Browse SoTA > Computer Vision > Action Detection

Action Detection

55 papers with code · Computer Vision

Benchmarks

Greatest papers with code

Asynchronous Interaction Aggregation for Action Detection

ECCV 2020 Alpha-Video/AlphaVideo

We propose the Asynchronous Interaction Aggregation network (AIA) that leverages different interactions to boost action detection.

ACTION DETECTION

Actor Conditioned Attention Maps for Video Action Detection

30 Dec 2018oulutan/ACAM_Demo

While observing complex events with multiple actors, humans do not assess each actor separately, but infer from the context.

ACTION DETECTION

Learning Latent Super-Events to Detect Multiple Activities in Videos

CVPR 2018 piergiaj/super-events-cvpr18

In this paper, we introduce the concept of learning latent super-events from activity videos, and present how it benefits activity detection in continuous videos.

ACTION DETECTION ACTIVITY DETECTION

SST: Single-Stream Temporal Action Proposals

CVPR 2017 shyamal-b/sst

Our paper presents a new approach for temporal detection of human actions in long, untrimmed video sequences.

ACTION DETECTION TEMPORAL ACTION PROPOSAL GENERATION

Actions as Moving Points

ECCV 2020 MCG-NJU/MOC-Detector

The existing action tubelet detectors often depend on heuristic anchor design and placement, which might be computationally expensive and sub-optimal for precise localization.

ACTION DETECTION ACTION RECOGNITION

Temporal Gaussian Mixture Layer for Videos

ICLR 2019 piergiaj/tgm-icml19

We introduce a new convolutional layer named the Temporal Gaussian Mixture (TGM) layer and present how it can be used to efficiently capture longer-term temporal information in continuous activity videos.

ACTION DETECTION ACTIVITY DETECTION

Decoupling Localization and Classification in Single Shot Temporal Action Detection

16 Apr 2019hypjudy/Decouple-SSAD

Each branch produces a set of action anchor layers by applying deconvolution to the feature maps of the main stream.

ACTION DETECTION

Single Shot Temporal Action Detection

17 Oct 2017hypjudy/Decouple-SSAD

The main drawback of this framework is that the boundaries of action instance proposals have been fixed during the classification step.

ACTION DETECTION