AEI: Actors-Environment Interaction with Adaptive Attention for Temporal Action Proposals Generation

Last update: Dec 13, 2022

Related tags

Deep Learning TAPG-AgentEnvInteration

Overview

AEI: Actors-Environment Interaction with Adaptive Attention for Temporal Action Proposals Generation

A pytorch-version implementation codes of paper: "AEI: Actors-Environment Interaction with Adaptive Attention for Temporal Action Proposals Generation", which is accepted in BMVC 2021.

Prerequisites

Python 3.8
Pytorch 1.9
fvcore
numpy, pandas, matplotlib, tensorboardX etc.

Download Features

3D Resnet-50 features extracted from rescaled videos of ActivityNet-1.3 can be downloaded [here](will be updated soon).

Training and Testing of AEI

Default configurations of AEI are stored in config/defaults.py. The modified configurations are stored in config/*.yaml for training and testing of AEI on different datasets (ActivityNet-1.3 and THUMOS-14). We can also modify configurations through commandline arguments.

To train AEI on TAPG task of ActivityNet-1.3 with 1 GPU:

python main.py --cfg-file config/anet_proposals.yaml MODE 'training' GPU_IDS [0]

To evaluate AEI on validation set of ActivityNet-1.3 with 1 GPU:

python main.py --cfg-file config/anet_proposals.yaml MODE 'validation' GPU_IDS [0]

Reference

This implementation is partly based on this pytorch-implementation of BMN.

paper:[AEI: Actors-Environment Interaction with Adaptive Attention for Temporal Action Proposals Generation](will update soon)

Multi-modal co-attention for drug-target interaction annotation and Its Application to SARS-CoV-2

CoaDTI Multi-modal co-attention for drug-target interaction annotation and Its Application to SARS-CoV-2 Abstract Environment The test was conducted i

7 Nov 14, 2022

Allows including an action inside another action (by preprocessing the Yaml file). This is how composite actions should have worked.

actions-includes Allows including an action inside another action (by preprocessing the Yaml file). Instead of using uses or run in your action step,

70 Nov 4, 2022

AEI: Actors-Environment Interaction with Adaptive Attention for Temporal Action Proposals Generation

Related tags

Overview

AEI: Actors-Environment Interaction with Adaptive Attention for Temporal Action Proposals Generation

Prerequisites

Download Features

Training and Testing of AEI

Reference

You might also like...

Multi-modal co-attention for drug-target interaction annotation and Its Application to SARS-CoV-2

Allows including an action inside another action (by preprocessing the Yaml file). This is how composite actions should have worked.

Official implementation of ACTION-Net: Multipath Excitation for Action Recognition (CVPR'21).

Human Action Controller - A human action controller running on different platforms.

Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition in CVPR19

TDN: Temporal Difference Networks for Efficient Action Recognition

Code for CVPR2021 paper "Learning Salient Boundary Feature for Anchor-free Temporal Action Localization"

Spatial Temporal Graph Convolutional Networks (ST-GCN) for Skeleton-Based Action Recognition in PyTorch

Efficient Two-Step Networks for Temporal Action Segmentation (Neurocomputing 2021)

Owner

Official Pytorch Implementation of 'Learning Action Completeness from Points for Weakly-supervised Temporal Action Localization' (ICCV-21 Oral)

CVPR2021: Temporal Context Aggregation Network for Temporal Action Proposal Refinement

The official TensorFlow implementation of the paper Action Transformer: A Self-Attention Model for Short-Time Pose-Based Human Action Recognition

A pytorch-version implementation codes of paper: "BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation"

PaddleRobotics is an open-source algorithm library for robots based on Paddle, including open-source parts such as human-robot interaction, complex motion control, environment perception, SLAM positioning, and navigation.

Unsupervised Semantic Segmentation by Contrasting Object Mask Proposals.

The implemention of Video Depth Estimation by Fusing Flow-to-Depth Proposals

Sparse R-CNN: End-to-End Object Detection with Learnable Proposals, CVPR2021

Learning Open-World Object Proposals without Learning to Classify

Code for the paper SphereRPN: Learning Spheres for High-Quality Region Proposals on 3D Point Clouds Object Detection, ICIP 2021.