Papers with Code 아카이브
Action Localization
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 4
- 평가표
- 0
- 보존된 평가 기록
- 0
Action Localization is finding the spatial and temporal co ordinates for an action in a video. An action localization model will identify which frame an action start and ends in video and return the x,y coordinates of an action. Further the co ordinates will change when the object performing action undergoes a displacement.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/zhrli324/rledit
공식 코드https://github.com/zhujiagang/DTPP
공식 코드End-to-end Video-level Representation Learning for Action Recognition
https://github.com/zhujiagang/gating-ConvNet-code
공식 코드Learning Gating ConvNet for Two-Stream based Methods in Action Recognition
https://github.com/zhuoxiao-chen/cevt
공식 코드Conditional Extreme Value Theory for Open Set Video Domain Adaptation
https://github.com/zhysora/fr-head
공식 코드Learning Discriminative Representations for Skeleton Based Action Recognition
https://github.com/zjunlp/BiasEdit
공식 코드BiasEdit: Debiasing Stereotyped Language Models via Model Editing
https://github.com/zjunlp/PromptKG/tree/main/deltaKG
공식 코드https://github.com/zjunlp/cake
공식 코드CaKE: Circuit-aware Editing Enables Generalizable Knowledge Learners
https://github.com/zjunlp/easyedit
공식 코드Editing Large Language Models: Problems, Methods, and Opportunities
https://github.com/zjunlp/knowledgecircuits
공식 코드https://github.com/zjunlp/knowledgeeditingpapers
공식 코드A Comprehensive Study of Knowledge Editing for Large Language Models
https://github.com/zjunlp/knowlm
공식 코드EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Models
https://github.com/zjunlp/oneedit
공식 코드OneEdit: A Neural-Symbolic Collaboratively Knowledge Editing System
https://github.com/zjunlp/pitfallsknowledgeediting
공식 코드Unveiling the Pitfalls of Knowledge Editing for Large Language Models
https://github.com/zjunlp/promptkg
공식 코드https://github.com/znaoya/aenet
공식 코드https://github.com/zongkaiz/fleke
공식 코드https://github.com/zshn25/pc4consistentdepth
공식 코드Pose Constraints for Consistent Self-supervised Monocular Depth and Ego-motion
https://github.com/zympsyche/bevworld
공식 코드BEVWorld: A Multimodal World Model for Autonomous Driving via Unified BEV Latent Space
https://github.com/zzhao71/ripplecot
공식 코드https://github.com/zzxslp/mm-navigator
공식 코드GPT-4V in Wonderland: Large Multimodal Models for Zero-Shot Smartphone GUI Navigation
https://github.com/zzysteve/skeletonx
공식 코드SkeletonX: Data-Efficient Skeleton-based Action Recognition via Cross-sample Feature Aggregation
https://gitlab.com/MISLgit/forensic-similarity-for-digital-images
공식 코드https://huggingface.co/datasets/SoftMINER-Group/NicheHazardQA
공식 코드Sowing the Wind, Reaping the Whirlwind: The Impact of Editing Language Models
https://huggingface.co/datasets/SoftMINER-Group/TechHazardQA
공식 코드https://gitee.com/gai-shaoyan/mind3d
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
https://gitee.com/zhengkeli/zkl-knowedit-rome
https://github.com/1075225782/GCN
Semi-Supervised Classification with Graph Convolutional Networks
https://github.com/1zgh/st-gcn
Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
https://github.com/2023-MindSpore-1/ms-code-11/tree/main/gcn
Semi-Supervised Classification with Graph Convolutional Networks
https://github.com/2023-MindSpore-1/ms-code-17/tree/main/AVA_cifar
AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions
https://github.com/2023-MindSpore-1/ms-code-17/tree/main/BMN
BMN: Boundary-Matching Network for Temporal Action Proposal Generation
https://github.com/2023-MindSpore-1/ms-code-187
A Closer Look at Spatiotemporal Convolutions for Action Recognition
https://github.com/2023-MindSpore-1/ms-code-214/tree/main/flownet2
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
https://github.com/2023-MindSpore-1/ms-code-216/tree/main/ReIDStrongBaseline
Very Deep Convolutional Networks for Large-Scale Image Recognition
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.