activity
20162022
most citedHierarchical Neural Architecture Search for Deep Stereo Matching

230 citations · 505 across the 18 of their papers we have counts for

collaborators

24 papers

cs.CL2022

The Devil in Linear Transformer

Zhen Qin, XiaoDong Han, Weixuan Sun +4

Linear transformers aim to reduce the quadratic space-time complexity of vanilla transformers. However, they usually suffer from degraded performances on various tasks and corpus.…

cs.CV20222 cited

Linear Video Transformer with Feature Fixation

Kaiyue Lu, Zexiang Liu, Jianyuan Wang +8

Vision Transformers have achieved impressive performance in video classification, while suffering from the quadratic complexity caused by the Softmax attention mechanism. Some stud…

cs.SD20223 cited

Locality Matters: A Locality-Biased Linear Attention for Automatic Speech Recognition

Jingyu Sun, Guiping Zhong, Dinghao Zhou +2

Conformer has shown a great success in automatic speech recognition (ASR) on many public benchmarks. One of its crucial drawbacks is the quadratic time-space complexity with respec…

cs.CV20221 cited

Implicit Motion Handling for Video Camouflaged Object Detection

Xuelian Cheng, Huan Xiong, Deng-Ping Fan +4

We propose a new video camouflaged object detection (VCOD) framework that can exploit both short-term dynamics and long-term temporal consistency to detect camouflaged objects from…

cs.CL202265 cited

cosFormer: Rethinking Softmax in Attention

Zhen Qin, Weixuan Sun, Hui Deng +6

Transformer has shown great successes in natural language processing, computer vision, and audio processing. As one of its core components, the softmax attention helps to capture l…

cs.CV20213 cited

Memory-Free Generative Replay For Class-Incremental Learning

Xiaomeng Xin, Yiran Zhong, Yunzhong Hou +2

Regularization-based methods are beneficial to alleviate the catastrophic forgetting problem in class-incremental learning. With the absence of old task images, they often assume t…