Author name cluster

Jungho Kim

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

1 author row

AAAI Conference 2025 Conference Paper

ProtoOcc: Accurate, Efficient 3D Occupancy Prediction Using Dual Branch Encoder-Prototype Query Decoder

Jungho Kim
Changwon Kang
Dongyoung Lee
Sehwan Choi
Jun Won Choi

In this paper, we introduce ProtoOcc, a novel 3D occupancy prediction model designed to predict the occupancy states and semantic classes of 3D voxels via a deep semantic understanding of scenes. ProtoOcc consists of two main components: the Dual Branch Encoder (DBE) and the Prototype Query Decoder (PQD). The DBE produces a new 3D voxel representation by combining 3D voxel and BEV representations across multiple scales using a dual branch structure. This design combines the BEV representation, which offers a large receptive field, with the voxel representation, known for its higher spatial resolution, thereby improving both performance and computational efficiency. The PQD employs two types of prototype-based queries to expedite the Transformer decoding process. Scene-Adaptive Prototypes are generated from the 3D voxel features of the input sample, while Scene-Agnostic Prototypes are updated during training using an Exponential Moving Average of the Scene-Adaptive Prototypes. Using these prototype-based queries for decoding, we can directly predict 3D occupancy in a single step, eliminating the need for iterative Transformer decoding. Additionally, we propose Robust Prototype Learning, which introduces noise into the prototype generation process and trains the model to denoise during the training phase. This approach enhances the robustness of ProtoOcc against degraded prototype feature quality. ProtoOcc achieves state-of-the-art performance with 45.02% mIoU on the Occ3D-nuScenes benchmark. For the single-frame method, it reaches 39.56% mIoU with 12.83 FPS on an NVIDIA RTX 3090.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

SiT Dataset: Socially Interactive Pedestrian Trajectory Dataset for Social Navigation Robots

Jong Wook Bae
Jungho Kim
Junyong Yun
Changwon Kang
Jeongseon Choi
Chanhyeok Kim
Junho Lee
Jungwook Choi

To ensure secure and dependable mobility in environments shared by humans and robots, social navigation robots should possess the capability to accurately perceive and predict the trajectories of nearby pedestrians. In this paper, we present a novel dataset of pedestrian trajectories, referred to as Social Interactive Trajectory (SiT) dataset, which can be used to train pedestrian detection, tracking, and trajectory prediction models needed to design social navigation robots. Our dataset includes sequential raw data captured by two 3D LiDARs and five cameras covering a 360-degree view, two inertial measurement unit (IMU) sensors, and real-time kinematic positioning (RTK), as well as annotations including 2D & 3D boxes, object classes, and object IDs. Thus far, various human trajectory datasets have been introduced to support the development of pedestrian motion forecasting models. Our SiT dataset differs from these datasets in the following two respects. First, whereas the pedestrian trajectory data in other datasets was obtained from static scenes, our data was collected while the robot navigates in a crowded environment, capturing human-robot interactive scenarios in motion. Second, our dataset has been carefully organized to facilitate training and evaluation of end-to-end prediction models encompassing 3D detection, 3D multi-object tracking, and trajectory prediction. This design allows for an end-to-end unified modular approach across different tasks. We have introduced a comprehensive benchmark for assessing models across all aforementioned tasks, and have showcased the performance of multiple baseline models as part of our evaluation. Our dataset provides a strong foundation for future research in pedestrian trajectory prediction, which could expedite the development of safe and agile social navigation robots. The SiT dataset, devkit, and pre-trained models are publicly released at: https: //spalaboratory. github. io/SiT

PDF Details

YNIMG Journal 2006 Journal Article

Cortical activation in the processing of passive sentences in L1 and L2: An fMRI study

Satoru Yokoyama
Hideyuki Okamoto
Tadao Miyamoto
Kei Yoshimoto
Jungho Kim
Kazuki Iwata
Hyeonjeong Jeong
Shinya Uchida

The question of whether the bilingual brain processes a first and second language (L1 and L2, respectively) differently is a central issue in many psycholinguistic and neurolinguistic studies. This study used functional magnetic resonance imaging (fMRI) to investigate whether late bilinguals process structurally complex sentences in L1 and L2 in different cortical networks. For this purpose, we directly compared brain activity during the processing of active and passive sentences in both L1 and L2. We asked 36 healthy subjects to judge whether or not a presented sentence was semantically plausible. Both L1 and L2 activated the left hemispheric language-related regions such as the left inferior frontal, superior/middle temporal, and parietal cortices. However, we found different activation patterns between L1 and L2 in the processing of passive sentences. Passive sentences elicited greater activation than their active counterparts in the left pars triangularis, the premotor area, and the superior parietal lobule in Japanese, but not in English. Furthermore, there was a significant interaction between sentence type (active versus passive) and language (Japanese versus English) in the left pars orbitalis. The results of this study indicate that late bilinguals use similar cortical regions to comprehend both L1 and L2. However, when late bilinguals are presented with structurally complex sentences, the involvement of these regions differs between L1 and L2. These results suggest that, in addition to age of L2 acquisition and L2 proficiency, differences in grammatical construction affect cortical representation during the comprehension of L1 and L2.

Details DOI