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.
FastForensics: Efficient Two-Stream Design for Real-Time Image Manipulation Detection
Online pre-training with long-form videos
DEAR: Depth-Enhanced Action Recognition
Retrieval-Augmented Instruction Tuning for Automated Process Engineering Calculations : A Tool-Chaining Problem-Solving Framework with Attributable Reflection
LLM-Based Multi-Hop Question Answering with Knowledge Graph Integration in Evolving Environments
EPO: Hierarchical LLM Agents with Environment Preference Optimization
Relation Also Knows: Rethinking the Recall and Editing of Factual Associations in Auto-Regressive Transformer Language Models
TSAK: Two-Stage Semantic-Aware Knowledge Distillation for Efficient Wearable Modality and Model Optimization in Manufacturing Lines
Comparative Analysis: Violence Recognition from Videos using Transfer Learning
Towards Battery-Free Wireless Sensing via Radio-Frequency Energy Harvesting
Towards Sustainable Personalized On-Device Human Activity Recognition with TinyML and Cloud-Enabled Auto Deployment
HabitAction: A Video Dataset for Human Habitual Behavior Recognition
Towards Human-Level Understanding of Complex Process Engineering Schematics: A Pedagogical, Introspective Multi-Agent Framework for Open-Domain Question Answering
A Comparison of Deep Learning and Established Methods for Calf Behaviour Monitoring
Enhancing Multi-hop Reasoning through Knowledge Erasure in Large Language Model Editing
Frame Order Matters: A Temporal Sequence-Aware Model for Few-Shot Action Recognition
TWLV-I: Analysis and Insights from Holistic Evaluation on Video Foundation Models
Generative AI based Secure Wireless Sensing for ISAC Networks
Explainable Deep Learning Framework for Human Activity Recognition
Limitations in Employing Natural Language Supervision for Sensor-Based Human Activity Recognition -- And Ways to Overcome Them
Beneath the Surface of Consistency: Exploring Cross-lingual Knowledge Representation Sharing in LLMs
TDS-CLIP: Temporal Difference Side Network for Image-to-Video Transfer Learning
MEGen: Generative Backdoor in Large Language Models via Model Editing
Event Stream based Human Action Recognition: A High-Definition Benchmark Dataset and Algorithms
Attribution Analysis Meets Model Editing: Advancing Knowledge Correction in Vision Language Models with VisEdit
SHARP: Segmentation of Hands and Arms by Range using Pseudo-Depth for Enhanced Egocentric 3D Hand Pose Estimation and Action Recognition
Resolving Lexical Bias in Edit Scoping with Projector Editor Networks
ELDER: Enhancing Lifelong Model Editing with Mixture-of-LoRA
Joint Temporal Pooling for Improving Skeleton-based Action Recognition
ALS-HAR: Harnessing Wearable Ambient Light Sensors to Enhance IMU-based Human Activity Recogntion
Temporal Reversed Training for Spiking Neural Networks with Generalized Spatio-Temporal Representation
Flatten: Video Action Recognition is an Image Classification task
Towards Physical World Backdoor Attacks against Skeleton Action Recognition
General-purpose Clothes Manipulation with Semantic Keypoints
Action Recognition for Privacy-Preserving Ambient Assisted Living
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.