Activity Recognition

297 papers with code • 4 benchmarks • 30 datasets

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

Libraries

Use these libraries to find Activity Recognition models and implementations
4 papers
19
3 papers
81
See all 5 libraries.

Most implemented papers

Real-world Anomaly Detection in Surveillance Videos

WaqasSultani/AnomalyDetectionCVPR2018 CVPR 2018

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.

Multivariate LSTM-FCNs for Time Series Classification

houshd/MLSTM-FCN 14 Jan 2018

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

CholecTriplet2021: A benchmark challenge for surgical action triplet recognition

CAMMA-public/cholectriplet2021 10 Apr 2022

In this paper, we present the challenge setup and assessment of the state-of-the-art deep learning methods proposed by the participants during the challenge.

Temporal Relational Reasoning in Videos

metalbubble/TRN-pytorch ECCV 2018

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

Representation Flow for Action Recognition

piergiaj/representation-flow-cvpr19 CVPR 2019

Our representation flow layer is a fully-differentiable layer designed to capture the `flow' of any representation channel within a convolutional neural network for action recognition.

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

chihyaoma/Activity-Recognition-with-CNN-and-RNN 30 Mar 2017

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.

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

guillaume-chevalier/HAR-stacked-residual-bidir-LSTMs 22 Aug 2017

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

Im2Flow: Motion Hallucination from Static Images for Action Recognition

rhgao/Im2Flow CVPR 2018

Second, we show the power of hallucinated flow for recognition, successfully transferring the learned motion into a standard two-stream network for activity recognition.

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

jfzhang95/pytorch-video-recognition 5 Aug 2019

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.

Understanding the Vulnerability of Skeleton-based Human Activity Recognition via Black-box Attack

realcrane/BASAR-Black-box-Attack-on-Skeletal-Action-Recognition 21 Nov 2022

Via BASAR, we find on-manifold adversarial samples are extremely deceitful and rather common in skeletal motions, in contrast to the common belief that adversarial samples only exist off-manifold.