most citedNot All Features Matter: Enhancing Few-shot CLIP with Adaptive Prior Refinement

7 citations · 12 across the 6 of their papers we have counts for

collaborators

6 papers

cs.LG2023

On the Value of Myopic Behavior in Policy Reuse

Kang Xu, Chenjia Bai, Shuang Qiu +5

Leveraging learned strategies in unfamiliar scenarios is fundamental to human intelligence. In reinforcement learning, rationally reusing the policies acquired from other tasks or…

cs.CV20233 cited

One-Shot High-Fidelity Talking-Head Synthesis with Deformable Neural Radiance Field

Weichuang Li, Longhao Zhang, Dong Wang +7

Talking head generation aims to generate faces that maintain the identity information of the source image and imitate the motion of the driving image. Most pioneering methods rely…

cs.CV20237 cited

Not All Features Matter: Enhancing Few-shot CLIP with Adaptive Prior Refinement

Xiangyang Zhu, Renrui Zhang, Bowei He +4

The popularity of Contrastive Language-Image Pre-training (CLIP) has propelled its application to diverse downstream vision tasks. To improve its capacity on downstream tasks, few-…

cs.CV2023

Propagate And Calibrate: Real-time Passive Non-line-of-sight Tracking

Yihao Wang, Zhigang Wang, Bin Zhao +3

Non-line-of-sight (NLOS) tracking has drawn increasing attention in recent years, due to its ability to detect object motion out of sight. Most previous works on NLOS tracking rely…

eess.IV20232 cited

Fully Self-Supervised Depth Estimation from Defocus Clue

Haozhe Si, Bin Zhao, Dong Wang +4

Depth-from-defocus (DFD), modeling the relationship between depth and defocus pattern in images, has demonstrated promising performance in depth estimation. Recently, several self-…

cs.CV2022

RCLane: Relay Chain Prediction for Lane Detection

Shenghua Xu, Xinyue Cai, Bin Zhao +4

Lane detection is an important component of many real-world autonomous systems. Despite a wide variety of lane detection approaches have been proposed, reporting steady benchmark i…