5 citations · 9 across the 14 of their papers we have counts for
15 papers
HuRo: Robotizing Human Videos for Scalable VLA Pretraining
Jinho Jeong, Se June Joo, Jaehyun Kang +4
Human video datasets offer an abundant and diverse source of interaction data that can complement expensive real-robot data. To bridge the human-to-robot embodiment gap, existing a…
Keep It Simple: Multi-Key Episodic Memory Retrieval for Ultra-Long Video Understanding
Yeeun Choi, Youngbeom Yoo, Joon-Young Lee +2
When videos extend from hours to days, directly processing them end-to-end becomes impractical for current Multi-modal Large Language Models (MLLMs). This ultra-long setting necess…
Where Did It Go Wrong? Process-Level Evaluation of Web Agents with Semantic State Tracking
Jiwan Chung, JiHyuk Byun, Vibhav Vineet +1
Web agents act through long interaction sequences, yet existing benchmarks evaluate only terminal success, discarding all process information and offering little guidance on improv…
Hierarchical Latent Action Model
Hanjung Kim, Lerrel Pinto, Seon Joo Kim
Latent Action Models (LAMs) enable learning from actionless data for applications ranging from robotic control to interactive world models. However, existing LAMs typically focus o…
Open-ended Hierarchical Streaming Video Understanding with Vision Language Models
Hyolim Kang, Yunsu Park, Youngbeom Yoo +2
We introduce Hierarchical Streaming Video Understanding, a task that combines online temporal action localization with free-form description generation. Given the scarcity of datas…
UniSkill: Imitating Human Videos via Cross-Embodiment Skill Representations
Hanjung Kim, Jaehyun Kang, Hyolim Kang +3
Mimicry is a fundamental learning mechanism in humans, enabling individuals to learn new tasks by observing and imitating experts. However, applying this ability to robots presents…
ActionSwitch: Class-agnostic Detection of Simultaneous Actions in Streaming Videos
Hyolim Kang, Jeongseok Hyun, Joungbin An +2
Online Temporal Action Localization (On-TAL) is a critical task that aims to instantaneously identify action instances in untrimmed streaming videos as soon as an action concludes…
Exploring Scalability of Self-Training for Open-Vocabulary Temporal Action Localization
Jeongseok Hyun, Su Ho Han, Hyolim Kang +2
The vocabulary size in temporal action localization (TAL) is limited by the scarcity of large-scale annotated datasets. To overcome this, recent works integrate vision-language mod…
Object Aware Egocentric Online Action Detection
Joungbin An, Yunsu Park, Hyolim Kang +1
Advancements in egocentric video datasets like Ego4D, EPIC-Kitchens, and Ego-Exo4D have enriched the study of first-person human interactions, which is crucial for applications in…
Shepherding Slots to Objects: Towards Stable and Robust Object-Centric Learning
Jinwoo Kim, Janghyuk Choi, Ho-Jin Choi +1
Object-centric learning (OCL) aspires general and compositional understanding of scenes by representing a scene as a collection of object-centric representations. OCL has also been…
ComMU: Dataset for Combinatorial Music Generation
Lee Hyun, Taehyun Kim, Hyolim Kang +5
Commercial adoption of automatic music composition requires the capability of generating diverse and high-quality music suitable for the desired context (e.g., music for romantic m…
Soft-Landing Strategy for Alleviating the Task Discrepancy Problem in Temporal Action Localization Tasks
Hyolim Kang, Hanjung Kim, Joungbin An +2
Temporal Action Localization (TAL) methods typically operate on top of feature sequences from a frozen snippet encoder that is pretrained with the Trimmed Action Classification (TA…
A Generalized Framework for Video Instance Segmentation
Miran Heo, Sukjun Hwang, Jeongseok Hyun +4
The handling of long videos with complex and occluded sequences has recently emerged as a new challenge in the video instance segmentation (VIS) community. However, existing method…
UBoCo : Unsupervised Boundary Contrastive Learning for Generic Event Boundary Detection
Hyolim Kang, Jinwoo Kim, Taehyun Kim +1
Generic Event Boundary Detection (GEBD) is a newly suggested video understanding task that aims to find one level deeper semantic boundaries of events. Bridging the gap between nat…
Winning the CVPR'2021 Kinetics-GEBD Challenge: Contrastive Learning Approach
Hyolim Kang, Jinwoo Kim, Kyungmin Kim +2
Generic Event Boundary Detection (GEBD) is a newly introduced task that aims to detect "general" event boundaries that correspond to natural human perception. In this paper, we int…