18 citations · 62 across the 9 of their papers we have counts for
7 papers · 1 filter
Learning a Condensed Frame for Memory-Efficient Video Class-Incremental Learning
Yixuan Pei, Zhiwu Qing, Jun Cen +6
Recent incremental learning for action recognition usually stores representative videos to mitigate catastrophic forgetting. However, only a few bulky videos can be stored due to t…
Generating Superpixels for High-resolution Images with Decoupled Patch Calibration
Yaxiong Wang, Yunchao Wei, Xueming Qian +2
Superpixel segmentation has recently seen important progress benefiting from the advances in differentiable deep learning. However, the very high-resolution superpixel segmentation…
Sketch-Guided Scenery Image Outpainting
Yaxiong Wang, Yunchao Wei, Xueming Qian +2
The outpainting results produced by existing approaches are often too random to meet users' requirement. In this work, we take the image outpainting one step forward by allowing us…
Crowd Scene Analysis by Output Encoding
Yao Xue, Siming Liu, Yonghui Li +1
Crowd scene analysis receives growing attention due to its wide applications. Grasping the accurate crowd location (rather than merely crowd count) is important for spatially ident…
Preparing Lessons: Improve Knowledge Distillation with Better Supervision
Tiancheng Wen, Shenqi Lai, Xueming Qian
Knowledge distillation (KD) is widely used for training a compact model with the supervision of another large model, which could effectively improve the performance. Previous metho…
VrR-VG: Refocusing Visually-Relevant Relationships
Yuanzhi Liang, Yalong Bai, Wei Zhang +3
Relationships encode the interactions among individual instances, and play a critical role in deep visual scene understanding. Suffering from the high predictability with non-visua…