13 citations · 16 across the 8 of their papers we have counts for
7 papers · 1 filter
Counterfactual Reasoning for Fine-Grained Evidence Disentanglement in VideoQA
Zhou Du, Hamid Krim, Xiao Wu +3
Recent advances in video multimodal models have significantly improved VideoQA performance. However, these systems often rely on spurious statistical correlations rather than answe…
Shot2Tactic-Caption: Multi-Scale Captioning of Badminton Videos for Tactical Understanding
Ning Ding, Keisuke Fujii, Toru Tamaki
Tactical understanding in badminton involves interpreting not only individual actions but also how tactics are dynamically executed over time. In this paper, we propose \textbf{Sho…
VIFSS: View-Invariant and Figure Skating-Specific Pose Representation Learning for Temporal Action Segmentation
Ryota Tanaka, Tomohiro Suzuki, Keisuke Fujii
Understanding human actions from videos plays a critical role across various domains, including sports analytics. In figure skating, accurately recognizing the type and timing of j…
MulCPred: Learning Multi-modal Concepts for Explainable Pedestrian Action Prediction
Yan Feng, Alexander Carballo, Keisuke Fujii +3
Pedestrian action prediction is of great significance for many applications such as autonomous driving. However, state-of-the-art methods lack explainability to make trustworthy pr…
3D Pose-Based Temporal Action Segmentation for Figure Skating: A Fine-Grained and Jump Procedure-Aware Annotation Approach
Ryota Tanaka, Tomohiro Suzuki, Keisuke Fujii
Understanding human actions from videos is essential in many domains, including sports. In figure skating, technical judgments are performed by watching skaters' 3D movements, and…
DRUformer: Enhancing the driving scene Important object detection with driving relationship self-understanding
Yingjie Niu, Ming Ding, Keisuke Fujii +3
Traffic accidents frequently lead to fatal injuries, contributing to over 50 million deaths until 2023. To mitigate driving hazards and ensure personal safety, it is crucial to ass…
Runner re-identification from single-view running video in the open-world setting
Tomohiro Suzuki, Kazushi Tsutsui, Kazuya Takeda +1
In many sports, player re-identification is crucial for automatic video processing and analysis. However, most of the current studies on player re-identification in multi- or singl…