4 citations · 6 across the 6 of their papers we have counts for
8 papers
ArticuTable: Generating Instance-Level Interactive Rigid-Articulated 3D Tabletop Scenes from a Single Image
Kai Lv, Yibo Yin, Lijun Guo +3
Embodied agents benefit from 3D environments that combine visual fidelity to real-world observations with physical interactivity. Existing single-image tabletop reconstruction meth…
PlanarTrack: A high-quality and challenging benchmark for large-scale planar object tracking
Yifan Jiao, Xinran Liu, Xiaoqiong Liu +3
Planar tracking has drawn increasing interest owing to its key roles in robotics and augmented reality. Despite recent great advancement, further development of planar tracking, pa…
DMTrack: Spatio-Temporal Multimodal Tracking via Dual-Adapter
Weihong Li, Shaohua Dong, Haonan Lu +3
In this paper, we explore adapter tuning and introduce a novel dual-adapter architecture for spatio-temporal multimodal tracking, dubbed DMTrack. The key of our DMTrack lies in two…
CGTrack: Cascade Gating Network with Hierarchical Feature Aggregation for UAV Tracking
Weihong Li, Xiaoqiong Liu, Heng Fan +1
Recent advancements in visual object tracking have markedly improved the capabilities of unmanned aerial vehicle (UAV) tracking, which is a critical component in real-world robotic…
Attention to Trajectory: Trajectory-Aware Open-Vocabulary Tracking
Yunhao Li, Yifan Jiao, Dan Meng +2
Open-Vocabulary Multi-Object Tracking (OV-MOT) aims to enable approaches to track objects without being limited to a predefined set of categories. Current OV-MOT methods typically…
LaMOT: Language-Guided Multi-Object Tracking
Yunhao Li, Xiaoqiong Liu, Luke Liu +2
Vision-Language MOT is a crucial tracking problem and has drawn increasing attention recently. It aims to track objects based on human language commands, replacing the traditional…
VastTrack: Vast Category Visual Object Tracking
Liang Peng, Junyuan Gao, Xinran Liu +5
In this paper, we introduce a novel benchmark, dubbed VastTrack, towards facilitating the development of more general visual tracking via encompassing abundant classes and videos.…
Beyond MOT: Semantic Multi-Object Tracking
Yunhao Li, Qin Li, Hao Wang +5
Current multi-object tracking (MOT) aims to predict trajectories of targets (i.e., ''where'') in videos. Yet, knowing merely ''where'' is insufficient in many crucial applications.…