CVPR Poster Large-scale Multi-view Tensor Clustering with Implicit ...
To solve the resultant optimization problem, we design an efficient algorithm of linear complexity. Moreover, extensive experiments are conducted and corresponding results well support the …
CVPR 2025 Accepted Papers
This page is cached for 1 hour. Changes to affiliation or name in your local profile may take up to 60 minutes to appear here.
Track: Poster Session THU-PM
The resultant detector is dubbed Azimuth-equivariant Detector (AeDet). Extensive experiments are conducted on nuScenes, and AeDet achieves a 62.0% NDS, surpassing the recent multi-view 3D …
Track: Poster Session 4 & Exhibit Hall
The resultant dataset accumulates over 2000 hours of driving videos, spanning areas all over the world with diverse weather conditions and traffic scenarios. Inheriting the merits from recent latent diffusion …
AdaBM: On-the-Fly Adaptive Bit Mapping for Image Super-Resolution
However, despite the benefits of the resultant adaptive network, existing works rely on time-intensive quantization-aware training with full access to the original training pairs to learn the appropriate bit …
Track: Poster Session 6 & Exhibit Hall
WS obtains an approximate ensemble of numerous pruned models to perform model augmentation, which can be conveniently synergized with SASD to elevate the source model's generalization …
Track: Poster Session 1 & Exhibit Hall
We introduce SEAS, using ShapE-Aligned Supervision, to enhance appearance-based person re-identification. When recognizing an individual's identity, existing methods primarily rely on …
CVPR Poster SynSP: Synergy of Smoothness and Precision in Pose ...
Moreover, SynSP can also address multi-view poses of one person simultaneously, fixing inaccuracies in predicted poses through heightened attention to similar poses from other views, thereby amplifying …
CVPR 2024 Awards
Discover the recipients of CVPR 2024 awards, celebrating outstanding research in computer vision and pattern recognition.
CVPR Poster Patient-Level Anatomy Meets Scanning-Level Physics ...
Reducing radiation doses benefits patients, however, the resultant low-dose computed tomography (LDCT) images often suffer from clinically unacceptable noise and artifacts.