paper-with-me

Papers

DCTM: Dilated Convolutional Transformer Model for Multimodal Engagement Estimation in Conversation

2023-07-31 · Vu Ngoc Tu, Van Thong Huynh, Hyung-Jeong Yang, M. Zaigham Zaheer, Shah Nawaz, Karthik Nandakumar, Soo-Hyung Kim

Conversational engagement estimation is posed as a regression problem, entailing the identification of the favorable attention and involvement of the participants in the conversation. This task arises as a crucial pursuit to gain insights into human's interaction dynamics and behavior patterns within a conversation. In this research, we introduce a dilated convolutional Transformer for modeling and estimating human engagement in the MULTIMEDIATE 2023 competition. Our proposed system surpasses the baseline models, exhibiting a noteworthy $7$\% improvement on test set and $4$\% on validation set. Moreover, we employ different modality fusion mechanism and show that for this type of data, a simple concatenated method with self-attention fusion gains the best performance.

📄 PDF Abstract BibTeX arXiv:2308.01966

Code (0)

등록된 구현이 없습니다.

Tasks

regression

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Adam 설명 없음
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…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
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…

Similar Papers 제목 키워드 기반

Congested Crowd Instance Localization with Dilated Convolutional Swin Transformer

2021-08-02 · Junyu Gao, Maoguo Gong, Xuelong Li

Crowd localization is a new computer vision task, evolved from crowd counting. Different from the latter, it provides more precise location information for each instance, not just counting numbers for the whole crowd sce…

Crowd CountingRepresentation Learning

Deep conditional transformation models for survival analysis

2022-10-20 · Gabriele Campanella, Lucas Kook, Ida Häggström, Torsten Hothorn 외

An every increasing number of clinical trials features a time-to-event outcome and records non-tabular patient data, such as magnetic resonance imaging or text data in the form of electronic health records. Recently, sev…

Survival Analysis

D-Former: A U-shaped Dilated Transformer for 3D Medical Image Segmentation

2022-01-03 · Yixuan Wu, Kuanlun Liao, Jintai Chen, Jinhong Wang 외

Computer-aided medical image segmentation has been applied widely in diagnosis and treatment to obtain clinically useful information of shapes and volumes of target organs and tissues. In the past several years, convolut…

DecoderImage SegmentationMedical Image SegmentationSegmentation+1

Study of List-Based OMP and an Enhanced Model for Direction Finding with Non-Uniform Arrays

2021-05-08 · W. S. Leite, R. C. de Lamare

This paper proposes an enhanced coarray transformation model (EDCTM) and a mixed greedy maximum likelihood algorithm called List-Based Maximum Likelihood Orthogonal Matching Pursuit (LBML-OMP) for direction-of-arrival es…

Direction of Arrival Estimation

Edge-Enhanced Dilated Residual Attention Network for Multimodal Medical Image Fusion

2024-11-18 · Meng Zhou, Yuxuan Zhang, Xiaolan Xu, Jiayi Wang 외

Multimodal medical image fusion is a crucial task that combines complementary information from different imaging modalities into a unified representation, thereby enhancing diagnostic accuracy and treatment planning. Whi…

Brain Tumor ClassificationDiagnostic