Papers with Code 아카이브
Activity Recognition
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 11
- 평가표
- 4
- 보존된 평가 기록
- 10
Human Activity Recognition is the problem of identifying events performed by humans given a video input. It is formulated as a binary (or multiclass) classification problem of outputting activity class labels. Activity Recognition is an important problem with many societal applications including smart surveillance, video search/retrieval, intelligent robots, and other monitoring systems.
Source: Learning Latent Sub-events in Activity Videos Using Temporal Attention Filters
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Finding and Editing Multi-Modal Neurons in Pre-Trained Transformers
FedOpenHAR: Federated Multi-Task Transfer Learning for Sensor-Based Human Activity Recognition
Trends in Integration of Knowledge and Large Language Models: A Survey and Taxonomy of Methods, Benchmarks, and Applications
A Wi-Fi Signal-Based Human Activity Recognition Using High-Dimensional Factor Models
Quantized Distillation: Optimizing Driver Activity Recognition Models for Resource-Constrained Environments
Semantic-aware Video Representation for Few-shot Action Recognition
Learning Human Action Recognition Representations Without Real Humans
Game Theory Solutions in Sensor-Based Human Activity Recognition: A Review
Massive Editing for Large Language Models via Meta Learning
OmniVec: Learning robust representations with cross modal sharing
Asymmetric Masked Distillation for Pre-Training Small Foundation Models
Distributed Agent-Based Collaborative Learning in Cross-Individual Wearable Sensor-Based Human Activity Recognition
FPGA-QHAR: Throughput-Optimized for Quantized Human Action Recognition on The Edge
Concatenated Masked Autoencoders as Spatial-Temporal Learner
Distilling Knowledge from CNN-Transformer Models for Enhanced Human Action Recognition
ProBio: A Protocol-guided Multimodal Dataset for Molecular Biology Lab
DEPN: Detecting and Editing Privacy Neurons in Pretrained Language Models
Pose-to-Motion: Cross-Domain Motion Retargeting with Pose Prior
Object-centric Video Representation for Long-term Action Anticipation
rTsfNet: a DNN model with Multi-head 3D Rotation and Time Series Feature Extraction for IMU-based Human Activity Recognition
A Survey on Knowledge Editing of Neural Networks
Optimization-Free Test-Time Adaptation for Cross-Person Activity Recognition
IndustReal: A Dataset for Procedure Step Recognition Handling Execution Errors in Egocentric Videos in an Industrial-Like Setting
On the recognition of the game type based on physiological signals and eye tracking
Distribution of Action Movements (DAM): A Descriptor for Human Action Recognition
Knowledge Editing for Large Language Models: A Survey
S3Aug: Segmentation, Sampling, and Shift for Action Recognition
Videoprompter: an ensemble of foundational models for zero-shot video understanding
Cross-Domain HAR: Few Shot Transfer Learning for Human Activity Recognition
ConViViT -- A Deep Neural Network Combining Convolutions and Factorized Self-Attention for Human Activity Recognition
Is Weakly-supervised Action Segmentation Ready For Human-Robot Interaction? No, Let's Improve It With Action-union Learning
Localizing and Editing Knowledge in Text-to-Image Generative Models
Deep Learning Techniques for Video Instance Segmentation: A Survey
Frozen Transformers in Language Models Are Effective Visual Encoder Layers
Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Survey
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.