English
Related papers

Related papers: Modality Mixer Exploiting Complementary Informatio…

200 papers

In late fusion, each modality is processed in a separate unimodal Convolutional Neural Network (CNN) stream and the scores of each modality are fused at the end. Due to its simplicity late fusion is still the predominant approach in many…

Computer Vision and Pattern Recognition · Computer Science 2020-04-01 Hamid Reza Vaezi Joze , Amirreza Shaban , Michael L. Iuzzolino , Kazuhito Koishida

Visual tracking often faces challenges such as invalid targets and decreased performance in low-light conditions when relying solely on RGB image sequences. While incorporating additional modalities like depth and infrared data has proven…

Computer Vision and Pattern Recognition · Computer Science 2023-12-25 Lei Liu , Mengya Zhang , Cheng Li , Chenglong Li , Jin Tang

Developing robust multi-modal feature representations is crucial for enhancing object tracking performance. In pursuit of this objective, a novel X Modality Assisting Network (X-Net) is introduced, which explores the impact of the fusion…

Computer Vision and Pattern Recognition · Computer Science 2025-02-25 Zhaisheng Ding , Haiyan Li , Ruichao Hou , Yanyu Liu , Shidong Xie

In this work, we address the problem of learning an ensemble of specialist networks using multimodal data, while considering the realistic and challenging scenario of possible missing modalities at test time. Our goal is to leverage the…

Computer Vision and Pattern Recognition · Computer Science 2019-12-24 Nuno C. Garcia , Sarah Adel Bargal , Vitaly Ablavsky , Pietro Morerio , Vittorio Murino , Stan Sclaroff

Multimodal emotion recognition leverages complementary information across modalities to gain performance. However, we cannot guarantee that the data of all modalities are always present in practice. In the studies to predict the missing…

Computer Vision and Pattern Recognition · Computer Science 2022-10-28 Haolin Zuo , Rui Liu , Jinming Zhao , Guanglai Gao , Haizhou Li

This paper proposes a novel multi-modal transformer network for detecting actions in untrimmed videos. To enrich the action features, our transformer network utilizes a new multi-modal attention mechanism that computes the correlations…

Computer Vision and Pattern Recognition · Computer Science 2023-06-01 Matthew Korban , Scott T. Acton , Peter Youngs

Skeleton-based action recognition has garnered significant attention due to the utilization of concise and resilient skeletons. Nevertheless, the absence of detailed body information in skeletons restricts performance, while other…

Computer Vision and Pattern Recognition · Computer Science 2024-08-16 Jinfu Liu , Chen Chen , Mengyuan Liu

Multi-modality image fusion aims at fusing modality-specific (complementarity) and modality-shared (correlation) information from multiple source images. To tackle the problem of the neglect of inter-feature relationships, high-frequency…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Xiaoli Zhang , Liying Wang , Libo Zhao , Xiongfei Li , Siwei Ma

Combining complementary information from multiple modalities is intuitively appealing for improving the performance of learning-based approaches. However, it is challenging to fully leverage different modalities due to practical challenges…

Machine Learning · Statistics 2018-05-31 Kuan Liu , Yanen Li , Ning Xu , Prem Natarajan

This paper investigates the optimal selection and fusion of feature encoders across multiple modalities and combines these in one neural network to improve sentiment detection. We compare different fusion methods and examine the impact of…

Computation and Language · Computer Science 2024-06-04 Zehui Wu , Ziwei Gong , Jaywon Koo , Julia Hirschberg

Multimodal entity linking (MEL) task, which aims at resolving ambiguous mentions to a multimodal knowledge graph, has attracted wide attention in recent years. Though large efforts have been made to explore the complementary effect among…

Artificial Intelligence · Computer Science 2023-07-20 Pengfei Luo , Tong Xu , Shiwei Wu , Chen Zhu , Linli Xu , Enhong Chen

Action detection is an essential and challenging task, especially for densely labelled datasets of untrimmed videos. The temporal relation is complex in those datasets, including challenges like composite action, and co-occurring action.…

Computer Vision and Pattern Recognition · Computer Science 2022-03-30 Rui Dai , Srijan Das , Kumara Kahatapitiya , Michael S. Ryoo , Francois Bremond

Diverse input data modalities can provide complementary cues for several tasks, usually leading to more robust algorithms and better performance. However, while a (training) dataset could be accurately designed to include a variety of…

Computer Vision and Pattern Recognition · Computer Science 2018-10-30 Nuno Garcia , Pietro Morerio , Vittorio Murino

Human action recognition in video is an active yet challenging research topic due to high variation and complexity of data. In this paper, a novel video based action recognition framework utilizing complementary cues is proposed to handle…

Computer Vision and Pattern Recognition · Computer Science 2019-09-10 Muhammad Usman Khalid , Jie Yu

Given a video and a linguistic query, video moment retrieval and highlight detection (MR&HD) aim to locate all the relevant spans while simultaneously predicting saliency scores. Most existing methods utilize RGB images as input,…

Computer Vision and Pattern Recognition · Computer Science 2025-01-22 Yifang Xu , Yunzhuo Sun , Benxiang Zhai , Zien Xie , Youyao Jia , Sidan Du

Modern Web systems such as social media and e-commerce contain rich contents expressed in images and text. Leveraging information from multi-modalities can improve the performance of machine learning tasks such as classification and…

Computer Vision and Pattern Recognition · Computer Science 2021-12-10 Huidong Liu , Shaoyuan Xu , Jinmiao Fu , Yang Liu , Ning Xie , Chien-Chih Wang , Bryan Wang , Yi Sun

Multimodal video understanding plays a crucial role in tasks such as action recognition and emotion classification by combining information from different modalities. However, multimodal models are prone to overfitting strong modalities,…

Computer Vision and Pattern Recognition · Computer Science 2025-10-14 Xiaoyu Ma , Ding Ding , Hao Chen

Compressed video action recognition has recently drawn growing attention, since it remarkably reduces the storage and computational cost via replacing raw videos by sparsely sampled RGB frames and compressed motion cues (e.g., motion…

Computer Vision and Pattern Recognition · Computer Science 2025-10-06 Bing Li , Jiaxin Chen , Dongming Zhang , Xiuguo Bao , Di Huang

Most existing multimodal trackers adopt uniform fusion strategies, overlooking the inherent differences between modalities. Moreover, they propagate temporal information through mixed tokens, leading to entangled and less discriminative…

Computer Vision and Pattern Recognition · Computer Science 2026-03-11 Shilei Wang , Pujian Lai , Dong Gao , Jifeng Ning , Gong Cheng

The construction of models for video action classification progresses rapidly. However, the performance of those models can still be easily improved by ensembling with the same models trained on different modalities (e.g. Optical flow).…

Computer Vision and Pattern Recognition · Computer Science 2020-11-06 Stepan Komkov , Maksim Dzabraev , Aleksandr Petiushko