이용하 교수

We present the first fully convolutional end-to-end solution for instance-aware semantic segmentation task. It inherits all the merits of FCNs for semantic segmentation [29] and instance mask proposal [5]. It performs instance mask prediction and classification jointly. The underlying convolutional representation is fully shared between the two sub-tasks, as well as between all regions of interest. The network architecture is highly integrated and efficient. It achieves state-of-the-art performa

Contrastive language-image pre-training (CLIP) is a powerful vision-language model that has shown great benefits for various tasks. However, we have identified some issues with its explainability, which undermine its credibility and limit the capacity for related tasks. Specifically, we find that CLIP tends to focus on background regions rather than foregrounds, with noisy activations at irrelevant positions on the visualization results. These phenomena conflict with conventional explainability

Motion planning of multiple mobile agents in virtual environments is a very challenging problem, especially if one wants to plan the motions of these agents in real-time. We propose a two layered approach to plan motions of multiple mobile agents in real-time. The mobile agents are moving in a 2-dimensional static environment with open spaces connected to each other by narrow corridors. The global path of each agent is computed by a decoupled planner during the preprocessing process with minimum

We proposed in a previous paper (2006) a hybrid two-layered approach for motion planning of multiple agents in static virtual environments, consisting of open spaces connected by multiple narrow passages. The discrete generalized Voronoi diagram (GVD) of the environment is used to identify narrow passages, and plan the global path of each agent independently of other agents' global paths. As each agent moves along its global path, the agent's path is locally modified using the hybrid technique o

Recently, teaching-learning procedures focused on student understanding has changed the didactic transposition of teachers' knowledge in the educational world. Accordingly, Pedagogical Content Knowledge, is believed to be the most important aspect of teacher knowledge in teaching-learning procedure. This study organized the misconceptions and error analyses focused on the function field which is the basis of secondary mathematics education and one subject hard to teach and analyze with respect t

Deep learning-based object detection methods address the problem of how to trade off the object detection accuracy and detection speed of the model. This paper proposes the PBA-YOLOv7 network algorithm, which is based on the YOLOv7 network, and first introduces the PConv, which lightens the ELAN module in the backbone network structure and reduces the number of parameters to improve the detection speed of the network and then designs and introduces the BiFusionNet network, which better aggregate

Do video-text transformers learn to model temporal relationships across frames? Despite their immense capacity and the abundance of multimodal training data, recent work has revealed the strong tendency of video-text models towards frame-based spatial representations, while temporal reasoning remains largely unsolved. In this work, we identify several key challenges in temporal learning of video-text transformers: the spatiotemporal trade-off from limited network size; the curse of dimensionalit

The crux of homography estimation is that the homography is characterized by the geometric correspondences between two related images rather than appearance features, which differs from typical image recognition tasks. Existing methods either decompose the task of homography estimation into several individual sub-problems and optimize them sequentially, or attempt to tackle it in an end-to-end manner by delegating the whole task to deep convolutional networks (CNNs). However, it is quite arduous

We present six-degree-of-freedom (6DoF) haptic rendering algorithms using translational (<TEX>$PD_t$</TEX>) and generalized penetration depth (<TEX>$PD_g$</TEX>). Our rendering algorithm can handle any type of object/object haptic interaction using penalty-based response and makes no assumption about the underlying geometry and topology. Moreover, our rendering algorithm can effectively deal with multiple contacts. Our penetration depth algorithms for <TEX>$PD_t$</TEX> and <TEX>$PD_g$</TEX> are

Weakly-Supervised Semantic Segmentation (WSSS) segments objects without a\nheavy burden of dense annotation. While as a price, generated pseudo-masks\nexist obvious noisy pixels, which result in sub-optimal segmentation models\ntrained over these pseudo-masks. But rare studies notice or work on this\nproblem, even these noisy pixels are inevitable after their improvements on\npseudo-mask. So we try to improve WSSS in the aspect of noise mitigation. And\nwe observe that many noisy pixels are of h

We consider the problem of creating tighter-fitting bounding volumes (more specifically rectangular swept spheres) when constructing bounding volume hierarchies (BVHs) for complex 3D geometries given in the form of unstructured triangle meshes/soups with the aim of speeding up our IPS Path Planner for rigid bodies, where the triangles often have very different sizes. Currently, the underlying collision and distance computation module (IPS CDC) does not take into account the sizes of the triangle

We proposed in a previous paper a hybrid technique, combining local steering behaviors and coordination graphs (CG), that allows real-time motion planning of multiple agents in a narrow passage. This hybrid technique not only avoids deadlocks, but also exhibits other interesting behaviors such as leader following, even though they are not explicitly coded in the algorithm. In this paper, we build upon the earlier result, and propose a two-layered approach to motion planning of multiple agents in

We present a novel approach for real-time motion planning of multiple formations in virtual environments with dynamic obstacles. Our algorithm is based on the continuum model for crowd simulation and our flexible virtual structure approach for formation control in virtual environments. Simulations created with our algorithm run at interactive rates in quite complex environments. In addition, each formation can be deformed in real-time and the deformation is triggered either automatically (e.g.,

Do video-text transformers learn to model temporal relationships across frames? Despite their immense capacity and the abundance of multimodal training data, recent work has revealed the strong tendency of video-text models towards frame-based spatial representations, while temporal reasoning remains largely unsolved. In this work, we identify several key challenges in temporal learning of video-text transformers: the spatiotemporal trade-off from limited network size; the curse of dimensionalit