Learning an Augmented RGB Representation with Cross-Modal Knowledge Distillation for Action Detection-Reference-Cited by-同舟云学术

Learning an Augmented RGB Representation with Cross-Modal Knowledge Distillation for Action Detection

Published:2021-10 Issue: Volume: Page:
ISSN:
Container-title:2021 IEEE/CVF International Conference on Computer Vision (ICCV)
language:
Short-container-title:

Author:

Dai Rui¹,Das Srijan²,Bremond Francois¹

Affiliation:

1. Inria

2. Stony Brook University

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/9709627/9709628/09710287.pdf?arnumber=9710287

Reference68 articles.

1. Representation learning with contrastive predictive coding;van den oord;Adv Neural Inform Process Syst,2018

2. Graph Distillation for Action Detection with Privileged Modalities

3. Online human action detection using joint classification-regression recurrent neural networks;li;European Conference on Computer Vision,2016

4. Skeleton-based action recognition with convolutional neural networks;li;2017 IEEE International Conference on Multimedia & Expo Workshops (ICMEW),2017

5. Temporal Convolutional Networks for Action Segmentation and Detection

Cited by 17 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Improving single‐stage activity recognition of excavators using knowledge distillation of temporal gradient data;Computer-Aided Civil and Infrastructure Engineering;2024-01-29

2. Effective Dual-Feature Fusion Network for Transmission Line Detection;IEEE Sensors Journal;2024-01-01

3. Multimodal Reaction: Information Modulation for Cross-Modal Representation Learning;IEEE Transactions on Multimedia;2024

4. Analyze video action with a deep learning model based on space-time and context information;Proceedings of the 12th International Symposium on Information and Communication Technology;2023-12-07

5. LAC - Latent Action Composition for Skeleton-based Action Segmentation;2023 IEEE/CVF International Conference on Computer Vision (ICCV);2023-10-01