Search Results for author:
Found 54 papers, 20 papers with code
Can masking background and object reduce static bias for zero-shot action recognition?
Experiments with masking background show that models depend on background bias as their performance decreases for Kinetics400.
Text-guided Synthetic Geometric Augmentation for Zero-shot 3D Understanding
Zero-shot recognition models require extensive training data for generalization.
Constant Rate Schedule: Constant-Rate Distributional Change for Efficient Training and Sampling in Diffusion Models
To obtain this noise schedule, we measure the rate of change in the probability distribution of the forward process and use it to determine the noise schedule before training diffusion models.
Formula-Supervised Visual-Geometric Pre-training
Throughout the history of computer vision, while research has explored the integration of images (visual) and point clouds (geometric), many advancements in image and 3D object recognition have tended to process these modalities separately.
Rethinking Image Super-Resolution from Training Data Perspectives
In this work, we investigate the understudied effect of the training data used for image super-resolution (SR).
Scaling Backwards: Minimal Synthetic Pre-training?
To this end, we search for a minimal, purely synthetic pre-training dataset that allows us to achieve performance similar to the 1 million images of ImageNet-1k.
Watermark-embedded Adversarial Examples for Copyright Protection against Diffusion Models
Diffusion Models (DMs) have shown remarkable capabilities in various image-generation tasks.
Primitive Geometry Segment Pre-training for 3D Medical Image Segmentation
From experimental results, we conclude that effective pre-training can be achieved by looking at primitive geometric objects only.
Traffic Incident Database with Multiple Labels Including Various Perspective Environmental Information
Our proposed dataset aims to improve the performance of traffic accident recognition by annotating ten types of environmental information as teacher labels in addition to the presence or absence of traffic accidents.
Image Generation and Learning Strategy for Deep Document Forgery Detection
In recent years, document processing has flourished and brought numerous benefits.
Leveraging Image-Text Similarity and Caption Modification for the DataComp Challenge: Filtering Track and BYOD Track
Our solution adopts large multimodal models CLIP and BLIP-2 to filter and modify web crawl data, and utilize external datasets along with a bag of tricks to improve the data quality.
Constructing Image-Text Pair Dataset from Books
Digital archiving is becoming widespread owing to its effectiveness in protecting valuable books and providing knowledge to many people electronically.
SegRCDB: Semantic Segmentation via Formula-Driven Supervised Learning
SegRCDB has a high potential to contribute to semantic segmentation pre-training and investigation by enabling the creation of large datasets without manual annotation.
Diffusion-based Holistic Texture Rectification and Synthesis
We present a novel framework for rectifying occlusions and distortions in degraded texture samples from natural images.
Exploring Limits of Diffusion-Synthetic Training with Weakly Supervised Semantic Segmentation
The advance of generative models for images has inspired various training techniques for image recognition utilizing synthetic images.
Pre-training Vision Transformers with Very Limited Synthesized Images
Prior work on FDSL has shown that pre-training vision transformers on such synthetic datasets can yield competitive accuracy on a wide range of downstream tasks.
RoseTracker: A system for automated rose growth monitoring
The RoseBlooming dataset is the innovative dataset of labeled images for cut flowers at the growing stage.
Pre-Training Auto-Generated Volumetric Shapes for 3D Medical Image Segmentation
Inspired by this approach, we propose the Auto-generated Volumetric Shapes Database (AVS-DB) for data-scarce 3D medical image segmentation tasks.
Scapegoat Generation for Privacy Protection from Deepfake
To protect privacy and prevent malicious use of deepfake, current studies propose methods that interfere with the generation process, such as detection and destruction approaches.
Visual Atoms: Pre-training Vision Transformers with Sinusoidal Waves
Unlike JFT-300M which is a static dataset, the quality of synthetic datasets will continue to improve, and the current work is a testament to this possibility.
Frequency-aware GAN for Adversarial Manipulation Generation
We observe that existing spatial attacks cause large degradation in image quality and find the loss of high-frequency detailed components might be its major reason.
Graph Representation for Order-Aware Visual Transformation
This paper proposes a new visual reasoning formulation that aims at discovering changes between image pairs and their temporal orders.
Neural Density-Distance Fields
However, it is difficult to achieve high localization performance by only density fields-based methods such as Neural Radiance Field (NeRF) since they do not provide density gradient in most empty regions.
Replacing Labeled Real-image Datasets with Auto-generated Contours
In the present work, we show that the performance of formula-driven supervised learning (FDSL) can match or even exceed that of ImageNet-21k without the use of real images, human-, and self-supervision during the pre-training of Vision Transformers (ViTs).
Community-Driven Comprehensive Scientific Paper Summarization: Insight from cvpaper.challenge
To alleviate this problem, we organized a group of non-native English speakers to write summaries of papers presented at a computer vision conference to share the knowledge of the papers read by the group.
Point Cloud Pre-Training With Natural 3D Structures
Moreover, the PC-FractalDB pre-trained model is especially effective in training with limited data.
Ranked #18 on
3D Object Detection
on SUN-RGBD val
(using extra training data)
Describing and Localizing Multiple Changes with Transformers
Change captioning tasks aim to detect changes in image pairs observed before and after a scene change and generate a natural language description of the changes.
Can Vision Transformers Learn without Natural Images?
Moreover, although the ViT pre-trained without natural images produces some different visualizations from ImageNet pre-trained ViT, it can interpret natural image datasets to a large extent.
Pre-training without Natural Images
Is it possible to use convolutional neural networks pre-trained without any natural images to assist natural image understanding?
Initialization Using Perlin Noise for Training Networks with a Limited Amount of Data
Our main idea is to initialize the network parameters by solving an artificial noise classification problem, where the aim is to classify Perlin noise samples into their noise categories.
Alleviating Over-segmentation Errors by Detecting Action Boundaries
Our model architecture consists of a long-term feature extractor and two branches: the Action Segmentation Branch (ASB) and the Boundary Regression Branch (BRB).
Ranked #11 on
Action Segmentation
on GTEA
Retrieving and Highlighting Action with Spatiotemporal Reference
In this paper, we present a framework that jointly retrieves and spatiotemporally highlights actions in videos by enhancing current deep cross-modal retrieval methods.
Would Mega-scale Datasets Further Enhance Spatiotemporal 3D CNNs?
Therefore, in the present paper, we conduct exploration study in order to improve spatiotemporal 3D CNNs as follows: (i) Recently proposed large-scale video datasets help improve spatiotemporal 3D CNNs in terms of video classification accuracy.
Weakly Supervised Dataset Collection for Robust Person Detection
To construct an algorithm that can provide robust person detection, we present a dataset with over 8 million images that was produced in a weakly supervised manner.
Augmented Cyclic Consistency Regularization for Unpaired Image-to-Image Translation
Herein, we propose Augmented Cyclic Consistency Regularization (ACCR), a novel regularization method for unpaired I2I translation.
Learning with Protection: Rejection of Suspicious Samples under Adversarial Environment
Our main idea is to apply a framework of learning with rejection and adversarial examples to assist in the decision making for such suspicious samples.
What Do Adversarially Robust Models Look At?
In this paper, we address the open question: "What do adversarially robust models look at?"
Automatic Paper Summary Generation from Visual and Textual Information
Due to the recent boom in artificial intelligence (AI) research, including computer vision (CV), it has become impossible for researchers in these fields to keep up with the exponentially increasing number of manuscripts.
Understanding Fake Faces
Face recognition research is one of the most active topics in computer vision (CV), and deep neural networks (DNN) are now filling the gap between human-level and computer-driven performance levels in face verification algorithms.
Neural Joking Machine : Humorous image captioning
In the present paper, in order to consider this question from an academic standpoint, we generate an image caption that draws a "laugh" by a computer.
Anticipating Traffic Accidents with Adaptive Loss and Large-scale Incident DB
In this paper, we propose a novel approach for traffic accident anticipation through (i) Adaptive Loss for Early Anticipation (AdaLEA) and (ii) a large-scale self-annotated incident database for anticipation.
Drive Video Analysis for the Detection of Traffic Near-Miss Incidents
Because of their recent introduction, self-driving cars and advanced driver assistance system (ADAS) equipped vehicles have had little opportunity to learn, the dangerous traffic (including near-miss incident) scenarios that provide normal drivers with strong motivation to drive safely.
Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?
The purpose of this study is to determine whether current video datasets have sufficient data for training very deep convolutional neural networks (CNNs) with spatio-temporal three-dimensional (3D) kernels.
Ranked #51 on
Action Recognition
on UCF101
Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition
The 3D ResNets trained on the Kinetics did not suffer from overfitting despite the large number of parameters of the model, and achieved better performance than relatively shallow networks, such as C3D.
cvpaper.challenge in 2016: Futuristic Computer Vision through 1,600 Papers Survey
The paper gives futuristic challenges disscussed in the cvpaper. challenge.
Collaborative Descriptors: Convolutional Maps for Preprocessing
The paper presents a novel concept for collaborative descriptors between deeply learned and hand-crafted features.
Could you guess an interesting movie from the posters?: An evaluation of vision-based features on movie poster database
In this paper, we aim to estimate the Winner of world-wide film festival from the exhibited movie poster.
Changing Fashion Cultures
The paper presents a novel concept that analyzes and visualizes worldwide fashion trends.
Motion Representation with Acceleration Images
Information of time differentiation is extremely important cue for a motion representation.
Human Action Recognition without Human
The objective of this paper is to evaluate "human action recognition without human".
cvpaper.challenge in 2015 - A review of CVPR2015 and DeepSurvey
The "cvpaper. challenge" is a group composed of members from AIST, Tokyo Denki Univ.
Dominant Codewords Selection with Topic Model for Action Recognition
Latent Dirichlet allocation (LDA) is used to develop approximations of human motion primitives; these are mid-level representations, and they adaptively integrate dominant vectors when classifying human activities.
Semantic Change Detection with Hypermaps
By the detected change areas, however, a human cannot understand how different the two images.
Feature Evaluation of Deep Convolutional Neural Networks for Object Recognition and Detection
In this paper, we evaluate convolutional neural network (CNN) features using the AlexNet architecture and very deep convolutional network (VGGNet) architecture.
