paper-with-me

Papers

Multiscaled Multi-Head Attention-based Video Transformer Network for Hand Gesture Recognition

2025-01-01 · Mallika Garg, Debashis Ghosh, Pyari Mohan Pradhan

Dynamic gesture recognition is one of the challenging research areas due to variations in pose, size, and shape of the signer's hand. In this letter, Multiscaled Multi-Head Attention Video Transformer Network (MsMHA-VTN) for dynamic hand gesture recognition is proposed. A pyramidal hierarchy of multiscale features is extracted using the transformer multiscaled head attention model. The proposed model employs different attention dimensions for each head of the transformer which enables it to provide attention at the multiscale level. Further, in addition to single modality, recognition performance using multiple modalities is examined. Extensive experiments demonstrate the superior performance of the proposed MsMHA-VTN with an overall accuracy of 88.22\% and 99.10\% on NVGesture and Briareo datasets, respectively.

📄 PDF Abstract BibTeX arXiv:2501.00935

Code (0)

등록된 구현이 없습니다.

Tasks

Gesture RecognitionHand Gesture RecognitionHand-Gesture Recognition

Methods 이 논문이 사용한 방법론

BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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 $x$…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Attention 설명 없음
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Adam 설명 없음

Similar Papers 제목 키워드 기반

ConvTransformer: A Convolutional Transformer Network for Video Frame Synthesis

2020-11-20 · Zhouyong Liu, Shun Luo, Wubin Li, Jingben Lu 외

Deep Convolutional Neural Networks (CNNs) are powerful models that have achieved excellent performance on difficult computer vision tasks. Although CNNs perform well whenever large labeled training samples are available,…

Decoder

SACT: Self-Aware Multi-Space Feature Composition Transformer for Multinomial Attention for Video Captioning

2020-06-25 · Chiranjib Sur

Video captioning works on the two fundamental concepts, feature detection and feature composition. While modern day transformers are beneficial in composing features, they lack the fundamental problems of selecting and u…

Dense Video CaptioningVideo Captioning

Space-time Mixing Attention for Video Transformer

2021-06-10 · NeurIPS 2021 12 · Adrian Bulat, Juan-Manuel Perez-Rua, Swathikiran Sudhakaran, Brais Martinez 외

This paper is on video recognition using Transformers. Very recent attempts in this area have demonstrated promising results in terms of recognition accuracy, yet they have been also shown to induce, in many cases, signi…

Action ClassificationAction RecognitionAction Recognition In VideosVideo Recognition

Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity

2025-02-03 · Haocheng Xi, Shuo Yang, Yilong Zhao, Chenfeng Xu 외

Diffusion Transformers (DiTs) dominate video generation but their high computational cost severely limits real-world applicability, usually requiring tens of minutes to generate a few seconds of video even on high-perfor…

Video Generation

FVAttn: Adaptive Sparse Attention with Runtime Load Balancing for Video Generation

2026-07-17 · Hao Liu, Chenghuan Huang, Ye Huang, Zhiying Wen 외 arxiv

Video Diffusion Transformers process long spatio-temporal sequences, making self-attention the main bottleneck in high-resolution video generation. Training-free sparse attention reduces this cost, but adaptive Top-p rou…

Temporal SequencesVideo Generation