5 papers
Towards Spatial Supersensing in the Wild
Tianjun Gu, Tianyu Xin, Kuan Zhang +12
The paper introduces VSI‑Super‑Wild, a large benchmark of real‑world long videos with human‑verified QA pairs to evaluate how well multimodal models can track and reason about agen…
Thinking in 360°: Humanoid Visual Search in the Wild
Heyang Yu, Yinan Han, Xiangyu Zhang +9
Humans rely on the synergistic control of head (cephalomotor) and eye (oculomotor) to efficiently search for visual information in 360°. However, prior approaches to visual search…
MambaTrack3D: A State Space Model Framework for LiDAR-Based Object Tracking under High Temporal Variation
Shengjing Tian, Yinan Han, Xiantong Zhao +2
Dynamic outdoor environments with high temporal variation (HTV) pose significant challenges for 3D single object tracking in LiDAR point clouds. Existing memory-based trackers ofte…
Adversarial Attacks on LiDAR-Based Tracking Across Road Users: Robustness Evaluation and Target-Aware Black-Box Method
Shengjing Tian, Xiantong Zhao, Yuhao Bian +2
In this study, we delve into the robustness of neural network-based LiDAR point cloud tracking models under adversarial attacks, a critical aspect often overlooked in favor of perf…
Robust Single Object Tracking in LiDAR Point Clouds under Adverse Weather Conditions
Xiantong Zhao, Xiuping Liu, Shengjing Tian +1
3D single object tracking (3DSOT) in LiDAR point clouds is a critical task for outdoor perception, enabling real-time perception of object location, orientation, and motion. Despit…