works on

From the 1 of 5 linked papers with an AI index.

collaborators

5 papers

cs.CV2026

PanoAffordanceNet: Towards Holistic Affordance Grounding in 360° Indoor Environments

Guoliang Zhu, Wanjun Jia, Caoyang Shao +3

The paper defines holistic affordance grounding for 360° indoor scenes and presents PanoAffordanceNet, a model that corrects equirectangular distortion and densifies sparse predict…

cs.CV2026

PS-MOT: Cultivating Instance Awareness from Point Seeds for Multi-Object Tracking

Kai Luo, Fei Teng, Mengfei Duan +6

We introduce Point-supervised Multi-Object Tracking (PS-MOT) as a cost-effective alternative to traditional bounding box supervision, shifting the focus from spatial fitting to top…

cs.CV2026

BLaDA: Bridging Language to Functional Dexterous Actions within 3DGS Fields

Fan Yang, Wenrui Chen, Guorun Yan +7

In unstructured environments, functional dexterous grasping calls for the tight integration of semantic understanding, precise 3D functional localization, and physically interpreta…

cs.RO2026

TRACER: Texture-Robust Affordance Chain-of-Thought for Deformable-Object Refinement

Wanjun Jia, Kang Li, Fan Yang +7

The central challenge in robotic manipulation of deformable objects lies in aligning high-level semantic instructions with physical interaction points under complex appearance and…

cs.CV2025

One-Shot Affordance Grounding of Deformable Objects in Egocentric Organizing Scenes

Wanjun Jia, Fan Yang, Mengfei Duan +6

Deformable object manipulation in robotics presents significant challenges due to uncertainties in component properties, diverse configurations, visual interference, and ambiguous…