Search Results for author:
Found 30 papers, 18 papers with code
Cascaded Learned Bloom Filter for Optimal Model-Filter Size Balance and Fast Rejection
Recent studies have demonstrated that learned Bloom filters, which combine machine learning with the classical Bloom filter, can achieve superior memory efficiency.
Broadcast Product: Shape-aligned Element-wise Multiplication and Beyond
We propose a new operator defined between two tensors, the broadcast product.
High-Frequency Anti-DreamBooth: Robust Defense against Personalized Image Synthesis
Recently, text-to-image generative models have been misused to create unauthorized malicious images of individuals, posing a growing social problem.
Revisiting Relevance Feedback for CLIP-based Interactive Image Retrieval
However, metric learning cannot handle differences in users' preferences, and requires data to train an image encoder.
Zero-Shot Character Identification and Speaker Prediction in Comics via Iterative Multimodal Fusion
To address this problem, we propose an iterative multimodal framework, the first to employ multimodal information for both character identification and speaker prediction tasks.
SVGEditBench: A Benchmark Dataset for Quantitative Assessment of LLM's SVG Editing Capabilities
SVGEditBench is a benchmark for assessing the LLMs' ability to edit SVG code.
ZoDi: Zero-Shot Domain Adaptation with Diffusion-Based Image Transfer
Deep learning models achieve high accuracy in segmentation tasks among others, yet domain shift often degrades the models' performance, which can be critical in real-world scenarios where no target images are available.
Theoretical and Empirical Analysis of Adaptive Entry Point Selection for Graph-based Approximate Nearest Neighbor Search
We present a theoretical and empirical analysis of the adaptive entry point selection for graph-based approximate nearest neighbor search (ANNS).
Cross-Lingual Learning in Multilingual Scene Text Recognition
We aim to find the condition that exploits knowledge from high-resource languages for improving performance in low-resource languages.
Adversarial Doodles: Interpretable and Human-drawable Attacks Provide Describable Insights
We optimize black bezier curves to fool the classifier by overlaying them onto the input image.
Relative NN-Descent: A Fast Index Construction for Graph-Based Approximate Nearest Neighbor Search
For example, in experiments on the GIST1M dataset, the construction of the proposed method is 2x faster than NSG.
General and Practical Tuning Method for Off-the-Shelf Graph-Based Index: SISAP Indexing Challenge Report by Team UTokyo
Despite the efficacy of graph-based algorithms for Approximate Nearest Neighbor (ANN) searches, the optimal tuning of such systems remains unclear.
Manga109Dialog: A Large-scale Dialogue Dataset for Comics Speaker Detection
For further understanding of comics, an automated approach is needed to link text in comics to characters speaking the words.
Defense-Prefix for Preventing Typographic Attacks on CLIP
In this study, we addressed the reduction of the impact of typographic attacks on CLIP without changing the model parameters.
Unbiased Scene Graph Generation using Predicate Similarities
The results of extensive experiments on the Visual Genome dataset show that the combination of our method and an existing debiasing approach greatly improves performance on tail predicates in challenging SGCls/SGDet tasks.
COO: Comic Onomatopoeia Dataset for Recognizing Arbitrary or Truncated Texts
To encourage research on this topic, we provide a novel comic onomatopoeia dataset (COO), which consists of onomatopoeia texts in Japanese comics.
ARM 4-BIT PQ: SIMD-based Acceleration for Approximate Nearest Neighbor Search on ARM
We accelerate the 4-bit product quantization (PQ) on the ARM architecture.
Cascading Feature Extraction for Fast Point Cloud Registration
We propose a method for speeding up a 3D point cloud registration through a cascading feature extraction.
What If We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labels
To the best of our knowledge, this is the first study that 1) shows sufficient performance by only using real labels and 2) introduces semi- and self-supervised methods into STR with fewer labels.
Towards Fully Automated Manga Translation
We are the first to incorporate context information obtained from manga image.
Building a Manga Dataset "Manga109" with Annotations for Multimedia Applications
Manga, or comics, which are a type of multimodal artwork, have been left behind in the recent trend of deep learning applications because of the lack of a proper dataset.
Efficient Image Retrieval via Decoupling Diffusion into Online and Offline Processing
Diffusion is commonly used as a ranking or re-ranking method in retrieval tasks to achieve higher retrieval performance, and has attracted lots of attention in recent years.
Ranked #1 on
Image Retrieval
on Par6k
Reconfigurable Inverted Index
Owing to the linear layout, the data structure can be dynamically adjusted after new items are added, maintaining the fast speed of the system.
Object Detection for Comics using Manga109 Annotations
We annotated an existing image dataset of comics and created the largest annotation dataset, named Manga109-annotations.
Unsupervised Adversarial Learning of 3D Human Pose from 2D Joint Locations
Our method can predict a 3D pose from 2D joint locations in a single image.
Region-Based Image Retrieval Revisited
Second, to help users specify spatial relationships among objects in an intuitive way, we propose recommendation techniques of spatial relationships.
PQk-means: Billion-scale Clustering for Product-quantized Codes
Data clustering is a fundamental operation in data analysis.
PQTable: Non-exhaustive Fast Search for Product-quantized Codes using Hash Tables
In this paper, we propose a product quantization table (PQTable); a fast search method for product-quantized codes via hash-tables.
PQTable: Fast Exact Asymmetric Distance Neighbor Search for Product Quantization Using Hash Tables
We propose the product quantization table (PQTable), a product quantization-based hash table that is fast and requires neither parameter tuning nor training steps.
Sketch-based Manga Retrieval using Manga109 Dataset
From the experiments, we verified that: (1) the retrieval accuracy of the proposed method is higher than those of previous methods; (2) the proposed method can localize an object instance with reasonable runtime and accuracy; and (3) sketch querying is useful for manga search.
