This paper proposes a method for learning embedding representations of style-transfer LoRA models based on their internal weight parameters, capturing transformation characteristics without relying on output examples or metadata. To vectorize LoRA models with multiple layers, we extract internal parameters layer-wise, then flatten and reduce dimensionality, representing each model as a sequence of low-dimensional vectors. Using this vector sequence as input, we perform triplet-based metric learning with a Triplet Network composed of three weight-sharing Transformer encoders and an MLP aggregation module. This framework estimates visual similarity between images transformed by different LoRA models. We conduct automatic evaluation of training validity, verify alignment with human relative similarity judgments, and perform retrieval-based ranking assessment. The results demonstrate that the proposed method learns embeddings consistent with human perception and enables stable retrieval of similar LoRA models.

This paper proposes a method to verbalize and generate corresponding outfit images based on natural language inputs describing everyday situations. To achieve this, an asymmetric pipeline is constructed for both dataset construction and situation-aware generative outfit retrieval. The design of this pipeline is grounded in the difference in task difficulty between generating images from situations and captioning images. A Vision-Language Model (VLM) is employed to caption outfit images, producing both the constituent elements of the outfit and the situations in which the outfit might be worn. These outputs are paired to construct a situation–outfit description dataset named OOTM (Outfit Of The Moment). An LLM trained on this dataset learns to transform situation descriptions into appropriate outfit descriptions. The generated outfit descriptions are then provided as input to a text-to-image model, which synthesizes outfit images. Through this process, the framework enables situation-aware outfit retrieval by generating outfit images that align with the given situational query. The appropriateness of the generated text and images for their respective situations was evaluated through both automatic evaluation using the constructed dataset and human subject experiments.

This paper proposes a retrieval algorithm that ranks LoRA adapters for additional merging, given a target image and the LoRA adapter currently used for image generation. In recent image generation workflows, multiple LoRA adapters are often applied simultaneously. However, selecting appropriate adapters to merge still relies on manual inspection of generated samples and associated metadata. We trained a Transformer-based classification model with token embedding to determine whether a given image is generated by a specific pair of LoRA adapters. This trained model can receive a target image, a fixed LoRA adapter in use, and candidate LoRA adapters, and then output a score reflecting the probability that two adapters, when merged, contribute to generating the target image. By ranking candidates based on this score, the proposed method can retrieve the LoRA adapter to be additionally merged. We implemented a retrieval system supporting 100 LoRA adapters, and both automatic evaluation and a user experiment demonstrate the effectiveness of the proposed approach.

This paper reveals the characteristics of the reviews that encourage readers to watch the reviewed movie by analyzing large-scale access log data. We assume that some of the reviews that users saw just before they clicked the links to a streaming site contain factors that help users decide whether they watch that movie. Our method used a random forest classifier trained to determine whether a review encouraged a movie-watching behavior. We conducted feature importance-based analysis using three types of features: review itself, item, and reviewer. We analyzed 70,000 user behaviors from Yahoo! Movies (a movie review site in Japan) and Gyao! (a movie streaming site in Japan). Through a cross-validation experiment, the classifier was able to classify encouraging reviews with an F-score of 0.78, and mainly the features about the item contributed to the classification performance. An additional subjects experiment confirmed that these features contribute to the review’s usefulness.

This paper proposes a method for extracting diverse expressions from online movie review texts for a given keyword query. When people watch a movie that makes them cry, they generally do not say “I cried.” Instead, they use such euphemistic language as “I needed a handkerchief” or “My makeup was running.” To enable information retrieval based on audience reactions such as “movies that make me cry” using review texts, a variety of paraphrased expressions must be collected for arbitrary queries. Our proposed method extracts such expressions from review datasets by applying two extensions to Doc2Vec: 1) it changes the granularity of the training sentences to mitigate a lack of context, and 2) it applies query expansion for similarity calculation in advance. We conducted a large-scale experiment using crowdsourcing with 1.29 million actual sentences taken from Yahoo! Movies, Japan. The experimental result revealed that changing the training data granularity and adding the query expansion are both effective to accurately collect more diverse expressions that have a meaning similar to the given query.

This paper proposes a method for ranking movies by keyword queries and examples using machine learning techniques that analyze actual data from the online movie review site. Existing search methods cannot rank movies in “surprising order” for the keyword query “surprising.” People and critics created many “My best surprising movies” rankings on the web. Our proposed method uses a LambdaMART, one of the mainstream Learning to Rank techniques, to learn these personalized rankings and sort the movies through the viewpoint represented by a given query. To accept more complex information needs, we diverted the learning results to a search-by-example algorithm that enables users to input examples, such as “surprising movies like The Usual Suspects or Fight Club.” The experiment using the personal ranking data from the personal content curation service in Yahoo! Movies Japan suggests two findings: direct learning of personal ranking does not improve search performance, and the search-by-example-based application increases user satisfaction.

This paper proposes a method of ranking geographic entities (places) where the purpose given as a query can be achieved. Most existing map search engines accept only the name of a place or the type of a place. Thus when searchers want to find a suitable place for “guitar practice”, they have to input a place type such as “music studio”. To create such a query, prior knowledge (i.e., that a music studio is suitable for playing guitar) is required. Our proposed method uses online review information on places to enable direct place retrieval from a given purpose query. Our method creates a bipartite graph consisting of places and the words that appear in the reviews of these places. The relevance between the given keyword query and a place is calculated by using the Random Walk with Restart algorithm. Additionally, we expand the graph with three hypotheses; 1) places that are suitable for the same purpose are similar to each other, and purposes that can be achieved in the same place are similar to each other, 2) the same purpose can be achieved in places with similar metadata, and 3) purposes which have semantically similar meaning can be achieved in the same places. Through an experiment using real review data taken from Google Maps, the usefulness of the proposed method was demonstrated. In particular, it was found that the expansion by places’ metadata is effective for finding more relevant places.

Deep hashing has been widely used to approximate nearest-neighbor search for image retrieval tasks. Most of them are trained with image-label pairs without any inter-label relationship, which may not make full use of the real-world data. This paper presents deep hashing, named HA2SH, that leverages multiple types of labels with hierarchical structures that an ethnological museum assigns to their artifacts. We experimentally prove that HA2SH can learn to generate hashes that give a better retrieval performance. Our code is available at https://github.com/wbw520/minpaku.

This paper proposes a new method of supplementing the context of short sentences for the training phase of Doc2Vec. Since CGM (Consumer Generated Media) sites and SNS sites become widespread, the importance of similarity calculation between a given query and a short sentence is increasing. As an example, a search by the query "sad" should find actual expressions such as "I needed a handkerchief" on a movie review site. Doc2Vec is one of the most widely used methods for vectorization of queries and sentences. However, Doc2Vec often exhibits low accuracy if the training data consists of short sentences, because they lack context. We modified Doc2Vec with the hypothesis that other posts for the same topic (i.e. reviews for the same movie in online movie review sites) may share the same background. Our method uses target-topic IDs instead of sentence IDs as the context in the training phase of the Doc2Vec with the PV-DM model; this model estimates the next term from a few previous terms and context. The model trained with item IDs vectorizes a sentence more accurately than a model trained with sentence IDs. We conducted a large-scale experiment using 1.2 million movie review posts and a crowdsourcing-based evaluation. The experimental result demonstrates that our new method achieves higher precision and nDCG than previous Doc2Vec variants and traditional topic modeling methods.