Related papers: Spatially Constrained Location Prior for Scene Par…

Sequential matching using hand-crafted heuristics has been standard practice in route-based place recognition for enhancing pairwise similarity results for nearly a decade. However, precision-recall performance of these algorithms…

One of the current trends in robotics is to employ large language models (LLMs) to provide non-predefined command execution and natural human-robot interaction. It is useful to have an environment map together with its language…

The image-level label has prevailed in weakly supervised semantic segmentation tasks due to its easy availability. Since image-level labels can only indicate the existence or absence of specific categories of objects, visualization-based…

In text recognition, self-supervised pre-training emerges as a good solution to reduce dependence on expansive annotated real data. Previous studies primarily focus on local visual representation by leveraging mask image modeling or…

In this paper we focus on the challenging problem of place categorization and semantic mapping on a robot without environment-specific training. Motivated by their ongoing success in various visual recognition tasks, we build our system…

This paper addresses a motion planning problem to achieve spatio-temporal-logical tasks, expressed by syntactically co-safe linear temporal logic specifications (scLTL\next), in uncertain environments. Here, the uncertainty is modeled as…

We present Context Forest (ConF), a technique for predicting properties of the objects in an image based on its global appearance. Compared to standard nearest-neighbour techniques, ConF is more accurate, fast and memory efficient. We train…

This paper focuses on visual semantic navigation, the task of producing actions for an active agent to navigate to a specified target object category in an unknown environment. To complete this task, the algorithm should simultaneously…

In this paper, a self-learning approach is proposed towards solving scene-specific pedestrian detection problem without any human' annotation involved. The self-learning approach is deployed as progressive steps of object discovery, object…

Although Simultaneous Localization and Mapping (SLAM) has been an active research topic for decades, current state-of-the-art methods still suffer from instability or inaccuracy due to feature insufficiency or its inherent estimation drift,…

The application of Contrastive Language-Image Pre-training (CLIP) in Weakly Supervised Semantic Segmentation (WSSS) research powerful cross-modal semantic understanding capabilities. Existing methods attempt to optimize input text prompts…

Robots require a semantic understanding of their surroundings to operate in an efficient and explainable way in human environments. In the literature, there has been an extensive focus on object labeling and exhaustive scene graph…

In this paper, we address the unexplored question of temporal sentence localization in human motions (TSLM), aiming to locate a target moment from a 3D human motion that semantically corresponds to a text query. Considering that 3D human…

Detecting pedestrians accurately in urban scenes is significant for realistic applications like autonomous driving or video surveillance. However, confusing human-like objects often lead to wrong detections, and small scale or heavily…

Accurate perception of dynamic traffic scenes is crucial for high-level autonomous driving systems, requiring robust object motion estimation and instance segmentation. However, traditional methods often treat them as separate tasks,…

Multi-label image classification is a fundamental but challenging task in computer vision. Over the past few decades, solutions exploring relationships between semantic labels have made great progress. However, the underlying…

Simultaneous Localization and Mapping (SLAM) plays a crucial role in enabling autonomous vehicles to navigate previously unknown environments. Semantic SLAM mostly extends visual SLAM, leveraging the higher density information available to…

This work explores the use of spatial context as a source of free and plentiful supervisory signal for training a rich visual representation. Given only a large, unlabeled image collection, we extract random pairs of patches from each image…

Dense visual prediction tasks have been constrained by their reliance on predefined categories, limiting their applicability in real-world scenarios where visual concepts are unbounded. While Vision-Language Models (VLMs) like CLIP have…

Semantic image synthesis aims at generating photorealistic images from semantic layouts. Previous approaches with conditional generative adversarial networks (GAN) show state-of-the-art performance on this task, which either feed the…