5 papers
The SonicAGI System for the REAL-TSE Challenge
Kai Li, Wendi Sang, Jintao Cheng +1
Real-world target speaker extraction (TSE) remains challenging because target speech, interference, and enrollment are recorded under mismatched acoustic conditions with reverberat…
Not All Tasks Quantize Equally: Fisher-Guided Quantization for Visual Geometry Transformer
Yipu Zhang, Jintao Cheng, Weilun Feng +5
Feed-forward 3D reconstruction models, represented by Visual Geometry Grounded Transformer (VGGT), jointly predict multiple visual geometry tasks such as depth estimation, camera p…
Beyond First-Order: Learning Riemannian Geometries for Invariant Visual Place Recognition
Jintao Cheng, Weibin Li, Zhijian He +3
Visual Place Recognition (VPR) demands representations robust to drastic environmental and viewpoint shifts. Existing aggregation paradigms either depend on extensive supervised tr…
A Semantically Consistent Dataset for Data-Efficient Query-Based Universal Sound Separation
Kai Li, Jintao Cheng, Chang Zeng +5
Query-based universal sound separation is fundamental to intelligent auditory systems, aiming to isolate specific sources from mixtures. Despite recent advances, existing methods c…
VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization
Yipu Zhang, Jintao Cheng, Xingyu Liu +8
3D reconstruction and view synthesis are fundamental to AR/VR, robotics, and digital twins. The Visual Geometry Grounded Transformer (VGGT) enables strong feed-forward 3D reconstru…