8 accepted papers
Emotion recognition is an important task in computer vision. However, current approaches using hard associations (e.g., element-wise addition or concatenation) suffer from information pollution. To overcome these challenges and utilize information at different scales, we present a novel Transformer-…
Magnetic resonance-guided focused ultrasound (MRg-FUS) has become attractive, accredited to its non-invasive nature. However, ultrasound beams focusing and steering is still challenging owing to aberrations induced by soft tissue heterogeneity. In particular for beam motion control to ensure real-ti
In empathetic conversations, individuals express their empathy towards others. Previous work has mainly focused on generating empathetic responses by utilizing the speaker’s emotion. Besides, external commonsense knowledge has been applied to enhance the system’s understandings of the speaker’s situ…
In this paper, we develop a weakly supervised learning algorithm to learn robust semantic correspondences from large-scale datasets with only image-level labels. Following the spirit of multiple instance learning (MIL), we decompose the weakly supervised correspondence learning problem into three st…
Although the soft robot is gaining considerable popularity in dexterous and safe manipulation, accurate motion control is still an open problem to be explored. Recent investigations suggest that reinforcement learning (RL) is a promising solution but lacks efficient adaptability for Sim2Real transfe…
Focused ultrasound (FUS) technology attracts increasing interests accrediting to its non-invasive and painless treatment of tumors. Magnetic resonance imaging (MRI) guidance has been introduced to monitor this procedure, thus allowing the ultrasound foci to be precisely controlled. However, manual p
In the feature/object tracking of eye-in-hand visual servoing, 2D motion estimation relying only on image plane feedback is easily affected by vision occlusion, blurring, or poor lighting. For the commonly-used template matching method, tracking performance greatly depends on the image quality. Fibe
Soft robots, owing to their elastomeric material, ensure safe interaction with their surroundings. These robot compliance properties inevitably impose a tradeoff against precise motion control, as to which conventional model-based methods were proposed to approximate the robot kinematics. However, t