75 citations · 157 across the 13 of their papers we have counts for
6 papers · 1 filter
STEERER: Resolving Scale Variations for Counting and Localization via Selective Inheritance Learning
Tao Han, Lei Bai, Lingbo Liu +1
Scale variation is a deep-rooted problem in object counting, which has not been effectively addressed by existing scale-aware algorithms. An important factor is that they typically…
Few-Shot Continual Learning via Flat-to-Wide Approaches
Muhammad Anwar Ma'sum, Mahardhika Pratama, Edwin Lughofer +3
Existing approaches on continual learning call for a lot of samples in their training processes. Such approaches are impractical for many real-world problems having limited samples…
Exploring Effective Mask Sampling Modeling for Neural Image Compression
Lin Liu, Mingming Zhao, Shanxin Yuan +5
Image compression aims to reduce the information redundancy in images. Most existing neural image compression methods rely on side information from hyperprior or context models to…
Joint Channel Estimation and Feedback with Masked Token Transformers in Massive MIMO Systems
Mingming Zhao, Lin Liu, Lifu Liu +2
The downlink channel state information (CSI) estimation and low overhead acquisition are the major challenges for massive MIMO systems in frequency division duplex to enable high M…
CLIP-Count: Towards Text-Guided Zero-Shot Object Counting
Ruixiang Jiang, Lingbo Liu, Changwen Chen
Recent advances in visual-language models have shown remarkable zero-shot text-image matching ability that is transferable to downstream tasks such as object detection and segmenta…
Visual Tuning
Bruce X. B. Yu, Jianlong Chang, Haixin Wang +9
Fine-tuning visual models has been widely shown promising performance on many downstream visual tasks. With the surprising development of pre-trained visual foundation models, visu…