44 citations · 279 across the 23 of their papers we have counts for
25 papers
ScanWeaver: Compiler-Driven Parallelization of Affine Recurrences via Associative Scan Lowering
Qiying Wu, Pavel Zolnikov
Selective state-space models such as Mamba highlight the practical importance of input-dependent scan recurrences, which preserve linear-time sequence modeling while improving lang…
Identity-Consistent Aggregation for Video Object Detection
Chaorui Deng, Da Chen, Qi Wu
In Video Object Detection (VID), a common practice is to leverage the rich temporal contexts from the video to enhance the object representations in each frame. Existing methods tr…
Learning Distinct and Representative Styles for Image Captioning
Qi Chen, Chaorui Deng, Qi Wu
Over the years, state-of-the-art (SoTA) image captioning methods have achieved promising results on some evaluation metrics (e.g., CIDEr). However, recent findings show that the ca…
ClusTR: Exploring Efficient Self-attention via Clustering for Vision Transformers
Yutong Xie, Jianpeng Zhang, Yong Xia +2
Although Transformers have successfully transitioned from their language modelling origins to image-based applications, their quadratic computational complexity remains a challenge…
UniMiSS: Universal Medical Self-Supervised Learning via Breaking Dimensionality Barrier
Yutong Xie, Jianpeng Zhang, Yong Xia +1
Self-supervised learning (SSL) opens up huge opportunities for medical image analysis that is well known for its lack of annotations. However, aggregating massive (unlabeled) 3D me…
Towards Accurate Text-based Image Captioning with Content Diversity Exploration
Guanghui Xu, Shuaicheng Niu, Mingkui Tan +3
Text-based image captioning (TextCap) which aims to read and reason images with texts is crucial for a machine to understand a detailed and complex scene environment, considering t…