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/alibaba/Deep-Vision/tree/main/Context-Motion-Decoupling

공식 코드

Self-supervised Video Representation Learning by Context and Motion Decoupling

https://github.com/alibaba/lightweight-neural-architecture-search

공식 코드

Maximizing Spatio-Temporal Entropy of Deep 3D CNNs for Efficient Video Recognition

https://github.com/alinlab/BAR

공식 코드

Learning from Failure: Training Debiased Classifier from Biased Classifier

https://github.com/alinlab/temporal-selfsupervision

공식 코드

Time Is MattEr: Temporal Self-supervision for Video Transformers

https://github.com/allanmsouza/acsp-fl

공식 코드

Adaptive Client Selection with Personalization for Communication Efficient Federated Learning

https://github.com/amathislab/epfl-smart-kitchen

공식 코드

EPFL-Smart-Kitchen-30: Densely annotated cooking dataset with 3D kinematics to challenge video and language models

https://github.com/amazon-research/stochastic-backpropagation

공식 코드

Stochastic Backpropagation: A Memory Efficient Strategy for Training Video Models

https://github.com/amazon-science/self-supervised-maclr

공식 코드

MaCLR: Motion-aware Contrastive Learning of Representations for Videos

https://github.com/ami-iit/paper_guo_2023_humanoids_lifting_risk_prediction

공식 코드

Online Action Recognition for Human Risk Prediction with Anticipated Haptic Alert via Wearables

https://github.com/amodaresi/memllm

공식 코드

MemLLM: Finetuning LLMs to Use An Explicit Read-Write Memory

https://github.com/anakin2555/decomposewhar

공식 코드

Decomposing and Fusing Intra- and Inter-Sensor Spatio-Temporal Signal for Multi-Sensor Wearable Human Activity Recognition

https://github.com/andongdeng/bear

공식 코드

A Large-scale Study of Spatiotemporal Representation Learning with a New Benchmark on Action Recognition

https://github.com/andreYoo/PeGCNs

공식 코드

Predictively Encoded Graph Convolutional Network for Noise-Robust Skeleton-based Action Recognition

https://github.com/andrea-cavallo-98/sparse-vnn

공식 코드

Sparse Covariance Neural Networks

https://github.com/anirudhs123/home

공식 코드

HomE: Homography-Equivariant Video Representation Learning

https://github.com/anirudhsom/PI-Net

공식 코드

PI-Net: A Deep Learning Approach to Extract Topological Persistence Images

https://github.com/anish-lakkapragada/ActivRecognition-Autism-Diagnosis

공식 코드

Classification of Abnormal Hand Movement for Aiding in Autism Detection: Machine Learning Study

https://github.com/anita-hu/MSAF

공식 코드

MSAF: Multimodal Split Attention Fusion

https://github.com/anjanaw/MEx

공식 코드

MEx: Multi-modal Exercises Dataset for Human Activity Recognition

https://github.com/anshitag/memit_csk

공식 코드

Editing Common Sense in Transformers

https://github.com/anshulbshah/PoseAction

공식 코드

Pose And Joint-Aware Action Recognition

https://github.com/anshulbshah/halp

공식 코드

HaLP: Hallucinating Latent Positives for Skeleton-based Self-Supervised Learning of Actions

https://github.com/antoine77340/MIL-NCE_HowTo100M

공식 코드

End-to-End Learning of Visual Representations from Uncurated Instructional Videos

https://github.com/antoine77340/RareAct

공식 코드

RareAct: A video dataset of unusual interactions

https://github.com/antran89/two-stream-fcan

공식 코드

Two-stream Flow-guided Convolutional Attention Networks for Action Recognition

https://github.com/aoqunjin/awesome-vla-post-training

공식 코드

Parallels Between VLA Model Post-Training and Human Motor Learning: Progress, Challenges, and Trends

https://github.com/apartresearch/specificityplus

공식 코드

Detecting Edit Failures In Large Language Models: An Improved Specificity Benchmark

https://github.com/apple2373/action-general.icdl

공식 코드

Action Recognition based on Cross-Situational Action-object Statistics

https://github.com/applied-machine-learning-lab/mm4ke

공식 코드

Model Merging for Knowledge Editing

https://github.com/aras62/SF-GRU

공식 코드

Pedestrian Action Anticipation using Contextual Feature Fusion in Stacked RNNs

https://github.com/arclab-hku/supereio

공식 코드

SuperEIO: Self-Supervised Event Feature Learning for Event Inertial Odometry

https://github.com/ardamamur/egoexor

공식 코드

EgoExOR: An Ego-Exo-Centric Operating Room Dataset for Surgical Activity Understanding

https://github.com/arnab-api/romba

공식 코드

Locating and Editing Factual Associations in Mamba

https://github.com/aroitberg/sims4action

공식 코드

Let's Play for Action: Recognizing Activities of Daily Living by Learning from Life Simulation Video Games

https://github.com/artest08/LateTemporalModeling3DCNN

공식 코드

Late Temporal Modeling in 3D CNN Architectures with BERT for Action Recognition

https://github.com/arturjordao/WearableSensorData

공식 코드

Human Activity Recognition Based on Wearable Sensor Data: A Standardization of the State-of-the-Art

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