https://github.com/edgarschnfld/CADA-VAE-PyTorch
공식 코드Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders
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://github.com/edouardoyallon/interferometric-graph-transform
공식 코드Interferometric Graph Transform: a Deep Unsupervised Graph Representation
https://github.com/egocentricvision/egowild
공식 코드https://github.com/egocentricvision/n-epic-kitchens
공식 코드E$^2$(GO)MOTION: Motion Augmented Event Stream for Egocentric Action Recognition
https://github.com/ehsanik/muscleTorch
공식 코드What Can You Learn from Your Muscles? Learning Visual Representation from Human Interactions
https://github.com/ekazakos/mtcn
공식 코드With a Little Help from my Temporal Context: Multimodal Egocentric Action Recognition
https://github.com/ekazakos/temporal-binding-network
공식 코드EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition
https://github.com/ekgus9/COME
공식 코드CoME: An Unlearning-based Approach to Conflict-free Model Editing
https://github.com/elicassion/3dtrl
공식 코드Learning Viewpoint-Agnostic Visual Representations by Recovering Tokens in 3D Space
https://github.com/emadeldeen24/TS-TCC
공식 코드Time-Series Representation Learning via Temporal and Contextual Contrasting
https://github.com/emansim/unsupervised-videos
공식 코드https://github.com/endlichere/ft-hid
공식 코드FT-HID: A Large Scale RGB-D Dataset for First and Third Person Human Interaction Analysis
https://github.com/epic-kitchens/action-models
공식 코드https://github.com/epic-kitchens/epic-kitchens-100-annotations
공식 코드https://github.com/epic-kitchens/epic-kitchens-100-narrator
공식 코드https://github.com/epic-kitchens/epic-sounds-annotations
공식 코드https://github.com/eric-mitchell/mend
공식 코드https://github.com/eric8932/jeep
공식 코드Joint Knowledge Editing for Information Enrichment and Probability Promotion
https://github.com/ericssonresearch/uda-4-tsc
공식 코드Deep Unsupervised Domain Adaptation for Time Series Classification: a Benchmark
https://github.com/ermongroup/NDA
공식 코드https://github.com/ermongroup/Wifi_Activity_Recognition
공식 코드https://github.com/erobic/occam-nets-v1
공식 코드OccamNets: Mitigating Dataset Bias by Favoring Simpler Hypotheses
https://github.com/eth-siplab/Finding_Order_in_Chaos
공식 코드Finding Order in Chaos: A Novel Data Augmentation Method for Time Series in Contrastive Learning
https://github.com/event-ahu/celex-har
공식 코드Event Stream based Human Action Recognition: A High-Definition Benchmark Dataset and Algorithms
https://github.com/event-ahu/hardvs
공식 코드HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors
https://github.com/event-ahu/uncertainty_aware_mobileformer
공식 코드Uncertainty-aware Bridge based Mobile-Former Network for Event-based Pattern Recognition
https://github.com/evm7/ego4dlta-icvae
공식 코드Intention-Conditioned Long-Term Human Egocentric Action Forecasting
https://github.com/ez-hwh/autocrawler
공식 코드AutoScraper: A Progressive Understanding Web Agent for Web Scraper Generation
https://github.com/ez-hwh/autoscraper
공식 코드AutoScraper: A Progressive Understanding Web Agent for Web Scraper Generation
https://github.com/f-ilic/AppearanceFreeActionRecognition
공식 코드https://github.com/fabienbaradel/glimpse_clouds
공식 코드Glimpse Clouds: Human Activity Recognition from Unstructured Feature Points
https://github.com/fabienbaradel/object_level_visual_reasoning
공식 코드https://github.com/facebookarchive/C3D
공식 코드Learning Spatiotemporal Features with 3D Convolutional Networks
https://github.com/facebookresearch/AVID-CMA
공식 코드Audio-Visual Instance Discrimination with Cross-Modal Agreement
https://github.com/facebookresearch/AVT
공식 코드https://github.com/facebookresearch/Ego-Exo
공식 코드Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.