English
Related papers

Related papers: Decomposed Cross-modal Distillation for RGB-based …

200 papers

State-of-the-art methods for video action recognition commonly use an ensemble of two networks: the spatial stream, which takes RGB frames as input, and the temporal stream, which takes optical flow as input. In recent work, both of these…

Computer Vision and Pattern Recognition · Computer Science 2019-02-07 Jonathan C. Stroud , David A. Ross , Chen Sun , Jia Deng , Rahul Sukthankar

Cross-modal distillation has been widely used to transfer knowledge across different modalities, enriching the representation of the target unimodal one. Recent studies highly relate the temporal synchronization between vision and sound to…

Computer Vision and Pattern Recognition · Computer Science 2023-04-28 Wenke Xia , Xingjian Li , Andong Deng , Haoyi Xiong , Dejing Dou , Di Hu

Recent temporal action segmentation approaches need frame annotations during training to be effective. These annotations are very expensive and time-consuming to obtain. This limits their performances when only limited annotated data is…

Computer Vision and Pattern Recognition · Computer Science 2022-11-04 Sovan Biswas , Anthony Rhodes , Ramesh Manuvinakurike , Giuseppe Raffa , Richard Beckwith

Recent years have witnessed the significant progress of action recognition task with deep networks. However, most of current video networks require large memory and computational resources, which hinders their applications in practice.…

Computer Vision and Pattern Recognition · Computer Science 2020-09-16 Haisheng Su , Jing Su , Dongliang Wang , Weihao Gan , Wei Wu , Mengmeng Wang , Junjie Yan , Yu Qiao

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

Anticipating future actions in a video is useful for many autonomous and assistive technologies. Most prior action anticipation work treat this as a vision modality problem, where the models learn the task information primarily from the…

Computer Vision and Pattern Recognition · Computer Science 2023-02-22 Sayontan Ghosh , Tanvi Aggarwal , Minh Hoai , Niranjan Balasubramanian

RGB-T saliency detection has emerged as an important computer vision task, identifying conspicuous objects in challenging scenes such as dark environments. However, existing methods neglect the characteristics of cross-modal features and…

Computer Vision and Pattern Recognition · Computer Science 2023-09-15 Guangyu Ren , Jitesh Joshi , Youngjun Cho

RGB-Thermal (RGB-T) object detection utilizes thermal infrared (TIR) images to complement RGB data, improving robustness in challenging conditions. Traditional RGB-T detectors assume balanced training data, where both modalities contribute…

Computer Vision and Pattern Recognition · Computer Science 2025-05-29 Chao Tian , Chao Yang , Guoqing Zhu , Qiang Wang , Zhenyu He

Defocus Blur Detection(DBD) aims to separate in-focus and out-of-focus regions from a single image pixel-wisely. This task has been paid much attention since bokeh effects are widely used in digital cameras and smartphone photography.…

Computer Vision and Pattern Recognition · Computer Science 2020-07-17 Xiaodong Cun , Chi-Man Pun

In this paper, we propose a new progressive pre-training method for image understanding tasks which leverages RGB-D datasets. The method utilizes Multi-Modal Contrastive Masked Autoencoder and Denoising techniques. Our proposed approach…

Computer Vision and Pattern Recognition · Computer Science 2024-09-17 Muhammad Abdullah Jamal , Omid Mohareri

We present a method for temporally consistent motion segmentation from RGB-D videos assuming a piecewise rigid motion model. We formulate global energies over entire RGB-D sequences in terms of the segmentation of each frame into a number…

Computer Vision and Pattern Recognition · Computer Science 2016-08-17 Peter Bertholet , Alexandru-Eugen Ichim , Matthias Zwicker

Heterogeneous data modalities can provide complementary cues for several tasks, usually leading to more robust algorithms and better performance. However, while training data can be accurately collected to include a variety of sensory…

Computer Vision and Pattern Recognition · Computer Science 2019-07-29 Nuno C. Garcia , Pietro Morerio , Vittorio Murino

Multimodal deep sensor fusion has the potential to enable autonomous vehicles to visually understand their surrounding environments in all weather conditions. However, existing deep sensor fusion methods usually employ convoluted…

Computer Vision and Pattern Recognition · Computer Science 2023-10-31 Sri Aditya Deevi , Connor Lee , Lu Gan , Sushruth Nagesh , Gaurav Pandey , Soon-Jo Chung

Modern neural networks are powerful predictive models. However, when it comes to recognizing that they may be wrong about their predictions, they perform poorly. For example, for one of the most common activation functions, the ReLU and its…

Computer Vision and Pattern Recognition · Computer Science 2022-08-17 Shervin Manzuri Shalmani , Fei Chiang , Rong Zheng

Spatial and temporal stream model has gained great success in video action recognition. Most existing works pay more attention to designing effective features fusion methods, which train the two-stream model in a separate way. However, it's…

Computer Vision and Pattern Recognition · Computer Science 2019-08-28 Jingran Zhang , Fumin Shen , Xing Xu , Heng Tao Shen

Encoder-decoder models have been widely used in RGBD semantic segmentation, and most of them are designed via a two-stream network. In general, jointly reasoning the color and geometric information from RGBD is beneficial for semantic…

Computer Vision and Pattern Recognition · Computer Science 2022-03-16 Yang Zhang , Yang Yang , Chenyun Xiong , Guodong Sun , Yanwen Guo

In domestic environments, robots require a comprehensive understanding of their surroundings to interact effectively and intuitively with untrained humans. In this paper, we propose DVEFormer - an efficient RGB-D Transformer-based approach…

Computer Vision and Pattern Recognition · Computer Science 2026-01-05 Söhnke Benedikt Fischedick , Daniel Seichter , Benedict Stephan , Robin Schmidt , Horst-Michael Gross

Continual learning seeks to maintain stable adaptation under non-stationary environments, yet this problem becomes particularly challenging in object detection, where most existing methods implicitly assume relatively balanced visual…

Computer Vision and Pattern Recognition · Computer Science 2026-03-30 Rangya Zhang , Jiaping Xiao , Lu Bai , Yuhang Zhang , Mir Feroskhan

Referring image segmentation (RIS) requires accurate segmentation of target regions in images according to language descriptions, which is a cross-modal task integrating vision and language. Existing RIS methods typically employ large-scale…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Chen Yang

Existing Transformer-based RGBT tracking methods either use cross-attention to fuse the two modalities, or use self-attention and cross-attention to model both modality-specific and modality-sharing information. However, the significant…

Computer Vision and Pattern Recognition · Computer Science 2023-04-25 Yabin Zhu , Chenglong Li , Xiao Wang , Jin Tang , Zhixiang Huang