Papers with Code 아카이브
Action Detection
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 8
- 평가표
- 11
- 보존된 평가 기록
- 81
Action Detection aims to find both where and when an action occurs within a video clip and classify what the action is taking place. Typically results are given in the form of action tublets, which are action bounding boxes linked across time in the video. This is related to temporal localization, which seeks to identify the start and end frame of an action, and action recognition, which seeks only to classify which action is taking place and typically assumes a trimmed video.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment
CBF-AFA: Chunk-Based Multi-SSL Fusion for Automatic Fluency Assessment
MultiHuman-Testbench: Benchmarking Image Generation for Multiple Humans
SEZ-HARN: Self-Explainable Zero-shot Human Activity Recognition Network
Including Semantic Information via Word Embeddings for Skeleton-based Action Recognition
Distributed Activity Detection for Cell-Free Hybrid Near-Far Field Communications
DeSPITE: Exploring Contrastive Deep Skeleton-Pointcloud-IMU-Text Embeddings for Advanced Point Cloud Human Activity Understanding
MORIC: CSI Delay-Doppler Decomposition for Robust Wi-Fi-based Human Activity Recognition
AgentSense: Virtual Sensor Data Generation Using LLM Agents in Simulated Home Environments
ScalableHD: Scalable and High-Throughput Hyperdimensional Computing Inference on Multi-Core CPUs
Scaling Human Activity Recognition: A Comparative Evaluation of Synthetic Data Generation and Augmentation Techniques
Through-the-Wall Radar Human Activity Recognition WITHOUT Using Neural Networks
Speaker Diarization with Overlapping Community Detection Using Graph Attention Networks and Label Propagation Algorithm
Attention Is Not Always the Answer: Optimizing Voice Activity Detection with Simple Feature Fusion
3D Skeleton-Based Action Recognition: A Review
Joint Activity Detection and Channel Estimation for Massive Connectivity: Where Message Passing Meets Score-Based Generative Priors
Knowledge Distillation for Reservoir-based Classifier: Human Activity Recognition
Spatio-Temporal Joint Density Driven Learning for Skeleton-Based Action Recognition
Towards Robust Overlapping Speech Detection: A Speaker-Aware Progressive Approach Using WavLM
MoPFormer: Motion-Primitive Transformer for Wearable-Sensor Activity Recognition
Enhancing Wearable Tap Water Audio Detection through Subclass Annotation in the HD-Epic Dataset
DeepConvContext: A Multi-Scale Approach to Timeseries Classification in Human Activity Recognition
Label Leakage in Federated Inertial-based Human Activity Recognition
SETransformer: A Hybrid Attention-Based Architecture for Robust Human Activity Recognition
Few-Shot Optimization for Sensor Data Using Large Language Models: A Case Study on Fatigue Detection
SPAR: Self-supervised Placement-Aware Representation Learning for Multi-Node IoT Systems
Robust Activity Detection for Massive Random Access
Time Series Similarity Score Functions to Monitor and Interact with the Training and Denoising Process of a Time Series Diffusion Model applied to a Human Activity Recognition Dataset based on IMUs
FlexFed: Mitigating Catastrophic Forgetting in Heterogeneous Federated Learning in Pervasive Computing Environments
Improving endpoint detection in end-to-end streaming ASR for conversational speech
Multi-Stage Speaker Diarization for Noisy Classrooms
A Training Framework for Optimal and Stable Training of Polynomial Neural Networks
SOS: A Shuffle Order Strategy for Data Augmentation in Industrial Human Activity Recognition
MONAQ: Multi-Objective Neural Architecture Querying for Time-Series Analysis on Resource-Constrained Devices
Beyond Pixels: Leveraging the Language of Soccer to Improve Spatio-Temporal Action Detection in Broadcast Videos
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.