Vision Paper

Vision research currently focuses on developing robust and efficient methods for processing and understanding visual information, often integrating it with other modalities like language and touch. Key areas include improving the accuracy and efficiency of models like transformers and exploring alternatives such as Mamba and structured state space models for various tasks, ranging from object detection and segmentation to navigation and scene understanding. This work is driven by the need for improved performance in applications such as robotics, autonomous systems, medical image analysis, and assistive technologies, with a strong emphasis on addressing challenges like limited data, computational cost, and generalization to unseen scenarios.

Papers

August 23, 2022

Learning More May Not Be Better: Knowledge Transferability in Vision and Language Tasks
Tianwei Chen, Noa Garcia, Mayu Otani, Chenhui Chu, Yuta Nakashima, Hajime Nagahara
LeArning Abstract Vision Paper Knowledge Transfer Vision Language Task Language Task Multi Modal Task Vision and Language Model

August 22, 2022

Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks
Wenhui Wang, Hangbo Bao, Li Dong, Johan Bjorck, Zhiliang Peng, Qiang Liu, Kriti Aggarwal, Owais Khan Mohammed, Saksham Singhal, Subhojit Som, Furu Wei
Vision Paper Vision Language Task Cross Modal Retrieval Modality Specific Multimodal Pre Multimodal Foundation Model Different Language

August 19, 2022

Atomist or Holist? A Diagnosis and Vision for More Productive Interdisciplinary AI Ethics Dialogue
Travis Greene, Amit Dhurandhar, Galit Shmueli
Vision Paper Medical Diagnosis Artificial Intelligence Research Research Ethic Entity Ideology

August 16, 2022

ViT-ReT: Vision and Recurrent Transformer Neural Networks for Human Activity Recognition in Videos
James Wensel, Hayat Ullah, Arslan Munir
Vision Transformer Vision Paper Gameplay Video Activity Recognition Recurrent Transformer

August 15, 2022

A Vision Transformer-Based Approach to Bearing Fault Classification via Vibration Signals
Abid Hasan Zim, Aeyan Ashraf, Aquib Iqbal, Asad Malik, Minoru Kuribayashi
Deep Learning Convolutional Neural Network Vision Paper Transformer Based Approach Vibration Signal Rolling Bearing Fault Classification Frequency Imaging Intelligent Fault Detection

July 30, 2022

A Survey on Masked Autoencoder for Self-supervised Learning in Vision and Beyond
Chaoning Zhang, Chenshuang Zhang, Junha Song, John Seon Keun Yi, Kang Zhang, In So Kweon
Timely Survey Self Supervised Learning Supervised Autoencoder Vision Paper Masked Autoencoders Masked AutoEncoder

July 29, 2022

Restoring Vision in Adverse Weather Conditions with Patch-Based Denoising Diffusion Models
Ozan Özdenizci, Robert Legenstein
Diffusion Model Vision Paper Image Restoration Denoising Diffusion Model Adverse Weather Weather Image Restoration Restoration Algorithm

July 27, 2022

Reducing the Vision and Language Bias for Temporal Sentence Grounding
Daizong Liu, Xiaoye Qu, Wei Hu
Cross Modal Vision Paper Multimodal Reasoning Contrastive Method Video Question Language Bias Temporal Sentence Grounding

July 26, 2022

V$^2$L: Leveraging Vision and Vision-language Models into Large-scale Product Retrieval
Wenhao Wang, Yifan Sun, Zongxin Yang, Yi Yang
Vision Language Model Full Model Vision Paper Vision Model Product Retrieval

July 18, 2022

Exploiting Unlabeled Data with Vision and Language Models for Object Detection
Shiyu Zhao, Zhixing Zhang, Samuel Schulter, Long Zhao, Vijay Kumar B. G, Anastasis Stathopoulos, Manmohan Chandraker, Dimitris Metaxas
Language Model Vision Paper Unlabeled Data Open Vocabulary Object Detection Semi Supervised Object Detection Unseen Category Generic Object Detection

July 10, 2022

LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action
Dhruv Shah, Blazej Osinski, Brian Ichter, Sergey Levine
Natural Language Human Language Vision Paper Robot Navigation Large Pre Trained Model Action Feature Goal Conditioned Policy Long Horizon Navigation

July 3, 2022

Beyond Visual Field of View: Perceiving 3D Environment with Echoes and Vision
Lingyu Zhu, Esa Rahtu, Hang Zhao
Depth Estimation Vision Paper Robot Navigation Depth Map Best View Dense Depth Map 3D Environment Acoustic Echo Visual Field

June 23, 2022

Towards Better User Studies in Computer Graphics and Vision
Zoya Bylinskii, Laura Herman, Aaron Hertzmann, Stefanie Hutka, Yile Zhang
Vision Paper User Experience User Study Computer Graphic

June 22, 2022

Vision- and tactile-based continuous multimodal intention and attention recognition for safer physical human-robot interaction
Christopher Yee Wong, Lucas Vergez, Wael Suleiman
Vision Paper Collaborative Robot Touch Sensor Intention Recognition Multimodal Intent Recognition

June 17, 2022

June 13, 2022

Compositional Mixture Representations for Vision and Text
Stephan Alaniz, Marco Federici, Zeynep Akata
Representation Learning Text Modality Vision Paper Representation Space Textual Representation Compositional Representation Spatial Transformer

June 12, 2022

Learning-Based Data Storage [Vision] (Technical Report)
Xiang Lian, Xiaofei Zhang
Deep Neural Network Vision Paper Technical Report

June 6, 2022

Beyond Just Vision: A Review on Self-Supervised Representation Learning on Multimodal and Temporal Data
Shohreh Deldari, Hao Xue, Aaqib Saeed, Jiayuan He, Daniel V. Smith, Flora D. Salim
Self Supervised Learning Training Data Narrative Review Vision Paper Multimodal Phenomenon Self Supervised Representation Learning Temporal Data Multimodal Self Supervised Learning Discriminative Pre

May 27, 2022

GIT: A Generative Image-to-text Transformer for Vision and Language
Jianfeng Wang, Zhengyuan Yang, Xiaowei Hu, Linjie Li, Kevin Lin, Zhe Gan, Zicheng Liu, Ce Liu, Lijuan Wang
Generative Model Transformer Based Human Language Vision Paper Generative Question Vision Language Task GIT Net Single Language

Vision Paper

Papers

Learning More May Not Be Better: Knowledge Transferability in Vision and Language Tasks

Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks

Atomist or Holist? A Diagnosis and Vision for More Productive Interdisciplinary AI Ethics Dialogue

ViT-ReT: Vision and Recurrent Transformer Neural Networks for Human Activity Recognition in Videos

A Vision Transformer-Based Approach to Bearing Fault Classification via Vibration Signals

A Survey on Masked Autoencoder for Self-supervised Learning in Vision and Beyond

Restoring Vision in Adverse Weather Conditions with Patch-Based Denoising Diffusion Models

Reducing the Vision and Language Bias for Temporal Sentence Grounding

V$^2$L: Leveraging Vision and Vision-language Models into Large-scale Product Retrieval

Exploiting Unlabeled Data with Vision and Language Models for Object Detection

LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action

Beyond Visual Field of View: Perceiving 3D Environment with Echoes and Vision

Towards Better User Studies in Computer Graphics and Vision

Vision- and tactile-based continuous multimodal intention and attention recognition for safer physical human-robot interaction

Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks

Language with Vision: a Study on Grounded Word and Sentence Embeddings

Compositional Mixture Representations for Vision and Text

Learning-Based Data Storage [Vision] (Technical Report)

Beyond Just Vision: A Review on Self-Supervised Representation Learning on Multimodal and Temporal Data

GIT: A Generative Image-to-text Transformer for Vision and Language