6 papers
VGGT-Segmentor: Geometry-Enhanced Cross-View Segmentation
Yulu Gao, Bohao Zhang, Zongheng Tang +3
Instance-level object segmentation across disparate egocentric and exocentric views is a fundamental challenge in visual understanding, critical for applications in embodied AI and…
CoST: Efficient Collaborative Perception From Unified Spatiotemporal Perspective
Zongheng Tang, Yi Liu, Yifan Sun +4
Collaborative perception shares information among different agents and helps solving problems that individual agents may face, e.g., occlusions and small sensing range. Prior metho…
Knowledge Distillation via Query Selection for Detection Transformer
Yi Liu, Luting Wang, Zongheng Tang +4
Transformers have revolutionized the object detection landscape by introducing DETRs, acclaimed for their simplicity and efficacy. Despite their advantages, the substantial size of…
Unleashing the Temporal-Spatial Reasoning Capacity of GPT for Training-Free Audio and Language Referenced Video Object Segmentation
Shaofei Huang, Rui Ling, Hongyu Li +5
In this paper, we propose an Audio-Language-Referenced SAM 2 (AL-Ref-SAM 2) pipeline to explore the training-free paradigm for audio and language-referenced video object segmentati…
DETR with Additional Global Aggregation for Cross-domain Weakly Supervised Object Detection
Zongheng Tang, Yifan Sun, Si Liu +1
This paper presents a DETR-based method for cross-domain weakly supervised object detection (CDWSOD), aiming at adapting the detector from source to target domain through weak supe…
Human-centric Spatio-Temporal Video Grounding With Visual Transformers
Zongheng Tang, Yue Liao, Si Liu +5
In this work, we introduce a novel task - Humancentric Spatio-Temporal Video Grounding (HC-STVG). Unlike the existing referring expression tasks in images or videos, by focusing on…