activity
20192026
most citedACIL: Analytic Class-Incremental Learning with Absolute Memorization and Privacy Protection

11 citations · 13 across the 7 of their papers we have counts for

collaborators

9 papers

cs.IR2026

Attribute-Prompted Kernel Hashing for Unsupervised Data-Efficient Cross-Modal Retrieval

Runhao Li, Xiaoxu Ma, Zhenyu Weng +5

Unsupervised cross-modal hashing enables efficient retrieval of semantically related instances across different modalities without requiring manual semantic annotation. However, ex…

cs.IR2026

Unsupervised Data-Efficient Cross-Modal Retrieval with Global-Neighborhood Alignment Hashing

Runhao Li, Xiaoxu Ma, Zhenyu Weng +5

Compared to supervised cross-modal hashing (CMH), unsupervised CMH reduces the reliance on manual labeling by learning binary codes from unlabeled image-text pairs. However, existi…

cs.CV2024

FACT: Feature Adaptive Continual-learning Tracker for Multiple Object Tracking

Rongzihan Song, Zhenyu Weng, Huiping Zhuang +3

Multiple object tracking (MOT) involves identifying multiple targets and assigning them corresponding IDs within a video sequence, where occlusions are often encountered. Recent me…

cs.DS2023

Constant Sequence Extension for Fast Search Using Weighted Hamming Distance

Zhenyu Weng, Huiping Zhuang, Haizhou Li +1

Representing visual data using compact binary codes is attracting increasing attention as binary codes are used as direct indices into hash table(s) for fast non-exhaustive search.…

cs.LG2022★ 1 cited

Mitigating Memorization of Noisy Labels by Clipping the Model Prediction

Hongxin Wei, Huiping Zhuang, Renchunzi Xie +4

In the presence of noisy labels, designing robust loss functions is critical for securing the generalization performance of deep neural networks. Cross Entropy (CE) loss has been s…

cs.LG2022★ 11 cited

ACIL: Analytic Class-Incremental Learning with Absolute Memorization and Privacy Protection

Huiping Zhuang, Zhenyu Weng, Hongxin Wei +3

Class-incremental learning (CIL) learns a classification model with training data of different classes arising progressively. Existing CIL either suffers from serious accuracy loss…