paper-with-me

홈 › Papers

CA3D: Convolutional-Attentional 3D Nets for Efficient Video Activity Recognition on the Edge

2025-05-26 · Gabriele Lagani, Fabrizio Falchi, Claudio Gennaro, Giuseppe Amato

In this paper, we introduce a deep learning solution for video activity recognition that leverages an innovative combination of convolutional layers with a linear-complexity attention mechanism. Moreover, we introduce a novel quantization mechanism to further improve the efficiency of our model during both training and inference. Our model maintains a reduced computational cost, while preserving robust learning and generalization capabilities. Our approach addresses the issues related to the high computing requirements of current models, with the goal of achieving competitive accuracy on consumer and edge devices, enabling smart home and smart healthcare applications where efficiency and privacy issues are of concern. We experimentally validate our model on different established and publicly available video activity recognition benchmarks, improving accuracy over alternative models at a competitive computing cost.

📄 PDF Abstract BibTeX arXiv:2505.19928

Code (0)

등록된 구현이 없습니다.

Tasks

Activity RecognitionQuantization

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition

2017-08-25 · Kensho Hara, Hirokatsu Kataoka, Yutaka Satoh

Convolutional neural networks with spatio-temporal 3D kernels (3D CNNs) have an ability to directly extract spatio-temporal features from videos for action recognition. Although the 3D kernels tend to overfit because of …

Action RecognitionHand-Gesture RecognitionTemporal Action Localization

Anomaly Recognition from surveillance videos using 3D Convolutional Neural Networks

2021-01-04 · R. Maqsood, UI. Bajwa, G. Saleem, Rana H. Raza 외

Anomalous activity recognition deals with identifying the patterns and events that vary from the normal stream. In a surveillance paradigm, these events range from abuse to fighting and road accidents to snatching, etc. …

Activity RecognitionAnomaly DetectionBinary Classification

Human Activity Recognition Using Cascaded Dual Attention CNN and Bi-Directional GRU Framework

2022-08-09 · Hayat Ullah, Arslan Munir

Vision-based human activity recognition has emerged as one of the essential research areas in video analytics domain. Over the last decade, numerous advanced deep learning algorithms have been introduced to recognize com…

Action RecognitionActivity RecognitionComputational EfficiencyHuman Activity Recognition

Video-FocalNets: Spatio-Temporal Focal Modulation for Video Action Recognition

2023-07-13 · ICCV 2023 1 · Syed Talal Wasim, Muhammad Uzair Khattak, Muzammal Naseer, Salman Khan 외

Recent video recognition models utilize Transformer models for long-range spatio-temporal context modeling. Video transformer designs are based on self-attention that can model global context at a high computational cost…

Action RecognitionTemporal Action LocalizationVideo Recognition

Chirality Nets for Human Pose Regression

2019-10-31 · NeurIPS 2019 12 · Raymond A. Yeh, Yuan-Ting Hu, Alexander G. Schwing

We propose Chirality Nets, a family of deep nets that is equivariant to the "chirality transform," i.e., the transformation to create a chiral pair. Through parameter sharing, odd and even symmetry, we propose and prove …

3D Human Pose Estimation3D Pose EstimationActivity RecognitionPose Estimation+2