Browse > Computer Vision > Action Detection

Action Detection

48 papers with code · Computer Vision

Leaderboards

Greatest papers with code

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

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.

 SOTA for Action Detection on THUMOS' 14 (using extra training data)

ACTION DETECTION ACTIVITY DETECTION

Libri-Light: A Benchmark for ASR with Limited or No Supervision

17 Dec 2019facebookresearch/libri-light

Additionally, we provide baseline systems and evaluation metrics working under three settings: (1) the zero resource/unsupervised setting (ABX), (2) the semi-supervised setting (PER, CER) and (3) the distant supervision setting (WER).

ACTION DETECTION ACTIVITY DETECTION SPEECH RECOGNITION

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

Fine-grained Activity Recognition in Baseball Videos

9 Apr 2018piergiaj/mlb-youtube

In this paper, we introduce a challenging new dataset, MLB-YouTube, designed for fine-grained activity detection.

ACTION DETECTION ACTIVITY DETECTION ACTIVITY RECOGNITION VIDEO CLASSIFICATION

Temporal Tessellation: A Unified Approach for Video Analysis

ICCV 2017 dot27/temporal-tessellation

A test video is processed by forming correspondences between its clips and the clips of reference videos with known semantics, following which, reference semantics can be transferred to the test video.

ACTION DETECTION VIDEO CAPTIONING VIDEO SUMMARIZATION VIDEO UNDERSTANDING

SoccerNet: A Scalable Dataset for Action Spotting in Soccer Videos

12 Apr 2018SilvioGiancola/SoccerNet-code

A total of 6, 637 temporal annotations are automatically parsed from online match reports at a one minute resolution for three main classes of events (Goal, Yellow/Red Card, and Substitution).

ACTION CLASSIFICATION ACTION DETECTION ACTION SPOTTING