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/t-hasegawa-fu/easy-ensemble
공식 코드Easy Ensemble: Simple Deep Ensemble Learning for Sensor-Based Human Activity Recognition
https://github.com/tacju/partimagenet
공식 코드https://github.com/taeoh-kim/temporal_data_augmentation
공식 코드Learning Temporally Invariant and Localizable Features via Data Augmentation for Video Recognition
https://github.com/tailin1009/dualhead-network
공식 코드Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition
https://github.com/take2rohit/stride
공식 코드STRIDE: Single-video based Temporally Continuous Occlusion-Robust 3D Pose Estimation
https://github.com/tal-aurorax/scen
공식 코드https://github.com/talalwasim/video-focalnets
공식 코드Video-FocalNets: Spatio-Temporal Focal Modulation for Video Action Recognition
https://github.com/talalwasim/vita-clip
공식 코드Vita-CLIP: Video and text adaptive CLIP via Multimodal Prompting
https://github.com/taoyang1122/MutualNet
공식 코드MutualNet: Adaptive ConvNet via Mutual Learning from Different Model Configurations
https://github.com/tarun005/FLAVR
공식 코드FLAVR: Flow-Agnostic Video Representations for Fast Frame Interpolation
https://github.com/tecsar-uncc/adg-pose
공식 코드ADG-Pose: Automated Dataset Generation for Real-World Human Pose Estimation
https://github.com/tencentarc/mcq
공식 코드Bridging Video-text Retrieval with Multiple Choice Questions
https://github.com/tencentyouturesearch/actiondetection-lstc
공식 코드LSTC: Boosting Atomic Action Detection with Long-Short-Term Context
https://github.com/tensorflow/models
공식 코드MoViNets: Mobile Video Networks for Efficient Video Recognition
https://github.com/tensorflow/models/tree/master/official/projects/video_ssl
공식 코드https://github.com/tensorflow/models/tree/master/official/vision/beta/projects/assemblenet
공식 코드AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures
https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet
공식 코드EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
https://github.com/thanhhff/MultiASL
공식 코드Action Selection Learning for Multi-label Multi-view Action Recognition
https://github.com/thanhhff/multitsf
공식 코드https://github.com/thartvigsen/grace
공식 코드Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors
https://github.com/the-sky001/widistill
공식 코드WiDistill: Distilling Large-scale Wi-Fi Datasets with Trajectory Matching
https://github.com/themaxiao/ditmos
공식 코드DiTMoS: Delving into Diverse Tiny-Model Selection on Microcontrollers
https://github.com/thu-keg/event-level-knowledge-editing
공식 코드https://github.com/thuhci/MMTSA
공식 코드MMTSA: Multimodal Temporal Segment Attention Network for Efficient Human Activity Recognition
https://github.com/thuml/videodg
공식 코드VideoDG: Generalizing Temporal Relations in Videos to Novel Domains
https://github.com/thunlp/eren
공식 코드https://github.com/tian0426/cl-har
공식 코드What Makes Good Contrastive Learning on Small-Scale Wearable-based Tasks?
https://github.com/tianyuan168326/EAN-Pytorch
공식 코드https://github.com/tigerchen52/qrneuron
공식 코드Identifying Query-Relevant Neurons in Large Language Models for Long-Form Texts
https://github.com/timschoonbeek/industreal
공식 코드https://github.com/tinapan-pt/VideoMoCo
공식 코드VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples
https://github.com/tingz123/fha-kitchens
공식 코드https://github.com/tkipf/pygcn
공식 코드Semi-Supervised Classification with Graph Convolutional Networks
https://github.com/tnbar/tednet
공식 코드Compressing Recurrent Neural Networks with Tensor Ring for Action Recognition
https://github.com/toastydom/net2brain
공식 코드Net2Brain: A Toolbox to compare artificial vision models with human brain responses
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.