9 papers
DeSpatial: The devil of Agentic Spatial Reasoning Lies in 3D Itself
Yifei Liu, Xiaolong Zhou, Ziyang Gong +8
Spatial agents have access to reconstruction and segmentation tools, yet inconsistent predictions and fragmented object identities can prevent their outputs from becoming reliable…
Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence
Yuanyuan Gao, Hao Li, Yifei Liu +14
The pursuit of spatial intelligence fundamentally relies on access to large-scale, fine-grained 3D data. However, existing approaches predominantly construct spatial understanding…
CanoVerse: 3D Object Scalable Canonicalization and Dataset for Generation and Pose
Li Jin, Yuchen Yang, Weikai Chen +11
3D learning systems implicitly assume that objects occupy a coherent reference frame. Nonetheless, in practice, every asset arrives with an arbitrary global rotation, and models ar…
From Detection to Association: Learning Discriminative Object Embeddings for Multi-Object Tracking
Yuqing Shao, Yuchen Yang, Rui Yu +5
End-to-end multi-object tracking (MOT) methods have recently achieved remarkable progress by unifying detection and association within a single framework. Despite their strong dete…
RacketVision: A Multiple Racket Sports Benchmark for Unified Ball and Racket Analysis
Linfeng Dong, Yuchen Yang, Hao Wu +4
We introduce RacketVision, a novel dataset and benchmark for advancing computer vision in sports analytics, covering table tennis, tennis, and badminton. The dataset is the first t…
Learnable SMPLify: A Neural Solution for Optimization-Free Human Pose Inverse Kinematics
Yuchen Yang, Linfeng Dong, Wei Wang +2
In 3D human pose and shape estimation, SMPLify remains a robust baseline that solves inverse kinematics (IK) through iterative optimization. However, its high computational cost li…
SGA-INTERACT: A 3D Skeleton-based Benchmark for Group Activity Understanding in Modern Basketball Tactic
Yuchen Yang, Wei Wang, Yifei Liu +5
Group Activity Understanding is predominantly studied as Group Activity Recognition (GAR) task. However, existing GAR benchmarks suffer from coarse-grained activity vocabularies an…
λScale: Enabling Fast Scaling for Serverless Large Language Model Inference
Minchen Yu, Rui Yang, Chaobo Jia +9
Serverless computing has emerged as a compelling solution for cloud-based model inference. However, as modern large language models (LLMs) continue to grow in size, existing server…
X as Supervision: Contending with Depth Ambiguity in Unsupervised Monocular 3D Pose Estimation
Yuchen Yang, Xuanyi Liu, Xing Gao +2
Recent unsupervised methods for monocular 3D pose estimation have endeavored to reduce dependence on limited annotated 3D data, but most are solely formulated in 2D space, overlook…