会员服务
APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformers
Arxiv
0+阅读 · 4月3日
Learning Graph Quantized Tokenizers
Arxiv
0+阅读 · 4月2日
Efficient 3D Recognition with Event-driven Spike Sparse Convolution
Arxiv
0+阅读 · 4月2日
Learning Dual-Arm Push and Grasp Synergy in Dense Clutter
Arxiv
0+阅读 · 4月2日
HCMA-UNet: A Hybrid CNN-Mamba UNet with Axial Self-Attention for Efficient Breast Cancer Segmentation
HCMA-UNet: A Hybrid CNN-Mamba UNet with Axial Self-Attention for Efficient Breast Cancer Segmentation
Arxiv
0+阅读 · 4月1日
VidTwin: Video VAE with Decoupled Structure and Dynamics
VidTwin: Video VAE with Decoupled Structure and Dynamics
Arxiv
0+阅读 · 3月28日
Extending Silicon Lifetime: A Review of Design Techniques for Reliable Integrated Circuits
Arxiv
0+阅读 · 3月27日
Semi-Supervised Self-Learning Enhanced Music Emotion Recognition
Arxiv
0+阅读 · 3月27日
MEET: A Million-Scale Dataset for Fine-Grained Geospatial Scene Classification with Zoom-Free Remote Sensing Imagery
Arxiv
0+阅读 · 3月14日
Revisiting Point Cloud Completion: Are We Ready For The Real-World?
Arxiv
0+阅读 · 3月10日
Revisiting Point Cloud Completion: Are We Ready For The Real-World?
Arxiv
0+阅读 · 3月11日
Modulating CNN Features with Pre-Trained ViT Representations for Open-Vocabulary Object Detection
Arxiv
0+阅读 · 3月6日
A Light Perspective for 3D Object Detection
Arxiv
0+阅读 · 3月10日
CPAny: Couple With Any Encoder to Refer Multi-Object Tracking
Arxiv
0+阅读 · 3月10日
If At First You Don't Succeed: Test Time Re-ranking for Zero-shot, Cross-domain Retrieval
Arxiv
0+阅读 · 2月28日
参考链接
微信扫码咨询专知VIP会员
Top