4 citations · 9 across the 9 of their papers we have counts for
7 papers · 1 filter
Multimodal Learning on Low-Quality Data with Conformal Predictive Self-Calibration
Xun Jiang, Yufan Gu, Disen Hu +5
Multimodal learning often grapples with the challenge of low-quality data, which predominantly manifests as two facets: modality imbalance and noisy corruption. While these issues…
DMM: Disparity-guided Multispectral Mamba for Oriented Object Detection in Remote Sensing
Minghang Zhou, Tianyu Li, Chaofan Qiao +5
Multispectral oriented object detection faces challenges due to both inter-modal and intra-modal discrepancies. Recent studies often rely on transformer-based models to address the…
Anti-Collapse Loss for Deep Metric Learning Based on Coding Rate Metric
Xiruo Jiang, Yazhou Yao, Xili Dai +3
Deep metric learning (DML) aims to learn a discriminative high-dimensional embedding space for downstream tasks like classification, clustering, and retrieval. Prior literature pre…
Hierarchical Graph Pattern Understanding for Zero-Shot VOS
Gensheng Pei, Fumin Shen, Yazhou Yao +3
The optical flow guidance strategy is ideal for obtaining motion information of objects in the video. It is widely utilized in video segmentation tasks. However, existing optical f…
BatchNorm-based Weakly Supervised Video Anomaly Detection
Yixuan Zhou, Yi Qu, Xing Xu +3
In weakly supervised video anomaly detection (WVAD), where only video-level labels indicating the presence or absence of abnormal events are available, the primary challenge arises…
MSFlow: Multi-Scale Flow-based Framework for Unsupervised Anomaly Detection
Yixuan Zhou, Xing Xu, Jingkuan Song +2
Unsupervised anomaly detection (UAD) attracts a lot of research interest and drives widespread applications, where only anomaly-free samples are available for training. Some UAD ap…
Do-GOOD: Towards Distribution Shift Evaluation for Pre-Trained Visual Document Understanding Models
Jiabang He, Yi Hu, Lei Wang +4
Numerous pre-training techniques for visual document understanding (VDU) have recently shown substantial improvements in performance across a wide range of document tasks. However,…