687 citations
- University of Southern CaliforniaUS6 papers
- National Institute of InformaticsJP4 papers
- KDDI (Japan)JP2 papers
- Osaka Institute of TechnologyJP2 papers
- Shibaura Institute of TechnologyJP2 papers
- Accenture (United States)US1 paper
- California Southern UniversityUS1 paper
- Carnegie Mellon UniversityUS1 paper
- Commonwealth Scientific and Industrial Research OrganisationAU1 paper
- Data61AU1 paper
- Doshisha UniversityJP1 paper
- Escuela Superior Politecnica del LitoralEC1 paper
7 papers · 1 filter
Fast graph-based denoising for point cloud color information
Ryosuke Watanabe, Keisuke Nonaka, Eduardo Pavez +2
Point clouds are utilized in various 3D applications such as cross-reality (XR) and realistic 3D displays. In some applications, e.g., for live streaming using a 3D point cloud, re…
Efficient Linear Attention for Fast and Accurate Keypoint Matching
Suwichaya Suwanwimolkul, Satoshi Komorita
Recently Transformers have provided state-of-the-art performance in sparse matching, crucial to realize high-performance 3D vision applications. Yet, these Transformers lack effici…
RoVISQ: Reduction of Video Service Quality via Adversarial Attacks on Deep Learning-based Video Compression
Jung-Woo Chang, Mojan Javaheripi, Seira Hidano +1
Video compression plays a crucial role in video streaming and classification systems by maximizing the end-user quality of experience (QoE) at a given bandwidth budget. In this pap…
SDOF-Tracker: Fast and Accurate Multiple Human Tracking by Skipped-Detection and Optical-Flow
Hitoshi Nishimura, Satoshi Komorita, Yasutomo Kawanishi +1
Multiple human tracking is a fundamental problem for scene understanding. Although both accuracy and speed are required in real-world applications, recent tracking methods based on…
SASL: Saliency-Adaptive Sparsity Learning for Neural Network Acceleration
Jun Shi, Jianfeng Xu, Kazuyuki Tasaka +1
Accelerating the inference speed of CNNs is critical to their deployment in real-world applications. Among all the pruning approaches, those implementing a sparsity learning framew…
Digital Watermarking for Deep Neural Networks
Yuki Nagai, Yusuke Uchida, Shigeyuki Sakazawa +1
Although deep neural networks have made tremendous progress in the area of multimedia representation, training neural models requires a large amount of data and time. It is well-kn…