Papers with Code 아카이브

Activity Recognition

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 11
평가표: 4
보존된 평가 기록: 10

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

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/ENSCMA2/flextape

공식 코드

"Flex Tape Can't Fix That": Bias and Misinformation in Edited Language Models

https://github.com/EdoWhite/Gate-Shift-Pose

공식 코드

Gate-Shift-Pose: Enhancing Action Recognition in Sports with Skeleton Information

https://github.com/Efstathia-Soufleri/PKD

공식 코드

Advancing Compressed Video Action Recognition through Progressive Knowledge Distillation

https://github.com/Ekim-Yurtsever/DeepTL-Lane-Change-Classification

공식 코드

Risky Action Recognition in Lane Change Video Clips using Deep Spatiotemporal Networks with Segmentation Mask Transfer

https://github.com/EricGuo5513/action-to-motion

공식 코드

Action2Motion: Conditioned Generation of 3D Human Motions

https://github.com/FingerRec/Self-Supervised-Temporal-Discriminative-Representation-Learning-for-Video-Action-Recognition

공식 코드

Self-supervised Temporal Discriminative Learning for Video Representation Learning

https://github.com/Forsad/Stable-Polynomial-Train

공식 코드

A Training Framework for Optimal and Stable Training of Polynomial Neural Networks

https://github.com/GMouYes/DHC_HGL

공식 코드

Deep Heterogeneous Contrastive Hyper-Graph Learning for In-the-Wild Context-Aware Human Activity Recognition

https://github.com/Gauffret/TrajectorySet

공식 코드

Revisiting hand-crafted feature for action recognition: a set of improved dense trajectories

https://github.com/Gbouna/MAK-GCN

공식 코드

Multi-Head Adaptive Graph Convolution Network for Sparse Point Cloud-Based Human Activity Recognition

https://github.com/Gbouna/RE-TCN

공식 코드

Action Recognition in Real-World Ambient Assisted Living Environment

https://github.com/GeetDsa/Activity_Recognition_3D_CNN

공식 코드

An IoT Based Framework For Activity Recognition Using Deep Learning Technique

https://github.com/GinnyXiao/ReSpike

공식 코드

ReSpike: Residual Frames-based Hybrid Spiking Neural Networks for Efficient Action Recognition

https://github.com/GiuliaDAngelo/Speckegomotion

공식 코드

Wandering around: A bioinspired approach to visual attention through object motion sensitivity

https://github.com/HCIS-Lab/Action-slot

공식 코드

Action-slot: Visual Action-centric Representations for Multi-label Atomic Activity Recognition in Traffic Scenes

https://github.com/HJYao00/Side4Video

공식 코드

Side4Video: Spatial-Temporal Side Network for Memory-Efficient Image-to-Video Transfer Learning

https://github.com/Heliot7/open-set-da

공식 코드

Open Set Domain Adaptation for Image and Action Recognition

https://github.com/HimangiM/RepLAI

공식 코드

Learning State-Aware Visual Representations from Audible Interactions

https://github.com/HobbitLong/CMC

공식 코드

Contrastive Multiview Coding

https://github.com/Howal/DNL-Object-Detection

공식 코드

Disentangled Non-Local Neural Networks

https://github.com/HsinYingLee/OPN

공식 코드

Unsupervised Representation Learning by Sorting Sequences

https://github.com/HuCui2022/DSTSA-GCN_Gesture

공식 코드

DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling

https://github.com/HumamAlwassel/XDC

공식 코드

Self-Supervised Learning by Cross-Modal Audio-Video Clustering

https://github.com/I2RDL2/ASTAR-HAR

공식 코드

A*HAR: A New Benchmark towards Semi-supervised learning for Class-imbalanced Human Activity Recognition

https://github.com/IBM/RegionViT

공식 코드

RegionViT: Regional-to-Local Attention for Vision Transformers

https://github.com/IBM/action-recognition-pytorch

공식 코드

Deep Analysis of CNN-based Spatio-temporal Representations for Action Recognition

https://github.com/IBM/bLVNet-TAM

공식 코드

More Is Less: Learning Efficient Video Representations by Big-Little Network and Depthwise Temporal Aggregation

https://github.com/IIT-PAVIS/subspace-clustering-action-recognition

공식 코드

Subspace Clustering for Action Recognition with Covariance Representations and Temporal Pruning

https://github.com/IMSY-DKFZ/self-distilled-swin

공식 코드

Self-distillation for surgical action recognition

https://github.com/IkeaASM/IKEA_ASM_Dataset

공식 코드

The IKEA ASM Dataset: Understanding People Assembling Furniture through Actions, Objects and Pose

https://github.com/IoBT-VISTEC/SleepPoseNet

공식 코드

SleepPoseNet: Multi-View Learning for Sleep Postural Transition Recognition Using UWB

https://github.com/IuliaDuta/RSTG

공식 코드

Recurrent Space-time Graph Neural Networks

https://github.com/JHang2020/HiCLR

공식 코드

Hierarchical Consistent Contrastive Learning for Skeleton-Based Action Recognition with Growing Augmentations

https://github.com/JHang2020/Shap-Mix

공식 코드

Shap-Mix: Shapley Value Guided Mixing for Long-Tailed Skeleton Based Action Recognition

https://github.com/Jeongseungwoo/Efficient-Continuous-Manifold-Learning

공식 코드

Deep Efficient Continuous Manifold Learning for Time Series Modeling

https://github.com/JerryYLi/Dataset-REPAIR

공식 코드

REPAIR: Removing Representation Bias by Dataset Resampling

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.