For example, in experiments on the GIST1M dataset, the construction of the proposed method is 2x faster than NSG.
Despite the efficacy of graph-based algorithms for Approximate Nearest Neighbor (ANN) searches, the optimal tuning of such systems remains unclear.
For further understanding of comics, an automated approach is needed to link text in comics to characters speaking the words.
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.
To encourage research on this topic, we provide a novel comic onomatopoeia dataset (COO), which consists of onomatopoeia texts in Japanese comics.
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.
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.
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
We annotated an existing image dataset of comics and created the largest annotation dataset, named Manga109-annotations.
Our method can predict a 3D pose from 2D joint locations in a single image.
Second, to help users specify spatial relationships among objects in an intuitive way, we propose recommendation techniques of spatial relationships.
In this paper, we propose a product quantization table (PQTable); a fast search method for product-quantized codes via 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.
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.