Satoshi Yamazaki

Shun Muroga, Satoshi Yamazaki, Koji Michishio et al.

We propose tabular two-dimensional correlation analysis for extracting features from multifaceted characterization data, essential for understanding material properties. This method visualizes similarities and phase lags in structural parameter changes through heatmaps, combining hierarchical clustering and asynchronous correlations. We applied the proposed method to datasets of carbon nanotube (CNTs) films annealed at various temperatures and revealed the complexity of their hierarchical structures, which include elements like voids, bundles, and amorphous carbon. Our analysis addresses the challenge of attempting to understand the sequence of structural changes, especially in multifaceted characterization data where 11 structural parameters derived from 8 characterization methods interact with complex behavior. The results show how phase lags (asynchronous changes from stimuli) and parameter similarities can illuminate the sequence of structural changes in materials, providing insights into phenomena like the removal of amorphous carbon and graphitization in annealed CNTs. This approach is beneficial even with limited data and holds promise for a wide range of material analyses, demonstrating its potential in elucidating complex material behaviors and properties.

Zongyao Li, Kengo Ishida, Satoshi Yamazaki et al.

We propose KFS-Bench, the first benchmark for key frame sampling in long video question answering (QA), featuring multi-scene annotations to enable direct and robust evaluation of sampling strategies. Key frame sampling is crucial for efficient long-form video understanding. In long video QA, selecting informative frames enables multimodal large language models (MLLMs) to improve both accuracy and efficiency. KFS-Bench addresses the limitation of prior works that only indirectly assess frame selection quality via QA accuracy. By providing ground-truth annotations of multiple disjoint scenes required per question, KFS-Bench allows us to directly analyze how different sampling approaches capture essential content across an entire long video. Using KFS-Bench, we conduct a comprehensive study of key frame sampling methods and identify that not only sampling precision but also scene coverage and sampling balance are the key factors influencing QA performance. Regarding all the factors, we design a novel sampling quality metric that correlates with QA accuracy. Furthermore, we develop a novel key frame sampling method that leverages question-video relevance to balance sampling diversity against question-frame similarity, thereby improving coverage of relevant scenes. Our adaptively balanced sampling approach achieves superior performance in both key frame sampling and QA performance. The benchmark is available at https://github.com/NEC-VID/KFS-Bench.

KuanChao Chu, Satoshi Yamazaki, Hideki Nakayama

This work focuses on training dataset enhancement of informative relational triplets for Scene Graph Generation (SGG). Due to the lack of effective supervision, the current SGG model predictions perform poorly for informative relational triplets with inadequate training samples. Therefore, we propose two novel training dataset enhancement modules: Feature Space Triplet Augmentation (FSTA) and Soft Transfer. FSTA leverages a feature generator trained to generate representations of an object in relational triplets. The biased prediction based sampling in FSTA efficiently augments artificial triplets focusing on the challenging ones. In addition, we introduce Soft Transfer, which assigns soft predicate labels to general relational triplets to make more supervisions for informative predicate classes effectively. Experimental results show that integrating FSTA and Soft Transfer achieve high levels of both Recall and mean Recall in Visual Genome dataset. The mean of Recall and mean Recall is the highest among all the existing model-agnostic methods.