computer-vision-9

Activity Prediction

3260 papers • 126 benchmarks • 313 datasets

Predict human activities in videos

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in activity-prediction-19

Trend

Dataset

Best Model

Actions

ActEV

Libraries

i

Use these libraries to find activity-prediction-19 models and implementations

Datasets

Home Action Genome

InfiniteRep

Subtasks

motion prediction Cyber Attack Detection Sequential skip prediction

Most implemented papers

Peeking Into the Future: Predicting Future Person Activities and Locations in Videos

Lu Jiang, Li Fei-Fei, Juan Carlos Niebles, A. Hauptmann, Junwei Liang•Sun Feb 10 2019

An end-to-end, multi-task learning system utilizing rich visual features about human behavioral information and interaction with their surroundings is proposed, providing the first empirical evidence that joint modeling of paths and activities benefits future path prediction.

412

Content

0

Paper Graph

Uncertainty-based Traffic Accident Anticipation with Spatio-Temporal Relational Learning

Wentao Bao, Qi Yu, Yu Kong•Fri Jul 31 2020

An uncertainty-based accident anticipation model with spatio-temporal relational learning that sequentially predicts the probability of traffic accident occurrence with dashcam videos is proposed to take advantage of graph convolution and recurrent networks for relational feature learning, and leverage Bayesian neural networks to address the intrinsic variability of latent relational representations.

192 0

Paper Graph

HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors

Yonghong Tian, Yaowei Wang, Lin Zhu, Bowei Jiang, Xiao Wang, Zong-Yao Wu, Zhimin Bao, Guoqiu Li•Wed Nov 16 2022

A novel spatial-temporal feature learning and fusion framework, termed ESTF, for event stream based human activity recognition, which first projects the event streams into spatial and temporal embeddings using StemNet, then, encodes and fuses the dual-view representations using Transformer networks.

72 0

Paper Graph

DeepProcess: Supporting Business Process Execution Using a MANN-Based Recommender System

T. Tran, Renuka Sindhgatta, Asjad M. Khan, Hung Le, Kien Do, A. Ghose, K. Dam•Fri Feb 02 2018

A novel memory-augmented neural network (MANN) based approach for constructing a process-aware recommender system, namely Write-Protected Dual Controller Memory-Augmented Neural Network (DCw-MANN), for building prescriptive models is proposed.

15 0

Paper Graph

Glimpse Clouds: Human Activity Recognition from Unstructured Feature Points

Graham W. Taylor, Christian Wolf, Fabien Baradel, J. Mille•Wed Feb 21 2018

A method for human activity recognition from RGB data that does not rely on any pose information during test time, and does not explicitly calculate pose information internally, is proposed, where a visual attention module learns to predict glimpse sequences in each frame.

165 0

Paper Graph

Ionospheric activity prediction using convolutional recurrent neural networks

Alexandre Boulch, Noëlie Cherrier, T. Castaings•Tue Oct 30 2018

This work proposes a method based on Deep Neural Networks (DNN) to forecast a sequence of global TEC maps consecutive to an input sequence of T EC maps, without introducing any prior knowledge other than Earth rotation periodicity.

24 0

Paper Graph

INFER: INtermediate representations for FuturE pRediction

K. Krishna, Krishna Murthy Jatavallabhula, Shashank Srikanth, J. Ansari, R. KarnikRam, Sarthak Sharma•Mon Mar 25 2019

This paper condition on semantics and train an autoregressive model to accurately predict future trajectories of traffic participants (vehicles) and demonstrates that semantics provide a significant boost over techniques that operate over raw pixel intensities/disparities.

39 0

Paper Graph

Data-driven perception of neuron point process with unknown unknowns

Ruochen Yang, Gaurav Gupta, P. Bogdan•Thu Nov 01 2018

Results suggest that the neural connection model with unknown unknowns can efficiently estimate the statistical properties of the process by increasing the network likelihood.

8 0

Paper Graph

Attention-based Multi-Input Deep Learning Architecture for Biological Activity Prediction: An Application in EGFR Inhibitors

Huy Pham, Trung Le•Tue Jun 11 2019

This study proposed an architecture training simultaneously both type of data in order to improve the overall performance of machine learning and deep learning models and successfully integrated Attention mechanism into the model, which helped to interpret the contribution of chemical structures on bioactivity.

5 0

Paper Graph

Adding a benchmark result helps the community track progress.