https://github.com/google-research/google-research/tree/master/vatt
공식 코드VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text
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/google-research/scenic
공식 코드https://github.com/google-research/scenic/tree/main/scenic/projects/mbt
공식 코드https://github.com/google/belief-localization
공식 코드https://github.com/gorayni/egocentric_photostreams
공식 코드Batch-based Activity Recognition from Egocentric Photo-Streams Revisited
https://github.com/gorayni/seeing_and_hearing
공식 코드Seeing and Hearing Egocentric Actions: How Much Can We Learn?
https://github.com/gorjanradevski/multimodal-distillation
공식 코드https://github.com/gorjanradevski/revisiting-spatial-temporal-layouts
공식 코드Revisiting spatio-temporal layouts for compositional action recognition
https://github.com/grasshlw/snn-neural-similarity-movie
공식 코드https://github.com/grassknoted/Modified-Two-Stream-Fusion-for-Real-time-ActionRecognition
공식 코드Real-time Action Recognition for Fine-Grained Actions and The Hand Wash Dataset
https://github.com/gsaponaro/tcds-gestures
공식 코드Beyond the Self: Using Grounded Affordances to Interpret and Describe Others' Actions
https://github.com/gsig/actor-observer
공식 코드Actor and Observer: Joint Modeling of First and Third-Person Videos
https://github.com/gsig/temporal-fields
공식 코드https://github.com/guillaume-chevalier/HAR-stacked-residual-bidir-LSTMs
공식 코드Deep Residual Bidir-LSTM for Human Activity Recognition Using Wearable Sensors
https://github.com/guoshengcv/cacl
공식 코드Cross-Architecture Self-supervised Video Representation Learning
https://github.com/guoxih/Busy-Quiet-Video-Disentangling-for-Video-Classification
공식 코드https://github.com/guoxih/region-based-non-local-network
공식 코드https://github.com/guoyang9/AdaVQA
공식 코드https://github.com/gurkirt/actNet-inAct
공식 코드Untrimmed Video Classification for Activity Detection: submission to ActivityNet Challenge
https://github.com/guxiao0822/trans_action
공식 코드TransAction: ICL-SJTU Submission to EPIC-Kitchens Action Anticipation Challenge 2021
https://github.com/gzaraunitn/autolabel
공식 코드AutoLabel: CLIP-based framework for Open-set Video Domain Adaptation
https://github.com/gzaraunitn/coloseo
공식 코드Simplifying Open-Set Video Domain Adaptation with Contrastive Learning
https://github.com/h-bouzid/spatr
공식 코드SpATr: MoCap 3D Human Action Recognition based on Spiral Auto-encoder and Transformer Network
https://github.com/haku-huang/h-more
공식 코드H-MoRe: Learning Human-centric Motion Representation for Action Analysis
https://github.com/hammadrizwan/PENME
공식 코드Resolving Lexical Bias in Edit Scoping with Projector Editor Networks
https://github.com/hamzaamrani/Deep-Inertial-Sensory-Clustering
공식 코드Unsupervised Deep Learning-based clustering for Human Activity Recognition
https://github.com/haochen-rye/ModEnsNet
공식 코드Group Ensemble: Learning an Ensemble of ConvNets in a single ConvNet
https://github.com/haohuang2003/sfhead
공식 코드Synchronized and Fine-Grained Head for Skeleton-Based Ambiguous Action Recognition
https://github.com/haoyanbin918/group-contextualization
공식 코드https://github.com/happyharrycn/actionformer_release
공식 코드ActionFormer: Localizing Moments of Actions with Transformers
https://github.com/hartvigsen-group/composable-interventions
공식 코드https://github.com/hassancpu/Temporal-Action-Localization
공식 코드https://github.com/hbilen/dynamic-image-nets
공식 코드https://github.com/hehefan/Point-Spatio-Temporal-Convolution
공식 코드PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences
https://github.com/heleiqiu/sttformer
공식 코드Spatio-Temporal Tuples Transformer for Skeleton-Based Action Recognition
https://github.com/helloworld1973/DNA-DA
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.