相关论文: Human-Machine CRFs for Identifying Bottlenecks in …

Effective environment perception is crucial for enabling downstream robotic applications. Individual robotic agents often face occlusion and limited visibility issues, whereas multi-agent systems can offer a more comprehensive mapping of…

Joint scene understanding and segmentation for automotive applications is a challenging problem in two key aspects:- (1) classifying every pixel in the entire scene and (2) performing this task under unstable weather and illumination…

Image semantic segmentation is parsing image into several partitions in such a way that each region of which involves a semantic concept. In a weakly supervised manner, since only image-level labels are available, discriminating objects…

Understanding humans from photographs has always been a fundamental goal of computer vision. In this thesis we have developed a hierarchy of tools that cover a wide range of topics with the objective of understanding humans from monocular…

Real-world objects occur in specific contexts. Such context has been shown to facilitate detection by constraining the locations to search. But can context directly benefit object detection? To do so, context needs to be learned…

General scene perception has progressed from object recognition toward open-vocabulary grounding, part localization, and affordance prediction. Yet these capabilities are often realized as isolated predictions that localize objects, parts,…

Inspired by speech recognition, recent state-of-the-art algorithms mostly consider scene text recognition as a sequence prediction problem. Though achieving excellent performance, these methods usually neglect an important fact that text in…

Dynamic scene understanding is the ability of a computer system to interpret and make sense of the visual information present in a video of a real-world scene. In this thesis, we present a series of frameworks for dynamic scene…

Multimodal Large Language Models (MLLMs) have demonstrated significant advances in visual understanding tasks. However, their capacity to comprehend human-centric scenes has rarely been explored, primarily due to the absence of…

Representing a scene and its constituent objects from raw sensory data is a core ability for enabling robots to interact with their environment. In this paper, we propose a novel approach for scene understanding, leveraging a hierarchical…

Object detection, scene graph generation and region captioning, which are three scene understanding tasks at different semantic levels, are tied together: scene graphs are generated on top of objects detected in an image with their pairwise…

We present a method for composing photorealistic scenes from captured images of objects. Our work builds upon neural radiance fields (NeRFs), which implicitly model the volumetric density and directionally-emitted radiance of a scene. While…

Identifying objects in an image and their mutual relationships as a scene graph leads to a deep understanding of image content. Despite the recent advancement in deep learning, the detection and labeling of visual object relationships…

A comprehensive and explicit understanding of surgical scenes plays a vital role in developing context-aware computer-assisted systems in the operating theatre. However, few works provide systematical analysis to enable hierarchical…

Automated scene analysis has been a topic of great interest in computer vision and cognitive science. Recently, with the growth of crowd phenomena in the real world, crowded scene analysis has attracted much attention. However, the visual…

Visual scene understanding is a fundamental task in computer vision that aims to extract meaningful information from visual data. It traditionally involves disjoint and specialized algorithms for different tasks that are tailored for…

Modelling individual objects in a scene as Neural Radiance Fields (NeRFs) provides an alternative geometric scene representation that may benefit downstream robotics tasks such as scene understanding and object manipulation. However, we…

Humans rarely perceive objects in isolation but interpret scenes through relationships among co-occurring elements. How such contextual knowledge is acquired without explicit supervision remains unclear. Here we combine human psychophysics…

Humans are excellent at perceiving illusory outlines. We are readily able to complete contours, shapes, scenes, and even unseen objects when provided with images that contain broken fragments of a connected appearance. In vision science,…

Active sensing and planning in unknown, cluttered environments is an open challenge for robots intending to provide home service, search and rescue, narrow-passage inspection, and medical assistance. Although many active sensing methods…