DevBench: A Comprehensive Benchmark for Software Development

1 code implementation • 13 Mar 2024 • Bowen Li, Wenhan Wu, Ziwei Tang, Lin Shi, John Yang, Jinyang Li, Shunyu Yao, Chen Qian, Binyuan Hui, Qicheng Zhang, Zhiyin Yu, He Du, Ping Yang, Dahua Lin, Chao Peng, Kai Chen

Recent advancements in large language models (LLMs) have significantly enhanced their coding capabilities.

Code Generation

Food-500 Cap: A Fine-Grained Food Caption Benchmark for Evaluating Vision-Language Models

1 code implementation • 6 Aug 2023 • Zheng Ma, Mianzhi Pan, Wenhan Wu, Kanzhi Cheng, Jianbing Zhang, ShuJian Huang, Jiajun Chen

Experiments on our proposed datasets demonstrate that popular VLMs underperform in the food domain compared with their performance in the general domain.

Part Aware Contrastive Learning for Self-Supervised Action Recognition

1 code implementation • 1 May 2023 • Yilei Hua, Wenhan Wu, Ce Zheng, Aidong Lu, Mengyuan Liu, Chen Chen, Shiqian Wu

This paper proposes an attention-based contrastive learning framework for skeleton representation learning, called SkeAttnCLR, which integrates local similarity and global features for skeleton-based action representations.

Contrastive Learning Data Augmentation +3

SkeletonMAE: Spatial-Temporal Masked Autoencoders for Self-supervised Skeleton Action Recognition

no code implementations • 1 Sep 2022 • Wenhan Wu, Yilei Hua, Ce Zheng, Shiqian Wu, Chen Chen, Aidong Lu

Given the unmasked skeleton sequence, the encoder is fine-tuned for the action recognition task.

Action Recognition Skeleton Based Action Recognition

Deep Learning-Based Human Pose Estimation: A Survey

1 code implementation • 24 Dec 2020 • Ce Zheng, Wenhan Wu, Chen Chen, Taojiannan Yang, Sijie Zhu, Ju Shen, Nasser Kehtarnavaz, Mubarak Shah

Furthermore, 2D and 3D human pose estimation datasets and evaluation metrics are included.

2D Human Pose Estimation 3D Human Pose Estimation +1