works on

From the 1 of 8k papers with an AI index.

output
20022026
most citedThe automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations

7.9k citations

Showing 2021 · cs.CVShow all

45 papers · 2 filters

cs.CV2021★ 115 cited

Memory-Augmented Deep Unfolding Network for Compressive Sensing

Jiechong Song, Bin Chen, Jian Zhang

Mapping a truncated optimization method into a deep neural network, deep unfolding network (DUN) has attracted growing attention in compressive sensing (CS) due to its good interpr…

cs.CV2021★ 1 cited

PTQ-SL: Exploring the Sub-layerwise Post-training Quantization

Zhihang Yuan, Yiqi Chen, Chenhao Xue +3

Network quantization is a powerful technique to compress convolutional neural networks. The quantization granularity determines how to share the scaling factors in weights, which a…

cs.CV2021★ 61 cited

ASFormer: Transformer for Action Segmentation

Fangqiu Yi, Hongyu Wen, Tingting Jiang

Algorithms for the action segmentation task typically use temporal models to predict what action is occurring at each frame for a minute-long daily activity. Recent studies have sh…

cs.CV2021★ 14 cited

Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning

Hanzhe Hu, Fangyun Wei, Han Hu +3

Due to the limited and even imbalanced data, semi-supervised semantic segmentation tends to have poor performance on some certain categories, e.g., tailed categories in Cityscapes…

cs.CV2021

Context-LGM: Leveraging Object-Context Relation for Context-Aware Object Recognition

Mingzhou Liu, Xinwei Sun, Fandong Zhang +2

Context, as referred to situational factors related to the object of interest, can help infer the object's states or properties in visual recognition. As such contextual features a…

cs.CV2021★ 1 cited

Semantic Dense Reconstruction with Consistent Scene Segments

Yingcai Wan, Yanyan Li, Yingxuan You +3

In this paper, a method for dense semantic 3D scene reconstruction from an RGB-D sequence is proposed to solve high-level scene understanding tasks. First, each RGB-D pair is consi…