Related papers: CLIPUNetr: Assisting Human-robot Interface for Unc…
Biomedical image segmentation is a crucial part of both scientific research and clinical care. With enough labelled data, deep learning models can be trained to accurately automate specific biomedical image segmentation tasks. However,…
Assessing the critical view of safety in laparoscopic cholecystectomy requires accurate identification and localization of key anatomical structures, reasoning about their geometric relationships to one another, and determining the quality…
Vision Transformers can achieve high accuracy and strong generalization across various contexts, but their practical applicability on real-world robotic systems is limited due to their quadratic attention complexity. Recent works have…
Scene understanding and object recognition is a difficult to achieve yet crucial skill for robots. Recently, Convolutional Neural Networks (CNN), have shown success in this task. However, there is still a gap between their performance on…
Vision language (VL) models like CLIP are robust to natural distribution shifts, in part because CLIP learns on unstructured data using a technique called caption supervision; the model inteprets image-linked texts as ground-truth labels.…
Promptable foundation models such as the Segment Anything Model (SAM) produce high-quality masks but remain semantically blind, relying on external prompts to specify categories. Existing vision-language approaches address this limitation…
Semantic segmentation is a crucial step in many Earth observation tasks. Large quantity of pixel-level annotation is required to train deep networks for semantic segmentation. Earth observation techniques are applied to varieties of…
Active recognition, which allows intelligent agents to explore observations for better recognition performance, serves as a prerequisite for various embodied AI tasks, such as grasping, navigation and room arrangements. Given the evolving…
Deep Neural Networks (DNNs) demonstrate remarkable capabilities in learning complex hierarchical data representations, but the nature of these representations remains largely unknown. Existing global explainability methods, such as Network…
The application of zero-shot learning in computer vision has been revolutionized by the use of image-text matching models. The most notable example, CLIP, has been widely used for both zero-shot classification and guiding generative models…
Systems involving human-robot collaboration necessarily require that steps be taken to ensure safety of the participating human. This is usually achievable if accurate, reliable estimates of the human's pose are available. In this paper, we…
As robots increasingly enter human-centered environments, they must not only be able to navigate safely around humans, but also adhere to complex social norms. Humans often rely on non-verbal communication through gestures and facial…
Most existing video tasks related to "human" focus on the segmentation of salient humans, ignoring the unspecified others in the video. Few studies have focused on segmenting and tracking all humans in a complex video, including pedestrians…
Multimodal emotion recognition (MER) aims to identify human emotions by combining data from various modalities such as language, audio, and vision. Despite the recent advances of MER approaches, the limitations in obtaining extensive…
LIDAR semantic segmentation, which assigns a semantic label to each 3D point measured by the LIDAR, is becoming an essential task for many robotic applications such as autonomous driving. Fast and efficient semantic segmentation methods are…
Visible-infrared person re-identification (VIReID) primarily deals with matching identities across person images from different modalities. Due to the modality gap between visible and infrared images, cross-modality identity matching poses…
Over the past decade, most methods in visual place recognition (VPR) have used neural networks to produce feature representations. These networks typically produce a global representation of a place image using only this image itself and…
Machine unlearning (MU) has gained significant attention as a means to remove specific data from trained models without requiring a full retraining process. While progress has been made in unimodal domains like text and image…
Referring image segmentation aims to segment an object referred to by natural language expression from an image. The primary challenge lies in the efficient propagation of fine-grained semantic information from textual features to visual…
Unsupervised panoptic segmentation aims to partition an image into semantically meaningful regions and distinct object instances without training on manually annotated data. In contrast to prior work on unsupervised panoptic scene…