Action Recognition

56개 벤치마크 · 논문 3,044편 · 이 태스크의 논문 보기 →

Benchmarks

Real Life Violence Situations Dataset

결과 6개

Most implemented

EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

2019-05-28 · 구현 144개

Learning Transferable Visual Models From Natural Language Supervision

2021-02-26 · 구현 82개

Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset

2017-05-22 · 구현 34개

Learning Spatiotemporal Features with 3D Convolutional Networks

2014-12-02 · 구현 29개

Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?

2017-11-27 · 구현 26개

Papers

SAFER-Activities: A Dataset for Smart Assessment of Fall Events and Routine Activities

2026-09-07 · Diwas Lamsal, Pramod Wickramatilake, Jednipat Moonrinta, Mongkol Ekpanyapong 외 arxiv

Smart healthcare monitoring systems require precise action recognition to ensure well-being and timely intervention in critical situations such as falls, particularly for mobility-challenged individuals. Existing dataset…

Action Recognition

Few-Shot Video Recognition via Hierarchical Metric Learning

2026-09-04 · Jiaxin Zhang, Haoran Gao, Xizhan Gao, Zihao Dong 외 arxiv

Few-shot action recognition (FSAR) aims to recognize unseen action categories with only a small number of annotated video samples. Recent works typically apply single-prototype supervision at the network output and fail …

Action Recognition Metric Learning

Hidden In Plain Gaze: Gaze Representations as Privacy Controls for Utility and Re-identification Risk in XR

2026-09-04 · Cory Ilo, Brendan-David John, Doug A. Bowman arxiv

Intelligent extended reality (XR) systems increasingly use eye and head tracking to infer user intent, task, and attention, but the same signals can also reveal biometric identity. We study whether gaze data representati…

Action Recognition

Pose-Anchored Optical Flow for Low-Latency Human Action Anticipation in Human-Robot Teaming

2026-08-26 · Lewis de Zoete Grundy, Chris McCarthy, Christopher Fluke arxiv

Human-robot interaction (HRI) requires robots to interpret human actions early in their execution in order to respond safely, efficiently, and naturally. However, many existing approaches to human action recognition rely…

Action Anticipation Action Recognition

MoTE: Mixture of Task Experts for Multi-Task Video Understanding

2026-08-25 · Muhammad Asad Ali, Umar Khan, Nadia Robertini, Didier Stricker hf

Procedural video-language models must solve heterogeneous tasks from the same visual evidence, including action recognition, forecasting, and procedure prediction. Dense transformer decoders share the same feed-forward n…

Action Recognition

ByteAction: Byte-space Action Recognition Foundation Model

2026-08-24 · Fangcheng Li, Zhen Yu, Kejun Wu, Qiong Liu 외 arxiv

Byte-space Action Recognition (BAR) aims to recognize human actions directly from compressed image bitstreams without any pixel decoding. By operating entirely in byte space, BAR is inherently independent of file integri…

Action Recognition

전체 3,044편 보기 →