Browse SoTA > Computer Vision > Activity Recognition

Activity Recognition

90 papers with code · Computer Vision

Human Activity Recognition is the problem of identifying events performed by humans given a video input. It is formulated as a binary (or multiclass) classification problem of outputting activity class labels. Activity Recognition is an important problem with many societal applications including smart surveillance, video search/retrieval, intelligent robots, and other monitoring systems.

Source: Learning Latent Sub-events in Activity Videos Using Temporal Attention Filters

Benchmarks

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

Greatest papers with code

AssembleNet++: Assembling Modality Representations via Attention Connections

18 Aug 2020google-research/google-research

We create a family of powerful video models which are able to: (i) learn interactions between semantic object information and raw appearance and motion features, and (ii) deploy attention in order to better learn the importance of features at each convolutional block of the network.

ACTION CLASSIFICATION ACTIVITY RECOGNITION

Large-scale weakly-supervised pre-training for video action recognition

CVPR 2019 microsoft/computervision-recipes

Second, frame-based models perform quite well on action recognition; is pre-training for good image features sufficient or is pre-training for spatio-temporal features valuable for optimal transfer learning?

 Ranked #1 on Egocentric Activity Recognition on EPIC-Kitchens (Actions Top-1 (S2) metric)

ACTION CLASSIFICATION ACTION RECOGNITION ACTIVITY RECOGNITION IN VIDEOS EGOCENTRIC ACTIVITY RECOGNITION TRANSFER LEARNING

Deep Residual Bidir-LSTM for Human Activity Recognition Using Wearable Sensors

22 Aug 2017guillaume-chevalier/LSTM-Human-Activity-Recognition

Human activity recognition (HAR) has become a popular topic in research because of its wide application.

ACTIVITY RECOGNITION

Temporal Relational Reasoning in Videos

ECCV 2018 metalbubble/TRN-pytorch

Temporal relational reasoning, the ability to link meaningful transformations of objects or entities over time, is a fundamental property of intelligent species.

ACTION CLASSIFICATION ACTION RECOGNITION COMMON SENSE REASONING HUMAN-OBJECT INTERACTION DETECTION RELATIONAL REASONING

TS-LSTM and Temporal-Inception: Exploiting Spatiotemporal Dynamics for Activity Recognition

30 Mar 2017jeffreyyihuang/two-stream-action-recognition

We demonstrate that using both RNNs (using LSTMs) and Temporal-ConvNets on spatiotemporal feature matrices are able to exploit spatiotemporal dynamics to improve the overall performance.

ACTION CLASSIFICATION ACTION RECOGNITION VIDEO UNDERSTANDING

Deep learning for time series classification

1 Oct 2020hfawaz/dl-4-tsc

In this context, deep learning has emerged in recent years as one of the most effective methods for tackling the supervised classification task, particularly in the field of computer vision.

ACTIVITY RECOGNITION DATA AUGMENTATION TIME SERIES TIME SERIES ANALYSIS TIME SERIES CLASSIFICATION TRANSFER LEARNING

Discriminating Spatial and Temporal Relevance in Deep Taylor Decompositions for Explainable Activity Recognition

5 Aug 2019jfzhang95/pytorch-video-recognition

However, by exploiting a simple technique that removes motion information, we show that it is not the case that this technique is effective as-is for representing relevance in non-image tasks.

ACTION RECOGNITION

Multivariate LSTM-FCNs for Time Series Classification

14 Jan 2018titu1994/LSTM-FCN

Over the past decade, multivariate time series classification has received great attention.

ACTION RECOGNITION TIME SERIES TIME SERIES CLASSIFICATION

NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding

12 May 2019shahroudy/NTURGB-D

Research on depth-based human activity analysis achieved outstanding performance and demonstrated the effectiveness of 3D representation for action recognition.

ACTION RECOGNITION ONE-SHOT 3D ACTION RECOGNITION

Real-world Anomaly Detection in Surveillance Videos

CVPR 2018 WaqasSultani/AnomalyDetectionCVPR2018

To avoid annotating the anomalous segments or clips in training videos, which is very time consuming, we propose to learn anomaly through the deep multiple instance ranking framework by leveraging weakly labeled training videos, i. e. the training labels (anomalous or normal) are at video-level instead of clip-level.

ACTIVITY RECOGNITION ANOMALY DETECTION IN SURVEILLANCE VIDEOS MULTIPLE INSTANCE LEARNING