Search Results for author:
Found 39 papers, 13 papers with code
YOLO in the Dark - Domain Adaptation Method for Merging Multiple Models -
We propose a new method of domain adaptation for merging multiple models with less effort than creating an additional dataset.
Acquiring Dynamic Light Fields through Coded Aperture Camera
A promising solution for compressive light field acquisition is to use a coded aperture camera, with which an entire light field can be computationally reconstructed from several images captured through differently-coded aperture patterns.
IDSOU at WNUT-2020 Task 2: Identification of Informative COVID-19 English Tweets
We introduce the IDSOU submission for the WNUT-2020 task 2: identification of informative COVID-19 English Tweets.
A Japanese Dataset for Subjective and Objective Sentiment Polarity Classification in Micro Blog Domain
We annotate 35, 000 SNS posts with both the writer’s subjective sentiment polarity labels and the reader’s objective ones to construct a Japanese sentiment analysis dataset.
Multi-Scale Spatio-Temporal Graph Convolutional Network for Facial Expression Spotting
In this paper, we propose a Multi-Scale Spatio-Temporal Graph Convolutional Network (SpoT-GCN) for facial expression spotting.
Time-Efficient Light-Field Acquisition Using Coded Aperture and Events
Different from the conventional coded-aperture imaging method, our method applies a sequence of coding patterns during a single exposure for an image frame.
NeISF: Neural Incident Stokes Field for Geometry and Material Estimation
To address this problem, we propose Neural Incident Stokes Fields (NeISF), a multi-view inverse rendering framework that reduces ambiguities using polarization cues.
Instruct Me More! Random Prompting for Visual In-Context Learning
Our findings suggest that InMeMo offers a versatile and efficient way to enhance the performance of visual ICL with lightweight training.
Inverse Rendering of Translucent Objects using Physical and Neural Renderers
To enhance the supervision of the proposed neural renderer, we also propose an augmented loss.
Learning Bottleneck Concepts in Image Classification
Using some image classification tasks as our testbed, we demonstrate BotCL's potential to rebuild neural networks for better interpretability.
Human-Imperceptible Identification with Learnable Lensless Imaging
Lensless imaging protects visual privacy by capturing heavily blurred images that are imperceptible for humans to recognize the subject but contain enough information for machines to infer information.
Inference Time Evidences of Adversarial Attacks for Forensic on Transformers
Vision Transformers (ViTs) are becoming a very popular paradigm for vision tasks as they achieve state-of-the-art performance on image classification.
Contrastive Losses Are Natural Criteria for Unsupervised Video Summarization
Video summarization aims to select the most informative subset of frames in a video to facilitate efficient video browsing.
A General Scattering Phase Function for Inverse Rendering
We tackle the problem of modeling light scattering in homogeneous translucent material and estimating its scattering parameters.
Learning More May Not Be Better: Knowledge Transferability in Vision and Language Tasks
Is more data always better to train vision-and-language models?
Privacy-Preserving Action Recognition via Motion Difference Quantization
This is followed by the Difference module to apply a pixel-wise intensity subtraction between consecutive frames to highlight motion features and suppress obvious high-level privacy attributes.
Acquiring a Dynamic Light Field through a Single-Shot Coded Image
To our knowledge, our method is the first to achieve a finer temporal resolution than the camera itself in compressive light-field acquisition.
Built Year Prediction from Buddha Face with Heterogeneous Labels
Buddha statues are a part of human culture, especially of the Asia area, and they have been alongside human civilisation for more than 2, 000 years.
WRIME: A New Dataset for Emotional Intensity Estimation with Subjective and Objective Annotations
We annotate 17, 000 SNS posts with both the writer{'}s subjective emotional intensity and the reader{'}s objective one to construct a Japanese emotion analysis dataset.
GCNBoost: Artwork Classification by Label Propagation through a Knowledge Graph
In this paper, we propose a novel use of a knowledge graph, that is constructed on annotated data and pseudo-labeled data.
Development of a Vertex Finding Algorithm using Recurrent Neural Network
Deep learning is a rapidly-evolving technology with possibility to significantly improve physics reach of collider experiments.
Match Them Up: Visually Explainable Few-shot Image Classification
Few-shot learning (FSL) approaches are usually based on an assumption that the pre-trained knowledge can be obtained from base (seen) categories and can be well transferred to novel (unseen) categories.
Ranked #34 on
Few-Shot Image Classification
on CIFAR-FS 5-way (5-shot)
Automated Grading System of Retinal Arterio-venous Crossing Patterns: A Deep Learning Approach Replicating Ophthalmologist's Diagnostic Process of Arteriolosclerosis
Our severity grading method was able to validate crossing points with precision and recall of 96. 3% and 96. 3%, respectively.
Noisy-LSTM: Improving Temporal Awareness for Video Semantic Segmentation
Semantic video segmentation is a key challenge for various applications.
SCOUTER: Slot Attention-based Classifier for Explainable Image Recognition
Explainable artificial intelligence has been gaining attention in the past few years.
Joint Learning of Vessel Segmentation and Artery/Vein Classification with Post-processing
Retinal imaging serves as a valuable tool for diagnosis of various diseases.
Constructing a Public Meeting Corpus
In this paper, we propose a full pipeline of analysis of a large corpus about a century of public meeting in historical Australian news papers, from construction to visual exploration.
5D Light Field Synthesis from a Monocular Video
To tackle this problem, we propose a deep learning-based method for synthesizing a light field video from a monocular video.
IterNet: Retinal Image Segmentation Utilizing Structural Redundancy in Vessel Networks
Retinal vessel segmentation is of great interest for diagnosis of retinal vascular diseases.
Ranked #5 on
Retinal Vessel Segmentation
on CHASE_DB1
BUDA.ART: A Multimodal Content-Based Analysis and Retrieval System for Buddha Statues
We introduce BUDA. ART, a system designed to assist researchers in Art History, to explore and analyze an archive of pictures of Buddha statues.
Historical and Modern Features for Buddha Statue Classification
While Buddhism has spread along the Silk Roads, many pieces of art have been displaced.
Using Natural Language Processing to Develop an Automated Orthodontic Diagnostic System
We work on the task of automatically designing a treatment plan from the findings included in the medical certificate written by the dentist.
Learning to Capture Light Fields through a Coded Aperture Camera
To make the acquisition process efficient, coded aperture cameras were successfully adopted; using these cameras, a light field is computationally reconstructed from several images that are acquired with different aperture patterns.
Joint optimization for compressive video sensing and reconstruction under hardware constraints
Compressive video sensing is the process of encoding multiple sub-frames into a single frame with controlled sensor exposures and reconstructing the sub-frames from the single compressed frame.
TransCut: Transparent Object Segmentation from a Light-Field Image
The segmentation of transparent objects can be very useful in computer vision applications.
Shape and Light Directions From Shading and Polarization
In contrast, photometric stereo method with multiple light sources can disambiguate the surface orientation and give a strong relationship between the surface normals and light directions.
Mobile Camera Array Calibration for Light Field Acquisition
The light field camera is useful for computer graphics and vision applications.
Background Modeling Based on Bidirectional Analysis
Although a result will be output with some delay because information is taken from a future period, our proposed approach improves the accuracy by about 30% if only a 33-millisecond of delay is acceptable.
Light Field Distortion Feature for Transparent Object Recognition
These approaches though cannot apply to transparent objects made of glass or plastic, as such objects take on the visual features of background objects, and the appearance of such objects dramatically varies with changes in scene background.
