Zobrazeno 1 - 10
of 258
pro vyhledávání: '"Yoon, Kuk-Jin"'
Autor:
Jeong, Wooseong, Yoon, Kuk-Jin
Publikováno v:
CVPR 2024
The goal of multi-task learning is to learn diverse tasks within a single unified network. As each task has its own unique objective function, conflicts emerge during training, resulting in negative transfer among them. Earlier research identified th
Externí odkaz:
http://arxiv.org/abs/2406.02996
Recent advancements in zero-shot video diffusion models have shown promise for text-driven video editing, but challenges remain in achieving high temporal consistency. To address this, we introduce Video-3DGS, a 3D Gaussian Splatting (3DGS)-based vid
Externí odkaz:
http://arxiv.org/abs/2406.02541
Human pose forecasting garners attention for its diverse applications. However, challenges in modeling the multi-modal nature of human motion and intricate interactions among agents persist, particularly with longer timescales and more agents. In thi
Externí odkaz:
http://arxiv.org/abs/2404.05218
Autor:
Joung, Byeongin, Lee, Byeong-Uk, Choe, Jaesung, Shin, Ukcheol, Kang, Minjun, Lee, Taeyeop, Kweon, In So, Yoon, Kuk-Jin
This paper proposes an algorithm for synthesizing novel views under few-shot setup. The main concept is to develop a stable surface regularization technique called Annealing Signed Distance Function (ASDF), which anneals the surface in a coarse-to-fi
Externí odkaz:
http://arxiv.org/abs/2403.19985
Trajectory prediction is a challenging problem that requires considering interactions among multiple actors and the surrounding environment. While data-driven approaches have been used to address this complex problem, they suffer from unreliable pred
Externí odkaz:
http://arxiv.org/abs/2403.10052
Multi-agent trajectory prediction is crucial for various practical applications, spurring the construction of many large-scale trajectory datasets, including vehicles and pedestrians. However, discrepancies exist among datasets due to external factor
Externí odkaz:
http://arxiv.org/abs/2312.15906
Recognizing objects from sparse and noisy events becomes extremely difficult when paired images and category labels do not exist. In this paper, we study label-free event-based object recognition where category labels and paired images are not availa
Externí odkaz:
http://arxiv.org/abs/2308.09383
Sensor fusion approaches for intelligent self-driving agents remain key to driving scene understanding given visual global contexts acquired from input sensors. Specifically, for the local waypoint prediction task, single-modality networks are still
Externí odkaz:
http://arxiv.org/abs/2308.02126
Understanding the interaction between multiple agents is crucial for realistic vehicle trajectory prediction. Existing methods have attempted to infer the interaction from the observed past trajectories of agents using pooling, attention, or graph-ba
Externí odkaz:
http://arxiv.org/abs/2305.14715
Autor:
Shin, Inkyu, Kim, Dahun, Yu, Qihang, Xie, Jun, Kim, Hong-Seok, Green, Bradley, Kweon, In So, Yoon, Kuk-Jin, Chen, Liang-Chieh
Video Panoptic Segmentation (VPS) aims to achieve comprehensive pixel-level scene understanding by segmenting all pixels and associating objects in a video. Current solutions can be categorized into online and near-online approaches. Evolving over th
Externí odkaz:
http://arxiv.org/abs/2304.04694