13 papers
Can we Trust Unreliable Voxels? Exploring 3D Semantic Occupancy Prediction under Label Noise
Wenxin Li, Kunyu Peng, Di Wen +6
3D semantic occupancy prediction is a cornerstone of robotic perception, yet real-world voxel annotations are inherently corrupted by structural artifacts and dynamic trailing effe…
Quo Vadis, Visual In-Context Learning? A Unified Benchmark Across Domains and Tasks
Pradnya Halady, Jiale Wei, Zdravko Marinov +2
Visual in-context learning has been proposed as a pathway towards dynamic models that can generate predictions based on a provided context and thereby can adapt to new vision tasks…
IMPACT-Scribe: Interactive Temporal Action Segmentation with Boundary Scribbles and Query Planning
Qian Yin, Di Wen, Kunyu Peng +11
Dense temporal annotation of procedural activity videos is vital for action understanding and embodied intelligence but remains labor-intensive due to reactive tools. Each correcti…
IMPACT-HOI: Supervisory Control for Onset-Anchored Partial HOI Event Construction
Haoshen Zhang, Di Wen, Kunyu Peng +12
We present IMPACT-HOI, a mixed-initiative framework for annotating egocentric procedural video by constructing structured event graphs for Human-Object Interactions (HOI), motivate…
IMPACT-CYCLE: A Contract-Based Multi-Agent System for Claim-Level Supervisory Correction of Long-Video Semantic Memory
Weitong Kong, Di Wen, Kunyu Peng +10
Correcting errors in long-video understanding is disproportionately costly: existing multimodal pipelines produce opaque, end-to-end outputs that expose no intermediate state for i…
Rethinking Video Human-Object Interaction: Set Prediction over Time for Unified Detection and Anticipation
Yuanhao Luo, Di Wen, Kunyu Peng +5
Video-based human-object interaction (HOI) understanding requires both detecting ongoing interactions and anticipating their future evolution. However, existing methods usually tre…