5 papers
An Anatomy of Vision-Language-Action Models: From Modules to Milestones and Challenges
Chao Xu, Suyu Zhang, Yang Liu +11
Vision-Language-Action (VLA) models are driving a revolution in robotics, enabling machines to understand instructions and interact with the physical world. This field is exploding…
MagicSkin: Balancing Marker and Markerless Modes in Vision-Based Tactile Sensors with a Translucent Skin
Oluwatimilehin Tijani, Zhuo Chen, Jiankang Deng +1
Vision-based tactile sensors (VBTS) face a fundamental trade-off in marker and markerless design on the tactile skin: opaque ink markers enable measurement of force and tangential…
Adaptive Parametric Activation: Unifying and Generalising Activation Functions Across Tasks
Konstantinos Panagiotis Alexandridis, Jiankang Deng, Anh Nguyen +1
The activation function plays a crucial role in model optimisation, yet the optimal choice remains unclear. For example, the Sigmoid activation is the de-facto activation in balanc…
TopoFR: A Closer Look at Topology Alignment on Face Recognition
Jun Dan, Yang Liu, Jiankang Deng +4
The field of face recognition (FR) has undergone significant advancements with the rise of deep learning. Recently, the success of unsupervised learning and graph neural networks h…
Fractal Calibration for long-tailed object detection
Konstantinos Panagiotis Alexandridis, Ismail Elezi, Jiankang Deng +2
Real-world datasets follow an imbalanced distribution, which poses significant challenges in rare-category object detection. Recent studies tackle this problem by developing re-wei…