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.
Detecting Edit Failures In Large Language Models: An Improved Specificity Benchmark
Cheating off your neighbors: Improving activity recognition through corroboration
CVB: A Video Dataset of Cattle Visual Behaviors
Sharing Leaky-Integrate-and-Fire Neurons for Memory-Efficient Spiking Neural Networks
Deep Neural Networks in Video Human Action Recognition: A Review
Cross-view Action Recognition Understanding From Exocentric to Egocentric Perspective
Generalizable Low-Resource Activity Recognition with Diverse and Discriminative Representation Learning
MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions
Editing Common Sense in Transformers
High Speed Human Action Recognition using a Photonic Reservoir Computer
Large Language Models are Few-Shot Health Learners
Editable Graph Neural Network for Node Classifications
CSI-Based Efficient Self-Quarantine Monitoring System Using Branchy Convolution Neural Network
Masked Path Modeling for Vision-and-Language Navigation
Can We Edit Factual Knowledge by In-Context Learning?
Spatiotemporal Attention-based Semantic Compression for Real-time Video Recognition
FieldHAR: A Fully Integrated End-to-end RTL Framework for Human Activity Recognition with Neural Networks from Heterogeneous Sensors
Enhancing Next Active Object-based Egocentric Action Anticipation with Guided Attention
Contrastive Predictive Autoencoders for Dynamic Point Cloud Self-Supervised Learning
Hang-Time HAR: A Benchmark Dataset for Basketball Activity Recognition using Wrist-Worn Inertial Sensors
Editing Large Language Models: Problems, Methods, and Opportunities
ConvBoost: Boosting ConvNets for Sensor-based Activity Recognition
Language Knowledge-Assisted Representation Learning for Skeleton-Based Action Recognition
Real-time Aerial Detection and Reasoning on Embedded-UAVs
SCP: Soft Conditional Prompt Learning for Aerial Video Action Recognition
WiFi-TCN: Temporal Convolution for Human Interaction Recognition based on WiFi signal
Privacy in Multimodal Federated Human Activity Recognition
Smart Pressure e-Mat for Human Sleeping Posture and Dynamic Activity Recognition
Overcoming Topology Agnosticism: Enhancing Skeleton-Based Action Recognition through Redefined Skeletal Topology Awareness
Riemannian Multinomial Logistics Regression for SPD Neural Networks
rWISDM: Repaired WISDM, a Public Dataset for Human Activity Recognition
Motion-Scenario Decoupling for Rat-Aware Video Position Prediction: Strategy and Benchmark
Evaluation of self-supervised pre-training for automatic infant movement classification using wearable movement sensors
Learning Higher-order Object Interactions for Keypoint-based Video Understanding
Exploring Few-Shot Adaptation for Activity Recognition on Diverse Domains
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.