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/YangDi666/SSTA-PRS
공식 코드https://github.com/YangDi666/UNIK
공식 코드UNIK: A Unified Framework for Real-world Skeleton-based Action Recognition
https://github.com/YangLiu9208/SAKDN
공식 코드Semantics-aware Adaptive Knowledge Distillation for Sensor-to-Vision Action Recognition
https://github.com/YihengZhang-CV/SeCo-Sequence-Contrastive-Learning
공식 코드SeCo: Exploring Sequence Supervision for Unsupervised Representation Learning
https://github.com/YinxPeng/HA-CM-main
공식 코드https://github.com/Ymm-cll/UniErase
공식 코드UniErase: Unlearning Token as a Universal Erasure Primitive for Language Models
https://github.com/YorkUCVIL/Static-Dynamic-Interpretability
공식 코드https://github.com/ZeruiW/VideoXAI
공식 코드https://github.com/ZhaofanQiu/pseudo-3d-residual-networks
공식 코드Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks
https://github.com/ZhenyueQin/Angular-Skeleton-Encoding
공식 코드Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition
https://github.com/ZhouYuxuanYX/Hypergraph-Transformer-for-Skeleton-based-Action-Recognition
공식 코드Hypergraph Transformer for Skeleton-based Action Recognition
https://github.com/Zhow01/S2RKE
공식 코드https://github.com/ZichenMiao/GNN-with-Low-rank-Learnable-Local-Filters
공식 코드https://github.com/ZichenMiao/L3Net
공식 코드https://github.com/ZihaoZhao/SpikeGatingFlow
공식 코드https://github.com/ZiweiXU/CapsuleMotion
공식 코드Unsupervised Motion Representation Learning with Capsule Autoencoders
https://github.com/aaai-24/generative-based-kd
공식 코드Generative Model-based Feature Knowledge Distillation for Action Recognition
https://github.com/abcyzj/Semantics2Hands
공식 코드Semantics2Hands: Transferring Hand Motion Semantics between Avatars
https://github.com/abcyzj/meshret
공식 코드Skinned Motion Retargeting with Dense Geometric Interaction Perception
https://github.com/abhinanda-punnakkal/BABEL
공식 코드https://github.com/acerkoo/disco
공식 코드Outdated Issue Aware Decoding for Reasoning Questions on Edited Knowledge
https://github.com/acewjh/fsfg
공식 코드Few-Shot Fine-Grained Action Recognition via Bidirectional Attention and Contrastive Meta-Learning
https://github.com/adap/flower
공식 코드https://github.com/adaptivemotorcontrollab/llavaction
공식 코드LLaVAction: evaluating and training multi-modal large language models for action recognition
https://github.com/adeboissiere/FUSION-human-action-recognition
공식 코드Infrared and 3D skeleton feature fusion for RGB-D action recognition
https://github.com/adityac94/Grad_CAM_plus_plus
공식 코드Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks
https://github.com/adrianiordache/mlfd
공식 코드Multi-Level Feature Distillation of Joint Teachers Trained on Distinct Image Datasets
https://github.com/aengusl/latent-adversarial-training
공식 코드Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs
https://github.com/afperezm/acoustic-images-distillation
공식 코드https://github.com/againerju/tcg_recognition
공식 코드https://github.com/aheldis/Attack-on-Scene-Flow-using-Point-Clouds
공식 코드https://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/ahmetgunduz/Real-time-GesRec
공식 코드Real-time Hand Gesture Detection and Classification Using Convolutional Neural Networks
https://github.com/ai-forever/ghost
공식 코드A new face swap method for image and video domains: a technical report
https://github.com/ai4life-group/splice
공식 코드Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.