Hongkai Xiong
- Papers
- 8
Cite
Notes
Only stored in your browser.
8papers
Authored papers
8UMG-CLIP: A Unified Multi-Granularity Vision Generalist for Open-World Understanding
arXiv 2024
Frequency-Aware Transformer for Learned Image Compression
arXiv 2023
Prune Spatio-temporal Tokens by Semantic-aware Temporal Accumulation
ICCV 2023 1
From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models
arXiv 2023
Betrayed by Attention: A Simple yet Effective Approach for Self-supervised Video Object Segmentation
arXiv 2023
Spatial-Temporal Transformer Networks for Traffic Flow Forecasting
arXiv 2020
PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search
ICLR 2020 1
Trained Rank Pruning for Efficient Deep Neural Networks
arXiv 2018
Affiliations
No known affiliations.
Frequent co-authors
10from 8 papers