Papers with Code 아카이브
Action Recognition
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 15
- 평가표
- 56
- 보존된 평가 기록
- 650
Action Recognition is a computer vision task that involves recognizing human actions in videos or images. The goal is to classify and categorize the actions being performed in the video or image into a predefined set of action classes.
In the video domain, it is an open question whether training an action classification network on a sufficiently large dataset, will give a similar boost in performance when applied to a different temporal task or dataset. The challenges of building video datasets has meant that most popular benchmarks for action recognition are small, having on the order of 10k videos.
Please note some benchmarks may be located in the Action Classification or Video Classification tasks, e.g. Kinetics-400.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/opengvlab/egovideo
공식 코드EgoVideo: Exploring Egocentric Foundation Model and Downstream Adaptation
https://github.com/opengvlab/hulk
공식 코드Hulk: A Universal Knowledge Translator for Human-Centric Tasks
https://github.com/opengvlab/humanbench
공식 코드Hulk: A Universal Knowledge Translator for Human-Centric Tasks
https://github.com/opengvlab/internvideo
공식 코드InternVideo: General Video Foundation Models via Generative and Discriminative Learning
https://github.com/opengvlab/internvideo2
공식 코드InternVideo2: Scaling Foundation Models for Multimodal Video Understanding
https://github.com/opengvlab/unmasked_teacher
공식 코드Unmasked Teacher: Towards Training-Efficient Video Foundation Models
https://github.com/openvinotoolkit/training_extensions
공식 코드ASL Recognition with Metric-Learning based Lightweight Network
https://github.com/optas/artemis
공식 코드https://github.com/ostadabbas/nns-detection-and-segmentation
공식 코드https://github.com/ostadabbas/video-based-infant-action-recognition
공식 코드Challenges in Video-Based Infant Action Recognition: A Critical Examination of the State of the Art
https://github.com/osvai/ske2grid
공식 코드Ske2Grid: Skeleton-to-Grid Representation Learning for Action Recognition
https://github.com/outsiders17711/e2eet-skeleton-based-hgr-using-data-level-fusion
공식 코드Real-Time Hand Gesture Recognition: Integrating Skeleton-Based Data Fusion and Multi-Stream CNN
https://github.com/ouxiang-li/speed
공식 코드SPEED: Scalable, Precise, and Efficient Concept Erasure for Diffusion Models
https://github.com/paddlepaddle/paddlevideo
공식 코드A Survey on Video Action Recognition in Sports: Datasets, Methods and Applications
https://github.com/paolomandica/hysp
공식 코드HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations
https://github.com/papermsucode/mutual-modality-learning
공식 코드https://github.com/park-jungin/dualpath
공식 코드https://github.com/pedro-dm-gomes/agar
공식 코드AGAR: Attention Graph-RNN for Adaptative Motion Prediction of Point Clouds of Deformable Objects
https://github.com/perathambkk/lipreading
공식 코드SpotFast Networks with Memory Augmented Lateral Transformers for Lipreading
https://github.com/pha123661/SA-DVAE
공식 코드https://github.com/philipposg/osdd
공식 코드Detecting Object States vs Detecting Objects: A New Dataset and a Quantitative Experimental Study
https://github.com/pic4ser/act
공식 코드Action Transformer: A Self-Attention Model for Short-Time Pose-Based Human Action Recognition
https://github.com/pic4ser/mpose2021
공식 코드Action Transformer: A Self-Attention Model for Short-Time Pose-Based Human Action Recognition
https://github.com/pic4sercentre/mpose2021
공식 코드Action Transformer: A Self-Attention Model for Short-Time Pose-Based Human Action Recognition
https://github.com/piergiaj/AViD
공식 코드https://github.com/piergiaj/representation-flow-cvpr19
공식 코드https://github.com/pkorus/neural-imaging
공식 코드https://github.com/pkunlp-icler/ike
공식 코드https://github.com/pmorerio/admd
공식 코드Learning with privileged information via adversarial discriminative modality distillation
https://github.com/polimi-ispl/icpr2020dfdc
공식 코드https://github.com/prabuddha1/acpe
공식 코드https://github.com/princeton-nlp/mquake
공식 코드MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions
https://github.com/prinshul/GWSDR
공식 코드https://github.com/pritamqu/CrissCross
공식 코드Self-Supervised Audio-Visual Representation Learning with Relaxed Cross-Modal Synchronicity
https://github.com/pritamqu/XKD
공식 코드XKD: Cross-modal Knowledge Distillation with Domain Alignment for Video Representation Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.