Papers with Code 아카이브
Activity Recognition
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 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://bitbucket.org/bfernando/videodarwin
공식 코드https://bitbucket.org/dmoltisanti/action_recognition_single_timestamps
공식 코드Action Recognition from Single Timestamp Supervision in Untrimmed Videos
https://bitbucket.org/edge-team-leat/microai_public
공식 코드Quantization and Deployment of Deep Neural Networks on Microcontrollers
https://bitbucket.org/sahasuman/bmvc2016_code
공식 코드Online Spatiotemporal Action Detection and Prediction via Causal Representations
https://github.com/0zgur0/STAR_Network
공식 코드https://github.com/11maxed11/phase-based-action-recognition
공식 코드https://github.com/1adrianb/video-transformers
공식 코드https://github.com/1xbq1/a2mc
공식 코드Attack-Augmentation Mixing-Contrastive Skeletal Representation Learning
https://github.com/1xbq1/psp-learning
공식 코드Pyramid Self-attention Polymerization Learning for Semi-supervised Skeleton-based Action Recognition
https://github.com/2000222/skateboard-ai
공식 코드SkateboardAI: The Coolest Video Action Recognition for Skateboarding
https://github.com/2020aptx4869lm/Forecasting-Human-Object-Interaction-in-FPV
공식 코드https://github.com/2tianyao1/actionllm
공식 코드https://github.com/3dperceptionlab/hierarchicalactionrecognition
공식 코드Enhancing Action Recognition by Leveraging the Hierarchical Structure of Actions and Textual Context
https://github.com/3dperceptionlab/visual-wetlandbirds
공식 코드Visual WetlandBirds Dataset: Bird Species Identification and Behavior Recognition in Videos
https://github.com/3huo/3DV-Action
공식 코드https://github.com/3huo/MVDI
공식 코드Action Recognition for Depth Video using Multi-view Dynamic Images
https://github.com/4dvlab/hucenlife
공식 코드Human-centric Scene Understanding for 3D Large-scale Scenarios
https://github.com/99eren99/dirfiaf
공식 코드https://github.com/99eren99/dis25k
공식 코드https://github.com/ABi-dot/Kedkg
공식 코드Knowledge Editing with Dynamic Knowledge Graphs for Multi-Hop Question Answering
https://github.com/ADiko1997/S-GEAR
공식 코드Semantically Guided Representation Learning For Action Anticipation
https://github.com/AIFARMS/NOR-behavior-recognition
공식 코드Vision-based Behavioral Recognition of Novelty Preference in Pigs
https://github.com/ActionR-G/ActionHSIC
공식 코드https://github.com/AdelaideAuto-IDLab/ID-Sensor
공식 코드Super Low Resolution RF Powered Accelerometers for Alerting on Hospitalized Patient Bed Exits
https://github.com/AlanZhang1995/TwoStreamSR
공식 코드Two-Stream Action Recognition-Oriented Video Super-Resolution
https://github.com/AlbertoSabater/Skeleton-based-One-shot-Action-Recognition
공식 코드One-shot action recognition in challenging therapy scenarios
https://github.com/Alibaba-MIIL/ImageNet21K
공식 코드https://github.com/Alibaba-MIIL/STAM
공식 코드https://github.com/Andy1621/CT-Net
공식 코드CT-Net: Channel Tensorization Network for Video Classification
https://github.com/Anirudh257/strm
공식 코드Spatio-temporal Relation Modeling for Few-shot Action Recognition
https://github.com/AnitaEpsilon/HAR
공식 코드Human Activity Recognition using Continuous Wavelet Transform and Convolutional Neural Networks
https://github.com/AnyiRao/SceneSeg
공식 코드A Local-to-Global Approach to Multi-modal Movie Scene Segmentation
https://github.com/Aries-chen/MedEditBench
공식 코드Beyond Memorization: A Rigorous Evaluation Framework for Medical Knowledge Editing
https://github.com/B-HAR-HumanActivityRecognition/B-HAR
공식 코드https://github.com/BBYL9413/TDS-CLIP
공식 코드TDS-CLIP: Temporal Difference Side Network for Image-to-Video Transfer Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.