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.
A Comprehensive Review of Few-shot Action Recognition
Decoupled Prompt-Adapter Tuning for Continual Activity Recognition
Can VLMs be used on videos for action recognition? LLMs are Visual Reasoning Coordinators
LORTSAR: Low-Rank Transformer for Skeleton-based Action Recognition
QuIIL at T3 challenge: Towards Automation in Life-Saving Intervention Procedures from First-Person View
SA-DVAE: Improving Zero-Shot Skeleton-Based Action Recognition by Disentangled Variational Autoencoders
Robots Can Multitask Too: Integrating a Memory Architecture and LLMs for Enhanced Cross-Task Robot Action Generation
Pose-guided multi-task video transformer for driver action recognition
CDFL: Efficient Federated Human Activity Recognition using Contrastive Learning and Deep Clustering
Shap-Mix: Shapley Value Guided Mixing for Long-Tailed Skeleton Based Action Recognition
Frequency Guidance Matters: Skeletal Action Recognition by Frequency-Aware Mixed Transformer
Enhancing Split Computing and Early Exit Applications through Predefined Sparsity
Gated Temporal Diffusion for Stochastic Long-Term Dense Anticipation
Human-Centric Transformer for Domain Adaptive Action Recognition
STARS: Self-supervised Tuning for 3D Action Recognition in Skeleton Sequences
Do You Act Like You Talk? Exploring Pose-based Driver Action Classification with Speech Recognition Networks
Augmented Neural Fine-Tuning for Efficient Backdoor Purification
Cross-Lingual Multi-Hop Knowledge Editing -- Benchmarks, Analysis and a Simple Contrastive Learning based Approach
Region-aware Image-based Human Action Retrieval with Transformers
Evaluation of Encoding Schemes on Ubiquitous Sensor Signal for Spiking Neural Network
Guidelines for Augmentation Selection in Contrastive Learning for Time Series Classification
Boosting Adversarial Transferability for Skeleton-based Action Recognition via Exploring the Model Posterior Space
Sensor-Aware Classifiers for Energy-Efficient Time Series Applications on IoT Devices
EA-VTR: Event-Aware Video-Text Retrieval
Mitigating Backdoor Attacks using Activation-Guided Model Editing
Composable Interventions for Language Models
CrowdTransfer: Enabling Crowd Knowledge Transfer in AIoT Community
Masked Video and Body-worn IMU Autoencoder for Egocentric Action Recognition
Rethinking Image-to-Video Adaptation: An Object-centric Perspective
DMSD-CDFSAR: Distillation from Mixed-Source Domain for Cross-Domain Few-shot Action Recognition
C2C: Component-to-Composition Learning for Zero-Shot Compositional Action Recognition
CodeUpdateArena: Benchmarking Knowledge Editing on API Updates
GeoWATCH for Detecting Heavy Construction in Heterogeneous Time Series of Satellite Images
Topological Persistence Guided Knowledge Distillation for Wearable Sensor Data
Self-supervised Learning via Cluster Distance Prediction for Operating Room Context Awareness
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.