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.
Editing Implicit Assumptions in Text-to-Image Diffusion Models
3DInAction: Understanding Human Actions in 3D Point Clouds
DECOMPL: Decompositional Learning with Attention Pooling for Group Activity Recognition from a Single Volleyball Image
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations
Zone-based Federated Learning for Mobile Sensing Data
Robust Multimodal Fusion for Human Activity Recognition
Sleep Quality Prediction from Wearables using Convolution Neural Networks and Ensemble Learning
Challenges of the Creation of a Dataset for Vision Based Human Hand Action Recognition in Industrial Assembly
Learning Discriminative Representations for Skeleton Based Action Recognition
Event Voxel Set Transformer for Spatiotemporal Representation Learning on Event Streams
CLIP-guided Prototype Modulating for Few-shot Action Recognition
SPARTAN: Self-supervised Spatiotemporal Transformers Approach to Group Activity Recognition
MITFAS: Mutual Information based Temporal Feature Alignment and Sampling for Aerial Video Action Recognition
Maximizing Spatio-Temporal Entropy of Deep 3D CNNs for Efficient Video Recognition
VALERIAN: Invariant Feature Learning for IMU Sensor-based Human Activity Recognition in the Wild
Towards Activated Muscle Group Estimation in the Wild
Ego-Vehicle Action Recognition based on Semi-Supervised Contrastive Learning
AZTR: Aerial Video Action Recognition with Auto Zoom and Temporal Reasoning
EdgeServe: A Streaming System for Decentralized Model Serving
Sketch2Cloth: Sketch-based 3D Garment Generation with Unsigned Distance Fields
Knowledge Augmented Relation Inference for Group Activity Recognition
Edit at your own risk: evaluating the robustness of edited models to distribution shifts
Texture-Based Input Feature Selection for Action Recognition
Unsupervised Video Anomaly Detection for Stereotypical Behaviours in Autism
Open Set Action Recognition via Multi-Label Evidential Learning
Spatial-temporal Transformer-guided Diffusion based Data Augmentation for Efficient Skeleton-based Action Recognition
Temporal-Channel Topology Enhanced Network for Skeleton-Based Action Recognition
A Preliminary Study on Pattern Reconstruction for Optimal Storage of Wearable Sensor Data
FG-SSA: Features Gradient-based Signals Selection Algorithm of Linear Complexity for Convolutional Neural Networks
DMMG: Dual Min-Max Games for Self-Supervised Skeleton-Based Action Recognition
Weakly Supervised Temporal Convolutional Networks for Fine-grained Surgical Activity Recognition
Analysis of Real-Time Hostile Activitiy Detection from Spatiotemporal Features Using Time Distributed Deep CNNs, RNNs and Attention-Based Mechanisms
Table Tennis Stroke Detection and Recognition Using Ball Trajectory Data
On Handling Catastrophic Forgetting for Incremental Learning of Human Physical Activity on the Edge
Dynamic Spatial-temporal Hypergraph Convolutional Network for Skeleton-based Action Recognition
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.