paper-with-me

Papers

Stacked Temporal Attention: Improving First-person Action Recognition by Emphasizing Discriminative Clips

2021-12-02 · Lijin Yang, Yifei HUANG, Yusuke Sugano, Yoichi Sato

First-person action recognition is a challenging task in video understanding. Because of strong ego-motion and a limited field of view, many backgrounds or noisy frames in a first-person video can distract an action recognition model during its learning process. To encode more discriminative features, the model needs to have the ability to focus on the most relevant part of the video for action recognition. Previous works explored to address this problem by applying temporal attention but failed to consider the global context of the full video, which is critical for determining the relatively significant parts. In this work, we propose a simple yet effective Stacked Temporal Attention Module (STAM) to compute temporal attention based on the global knowledge across clips for emphasizing the most discriminative features. We achieve this by stacking multiple self-attention layers. Instead of naive stacking, which is experimentally proven to be ineffective, we carefully design the input to each self-attention layer so that both the local and global context of the video is considered during generating the temporal attention weights. Experiments demonstrate that our proposed STAM can be built on top of most existing backbones and boost the performance in various datasets.

📄 PDF Abstract BibTeX arXiv:2112.01038

Code (0)

등록된 구현이 없습니다.

Tasks

Action RecognitionVideo Understanding

Similar Papers 제목 키워드 기반

Enhancing Temporal Understanding in Video-LLMs through Stacked Temporal Attention in Vision Encoders

2025-10-29 · Ali Rasekh, Erfan Bagheri Soula, Omid Daliran, Simon Gottschalk 외 arxiv

Despite significant advances in Multimodal Large Language Models (MLLMs), understanding complex temporal dynamics in videos remains a major challenge. Our experiments show that current Video Large Language Model (Video-L…

Video Question AnsweringAction Recognition

Channel-Temporal Attention for First-Person Video Domain Adaptation

2021-08-17 · Xianyuan Liu, Shuo Zhou, Tao Lei, Haiping Lu

Unsupervised Domain Adaptation (UDA) can transfer knowledge from labeled source data to unlabeled target data of the same categories. However, UDA for first-person action recognition is an under-explored problem, with la…

Action RecognitionDomain AdaptationUnsupervised Domain Adaptation

DeepBrain: Towards Personalized EEG Interaction through Attentional and Embedded LSTM Learning

2020-02-06 · Di Wu, Huayan Wan, Siping Liu, Weiren Yu 외

The "mind-controlling" capability has always been in mankind's fantasy. With the recent advancements of electroencephalograph (EEG) techniques, brain-computer interface (BCI) researchers have explored various solutions t…

Brain Computer InterfaceEEGElectroencephalogram (EEG)

VidTr: Video Transformer Without Convolutions

2021-04-23 · ICCV 2021 10 · Yanyi Zhang, Xinyu Li, Chunhui Liu, Bing Shuai 외

We introduce Video Transformer (VidTr) with separable-attention for video classification. Comparing with commonly used 3D networks, VidTr is able to aggregate spatio-temporal information via stacked attentions and provid…

Action ClassificationAction RecognitionVideo Classification

Stacked Spatio-Temporal Graph Convolutional Networks for Action Segmentation

2018-11-26 · Pallabi Ghosh, Yi Yao, Larry S. Davis, Ajay Divakaran

We propose novel Stacked Spatio-Temporal Graph Convolutional Networks (Stacked-STGCN) for action segmentation, i.e., predicting and localizing a sequence of actions over long videos. We extend the Spatio-Temporal Graph C…

Action RecognitionAction SegmentationDecoderSkeleton Based Action Recognition+1