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/kahnchana/svt
공식 코드https://github.com/kailliang/Lane-Change-Classification-and-Prediction-with-Action-Recognition-Networks
공식 코드Lane Change Classification and Prediction with Action Recognition Networks
https://github.com/kaiyoo/precondition-and-effect-reasoning-for-action-recognition
공식 코드https://github.com/kakashiz/nedb-net
공식 코드Noise and Edge Based Dual Branch Image Manipulation Detection
https://github.com/kaleab-k/VideoAT
공식 코드Analysis and Extensions of Adversarial Training for Video Classification
https://github.com/kalpitthakkar/pb-gcn
공식 코드Part-based Graph Convolutional Network for Action Recognition
https://github.com/kathpra/lshr_lsht
공식 코드Local Spherical Harmonics Improve Skeleton-Based Hand Action Recognition
https://github.com/kawakera-lab/crossmodeltransfer
공식 코드Cross-Model Transfer of Task Vectors via Few-Shot Orthogonal Alignment
https://github.com/kebii/r2et
공식 코드Skinned Motion Retargeting with Residual Perception of Motion Semantics & Geometry
https://github.com/keltin13/concept-rot
공식 코드Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing
https://github.com/kennymckormick/aras-dataset
공식 코드Mitigating Representation Bias in Action Recognition: Algorithms and Benchmarks
https://github.com/kennymckormick/pyskl
공식 코드PYSKL: Towards Good Practices for Skeleton Action Recognition
https://github.com/kennymckormick/transrank
공식 코드https://github.com/kenshohara/3D-ResNets
공식 코드Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition
https://github.com/kenshohara/3D-ResNets-PyTorch
공식 코드Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?
https://github.com/kenziyuliu/ms-g3d
공식 코드Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition
https://github.com/kevin-ssy/Optical-Flow-Guided-Feature
공식 코드Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognition
https://github.com/keynekassapa13/LAC
공식 코드Self-Supervised Contrastive Learning for Videos using Differentiable Local Alignment
https://github.com/khadidja-delloul/rgb-d-theatre-scenes-dataset
공식 코드TS-RGBD Dataset: a Novel Dataset for Theatre Scenes Description for People with Visual Impairments
https://github.com/khu-vll/devias
공식 코드DEVIAS: Learning Disentangled Video Representations of Action and Scene
https://github.com/khu-vll/glad
공식 코드https://github.com/khuvll/glad
공식 코드https://github.com/kimihiroh/promqa
공식 코드ProMQA: Question Answering Dataset for Multimodal Procedural Activity Understanding
https://github.com/kini5gowda/TruZe
공식 코드A New Split for Evaluating True Zero-Shot Action Recognition
https://github.com/kini5gowda/stories
공식 코드Telling Stories for Common Sense Zero-Shot Action Recognition
https://github.com/kiyoon/channel_sampling
공식 코드Capturing Temporal Information in a Single Frame: Channel Sampling Strategies for Action Recognition
https://github.com/kiyoon/verb_ambiguity
공식 코드An Action Is Worth Multiple Words: Handling Ambiguity in Action Recognition
https://github.com/kiyoon/video-adversarial-augmentation
공식 코드https://github.com/klauscc/tallformer
공식 코드TALLFormer: Temporal Action Localization with a Long-memory Transformer
https://github.com/kmeng01/rome
공식 코드https://github.com/knmac/adaptive_spatiotemporal
공식 코드Efficient Human Vision Inspired Action Recognition using Adaptive Spatiotemporal Sampling
https://github.com/kpeng9510/featfsda
공식 코드Exploring Few-Shot Adaptation for Activity Recognition on Diverse Domains
https://github.com/kpeng9510/hopadiff
공식 코드https://github.com/kpeng9510/os-sar
공식 코드Navigating Open Set Scenarios for Skeleton-based Action Recognition
https://github.com/kpeng9510/proformer
공식 코드Delving Deep into One-Shot Skeleton-based Action Recognition with Diverse Occlusions
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.