Papers with Code 아카이브
Action Classification
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 28
- 보존된 평가 기록
- 444
Image source: The Kinetics Human Action Video Dataset
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/adeboissiere/FUSION-human-action-recognition
공식 코드Infrared and 3D skeleton feature fusion for RGB-D action recognition
https://github.com/ahmed-nady/multimodal-action-recognition
공식 코드EPAM-Net: An Efficient Pose-driven Attention-guided Multimodal Network for Video Action Recognition
https://github.com/airsplay/vimpac
공식 코드VIMPAC: Video Pre-Training via Masked Token Prediction and Contrastive Learning
https://github.com/akshitac8/tfvaegan
공식 코드Latent Embedding Feedback and Discriminative Features for Zero-Shot Classification
https://github.com/alexandrosstergiou/Saliency-Tubes-Visual-Explanations-for-Spatio-Temporal-Convolutions
공식 코드Saliency Tubes: Visual Explanations for Spatio-Temporal Convolutions
https://github.com/alexandrosstergiou/Squeeze-and-Recursion-Temporal-Gates/blob/master/train_model.py
공식 코드Learn to cycle: Time-consistent feature discovery for action recognition
https://github.com/alibaba-mmai-research/TAdaConv
공식 코드Temporally-Adaptive Models for Efficient Video Understanding
https://github.com/alibaba-mmai-research/masked-action-recognition
공식 코드https://github.com/alibaba-mmai-research/pytorch-video-understanding
공식 코드TAda! Temporally-Adaptive Convolutions for Video Understanding
https://github.com/alibaba/AliceMind
공식 코드mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video
https://github.com/amazon-research/video-contrastive-learning
공식 코드https://github.com/anirudhs123/home
공식 코드https://github.com/anonymous-p/Flickering_Adversarial_Video
공식 코드Over-the-Air Adversarial Flickering Attacks against Video Recognition Networks
https://github.com/anshulbshah/PoseAction
공식 코드https://github.com/aroitberg/sims4action
공식 코드https://github.com/baaivision/eva
공식 코드EVA: Exploring the Limits of Masked Visual Representation Learning at Scale
https://github.com/bomri/SlowFast/blob/master/projects/vtn/README.md
공식 코드https://github.com/bouracha/generative_imputation
공식 코드Hierarchical Graph-Convolutional Variational AutoEncoding for Generative Modelling of Human Motion
https://github.com/buxiangzhiren/contextloc
공식 코드Enriching Local and Global Contexts for Temporal Action Localization
https://github.com/ccp-eva/sporttaskme21
공식 코드Spatio-Temporal CNN baseline method for the Sports Video Task of MediaEval 2021 benchmark
https://github.com/ccp-eva/sporttaskme22
공식 코드Baseline Method for the Sport Task of MediaEval 2022 with 3D CNNs using Attention Mechanisms
https://github.com/chihyaoma/Activity-Recognition-with-CNN-and-RNN
공식 코드TS-LSTM and Temporal-Inception: Exploiting Spatiotemporal Dynamics for Activity Recognition
https://github.com/czyssrs/GloREPlus
공식 코드Global Textual Relation Embedding for Relational Understanding
https://github.com/daveishan/spact
공식 코드SPAct: Self-supervised Privacy Preservation for Action Recognition
https://github.com/ddz16/TUT
공식 코드Do we really need temporal convolutions in action segmentation?
https://github.com/deepglint/alip
공식 코드ALIP: Adaptive Language-Image Pre-training with Synthetic Caption
https://github.com/dominickrei/pi-vit
공식 코드Just Add $π$! Pose Induced Video Transformers for Understanding Activities of Daily Living
https://github.com/dominickrei/poseawarevt
공식 코드Seeing the Pose in the Pixels: Learning Pose-Aware Representations in Vision Transformers
https://github.com/dxli94/WLASL
공식 코드https://github.com/epic-kitchens/action-models
공식 코드https://github.com/facebookresearch/GloRe
공식 코드https://github.com/facebookresearch/Motionformer
공식 코드Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers
https://github.com/facebookresearch/OctConv
공식 코드Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution
https://github.com/facebookresearch/R2Plus1D
공식 코드A Closer Look at Spatiotemporal Convolutions for Action Recognition
https://github.com/facebookresearch/SlowFast
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.