Spot Check Equivalence: an Interpretable Metric for Information Elicitation Mechanisms

no code implementations • 21 Feb 2024 • Shengwei Xu, Yichi Zhang, Paul Resnick, Grant Schoenebeck

However, different metrics lead to divergent and even contradictory results in various contexts.

Towards More Unified In-context Visual Understanding

no code implementations • 5 Dec 2023 • Dianmo Sheng, Dongdong Chen, Zhentao Tan, Qiankun Liu, Qi Chu, Jianmin Bao, Tao Gong, Bin Liu, Shengwei Xu, Nenghai Yu

Thanks to this design, the model is capable of handling in-context vision understanding tasks with multimodal output in a unified pipeline. Experimental results demonstrate that our model achieves competitive performance compared with specialized models and previous ICL baselines.

Decoder Image Captioning +2

Two-Stage Copy-Move Forgery Detection with Self Deep Matching and Proposal SuperGlue

1 code implementation • 16 Dec 2020 • Yaqi Liu, Chao Xia, Xiaobin Zhu, Shengwei Xu

The first stage is a backbone self deep matching network, and the second stage is named as Proposal SuperGlue.