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.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Implicit Temporal Modeling with Learnable Alignment for Video Recognition
On the Effectiveness of Image Manipulation Detection in the Age of Social Media
Self-Supervised 3D Action Representation Learning with Skeleton Cloud Colorization
GoferBot: A Visual Guided Human-Robot Collaborative Assembly System
Human activity recognition using deep learning approaches and single frame cnn and convolutional lstm
ATTACH Dataset: Annotated Two-Handed Assembly Actions for Human Action Understanding
Robust Cross-Modal Knowledge Distillation for Unconstrained Videos
PMI Sampler: Patch Similarity Guided Frame Selection for Aerial Action Recognition
NEV-NCD: Negative Learning, Entropy, and Variance regularization based novel action categories discovery
Peer-to-Peer Federated Continual Learning for Naturalistic Driving Action Recognition
Skeleton-based action analysis for ADHD diagnosis
Attack-Augmentation Mixing-Contrastive Skeletal Representation Learning
Vita-CLIP: Video and text adaptive CLIP via Multimodal Prompting
Therbligs in Action: Video Understanding through Motion Primitives
Off-Policy Action Anticipation in Multi-Agent Reinforcement Learning
A real-time algorithm for human action recognition in RGB and thermal video
DIR-AS: Decoupling Individual Identification and Temporal Reasoning for Action Segmentation
Focalized Contrastive View-invariant Learning for Self-supervised Skeleton-based Action Recognition
MoLo: Motion-augmented Long-short Contrastive Learning for Few-shot Action Recognition
AutoLabel: CLIP-based framework for Open-set Video Domain Adaptation
On the Benefits of 3D Pose and Tracking for Human Action Recognition
DOAD: Decoupled One Stage Action Detection Network
HaLP: Hallucinating Latent Positives for Skeleton-based Self-Supervised Learning of Actions
STMT: A Spatial-Temporal Mesh Transformer for MoCap-Based Action Recognition
HARFLOW3D: A Latency-Oriented 3D-CNN Accelerator Toolflow for HAR on FPGA Devices
Streaming Video Model
VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking
A Video-based End-to-end Pipeline for Non-nutritive Sucking Action Recognition and Segmentation in Young Infants
Colo-SCRL: Self-Supervised Contrastive Representation Learning for Colonoscopic Video Retrieval
Unmasked Teacher: Towards Training-Efficient Video Foundation Models
Rethinking matching-based few-shot action recognition
CycleACR: Cycle Modeling of Actor-Context Relations for Video Action Detection
TimeBalance: Temporally-Invariant and Temporally-Distinctive Video Representations for Semi-Supervised Action Recognition
Structured Video-Language Modeling with Temporal Grouping and Spatial Grounding
Prompt-Guided Zero-Shot Anomaly Action Recognition using Pretrained Deep Skeleton Features
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.