificial intelligence Model for Real-Time Human Action Localization and Tracking

9 Nov 2019

The basic foundation of the proposed model is the utilization of motion vectors, which already exist in a compressed video bit stream and provide sufficient information to improve the localization of the target action without requiring high consumption of computational resources compared with other popular methods of extracting motion information, such as optical flows.

# Temporal Action Localization using Long Short-Term Dependency

4 Nov 2019

In the present study, we developed a novel method, referred to as Gemini Network, for effective modeling of temporal structures and achieving high-performance temporal action localization.

# Towards Train-Test Consistency for Semi-supervised Temporal Action Localization

24 Oct 2019

The inconsistent strategy makes it hard to explicitly supervise the action localization model with temporal boundary annotations at training time.