90 citations
- Honda (Germany)DE9 papers
- Honda Research Institute Japan Co., Ltd. (Japan)JP5 papers
- Carnegie Mellon UniversityUS4 papers
- Georgia Institute of TechnologyUS4 papers
- Bielefeld UniversityDE3 papers
- Honda (United States)US3 papers
- Kyoto UniversityJP3 papers
- Technische Universität DarmstadtDE3 papers
- University of Maryland, College ParkUS3 papers
- Cornell UniversityUS2 papers
- École Polytechnique Fédérale de LausanneCH2 papers
- Google (United States)US2 papers
7 papers · 1 filter
A Unified Tokenization Framework for Pain Recognition using Heterogeneous 3D Modalities
Stefanos Gkikas, Christian Arzate Cruz, Valentina Becchetti +3
Pain is a complex and pervasive phenomenon affecting a large percentage of the population, and accurate assessment is essential for effective clinical management and intervention.…
Decoupled PROB: Decoupled Query Initialization Tasks and Objectness-Class Learning for Open World Object Detection
Riku Inoue, Masamitsu Tsuchiya, Yuji Yasui
Open World Object Detection (OWOD) is a challenging computer vision task that extends standard object detection by (1) detecting and classifying unknown objects without supervision…
Channel-wise Motion Features for Efficient Motion Segmentation
Riku Inoue, Masamitsu Tsuchiya, Yuji Yasui
For safety-critical robotics applications such as autonomous driving, it is important to detect all required objects accurately in real-time. Motion segmentation offers a solution…
ViTGAN: Training GANs with Vision Transformers
Kwonjoon Lee, Huiwen Chang, Lu Jiang +3
Recently, Vision Transformers (ViTs) have shown competitive performance on image recognition while requiring less vision-specific inductive biases. In this paper, we investigate if…
SVMax: A Feature Embedding Regularizer
Ahmed Taha, Alex Hanson, Abhinav Shrivastava +1
A neural network regularizer (e.g., weight decay) boosts performance by explicitly penalizing the complexity of a network. In this paper, we penalize inferior network activations -…
Spatio-Temporal Pyramid Graph Convolutions for Human Action Recognition and Postural Assessment
Behnoosh Parsa, Athma Narayanan, Behzad Dariush
Recognition of human actions and associated interactions with objects and the environment is an important problem in computer vision due to its potential applications in a variety…