Search results

Section: Publications & Resources

Publication: IEEE Transactions on Image Processing

The bottleneck size $\beta $ is a crucial parameter that governs the trade-off between information compression and information preservation in information bottleneck (IB) theory. Existing technologi

Section: Publications & Resources

Publication: IEEE Transactions on Image Processing

RGBE tracking aims to integrate modality-aligned RGB and event features to perform temporal identity association and spatial localization of targets. Existing methods do not effectively mitigate the m

Section: Publications & Resources

Publication: IEEE Transactions on Image Processing

Generalizable vehicle re-identification (ReID) seeks to develop models capable of adapting to previously unseen domains without additional fine-tuning or retraining. Most existing approaches attempt t

Section: Publications & Resources

Publication: IEEE Transactions on Image Processing

As a paradigm in continual learning, class incremental learning (CIL) aims to assimilate tasks with mutually exclusive label spaces in sequence while preserving previously established knowledge. Mitig

Section: Publications & Resources

Publication: IEEE Transactions on Image Processing

We study the problem of lossy attribute compression, given encoded 3D point cloud geometry available at the decoder, in a multi-resolution B-spline projection framework. A target continuous 3D attribu

Section: Publications & Resources

Publication: IEEE Transactions on Image Processing

Computational optical imaging reconstructs signals from limited and noisy measurements, leading to ill-posed inverse problems that require regularization. Graph regularization (GR) has shown promise f

Section: Publications & Resources

Publication: IEEE Transactions on Image Processing

Traditional temporal action localization (TAL) methods rely on large amounts of detailed annotated data, whereas few-shot TAL reduces this dependence by using only a few training samples to identify u

Section: Publications & Resources

Publication: IEEE Transactions on Image Processing

Event cameras are increasingly used for Multiple Object Tracking (MOT), but their asynchronous event output often requires specialized methods. Existing processing methods primarily follow two paradig

Section: Publications & Resources

Publication: IEEE Transactions on Image Processing

Egocentric video-language understanding demands both high efficiency and accurate spatial-temporal modeling. Existing approaches face three key challenges: 1) Excessive pre-training cost arising from

Section: Publications & Resources

Publication: IEEE Transactions on Image Processing

Accurate medical image segmentation plays a vital role in clinical diagnostics by facilitating the precise delineation of anatomical structures and pathological regions. However, the performance of ex