Related papers: Exploring Segment-level Semantics for Online Phase…
Medical image segmentation plays a crucial role in clinical workflows, but domain shift often leads to performance degradation when models are applied to unseen clinical domains. This challenge arises due to variations in imaging…
Spatial attention mechanism has been widely used in semantic segmentation of remote sensing images given its capability to model long-range dependencies. Many methods adopting spatial attention mechanism aggregate contextual information…
Increasing scene-awareness is a key challenge in video anomaly detection (VAD). In this work, we propose a hierarchical semantic contrast (HSC) method to learn a scene-aware VAD model from normal videos. We first incorporate foreground…
Semantic segmentation is the task of classifying each pixel in an image. Training a segmentation model achieves best results using annotated images, where each pixel is annotated with the corresponding class. When obtaining fine annotations…
Segments that span contiguous parts of inputs, such as phonemes in speech, named entities in sentences, actions in videos, occur frequently in sequence prediction problems. Segmental models, a class of models that explicitly hypothesizes…
Medical image segmentation plays a crucial role in computer-aided diagnosis. However, existing methods heavily rely on fully supervised training, which requires a large amount of labeled data with time-consuming pixel-wise annotations.…
Surgical phase recognition is of particular interest to computer assisted surgery systems, in which the goal is to predict what phase is occurring at each frame for a surgery video. Networks with multi-stage architecture have been widely…
Volumetric medical segmentation is a critical component of 3D medical image analysis that delineates different semantic regions. Deep neural networks have significantly improved volumetric medical segmentation, but they generally require…
The ability to predict and therefore to anticipate the future is an important attribute of intelligence. It is also of utmost importance in real-time systems, e.g. in robotics or autonomous driving, which depend on visual scene…
In this dissertation, I present my work towards exploring temporal information for better video understanding. Specifically, I have worked on two problems: action recognition and semantic segmentation. For action recognition, I have…
While the Segment Anything Model (SAM) excels in semantic segmentation for general-purpose images, its performance significantly deteriorates when applied to medical images, primarily attributable to insufficient representation of medical…
Video semantic segmentation aims to generate accurate semantic maps for each video frame. To this end, many works dedicate to integrate diverse information from consecutive frames to enhance the features for prediction, where a feature…
Instance segmentation in videos, which aims to segment and track multiple objects in video frames, has garnered a flurry of research attention in recent years. In this paper, we present a novel weakly supervised framework with…
Nuanced understanding and the generation of detailed descriptive content for (bimanual) manipulation actions in videos is important for disciplines such as robotics, human-computer interaction, and video content analysis. This study…
Semantic segmentation from RGB cameras is essential to the perception of autonomous flying vehicles. The stability of predictions through the captured videos is paramount to their reliability and, by extension, to the trustworthiness of the…
Semantic segmentation in very high resolution (VHR) aerial images is one of the most challenging tasks in remote sensing image understanding. Most of the current approaches are based on deep convolutional neural networks (DCNNs). However,…
Models for semantic segmentation require a large amount of hand-labeled training data which is costly and time-consuming to produce. For this purpose, we present a label fusion framework that is capable of improving semantic pixel labels of…
Colo-segment recognition in colonoscopy videos is a key requirement for many downstream tasks, but existing automatic recognition methods only use colonoscopy images without fully exploiting the use of temporal information, leading to poor…
The Segment Anything Model (SAM) exhibits a capability to segment a wide array of objects in natural images, serving as a versatile perceptual tool for various downstream image segmentation tasks. In contrast, medical image segmentation…
Automatic segmentation of hepatocellular carcinoma (HCC) in Digital Subtraction Angiography (DSA) videos can assist radiologists in efficient diagnosis of HCC and accurate evaluation of tumors in clinical practice. Few studies have…