Search Results for author: Boyang xia

Found 6 papers, 3 papers with code

NIERT: Accurate Numerical Interpolation through Unifying Scattered Data Representations using Transformer Encoder

1 code implementation19 Sep 2022 Shizhe Ding, Boyang xia, Milong Ren, Dongbo Bu

Interpolation for scattered data is a classical problem in numerical analysis, with a long history of theoretical and practical contributions.

Representation Learning

CODER: Coupled Diversity-Sensitive Momentum Contrastive Learning for Image-Text Retrieval

no code implementations21 Aug 2022 Haoran Wang, Dongliang He, Wenhao Wu, Boyang xia, Min Yang, Fu Li, Yunlong Yu, Zhong Ji, Errui Ding, Jingdong Wang

We introduce dynamic dictionaries for both modalities to enlarge the scale of image-text pairs, and diversity-sensitiveness is achieved by adaptive negative pair weighting.

Clustering Contrastive Learning +4

NSNet: Non-saliency Suppression Sampler for Efficient Video Recognition

no code implementations21 Jul 2022 Boyang xia, Wenhao Wu, Haoran Wang, Rui Su, Dongliang He, Haosen Yang, Xiaoran Fan, Wanli Ouyang

On the video level, a temporal attention module is learned under dual video-level supervisions on both the salient and the non-salient representations.

Action Recognition Video Classification +1

Temporal Saliency Query Network for Efficient Video Recognition

no code implementations21 Jul 2022 Boyang xia, Zhihao Wang, Wenhao Wu, Haoran Wang, Jungong Han

For each category, the common pattern of it is employed as a query and the most salient frames are responded to it.

Action Recognition Video Recognition

Temporal Action Proposal Generation with Background Constraint

1 code implementation15 Dec 2021 Haosen Yang, Wenhao Wu, Lining Wang, Sheng Jin, Boyang xia, Hongxun Yao, Hujie Huang

To evaluate the confidence of proposals, the existing works typically predict action score of proposals that are supervised by the temporal Intersection-over-Union (tIoU) between proposal and the ground-truth.

Temporal Action Proposal Generation

Cannot find the paper you are looking for? You can Submit a new open access paper.