Synthesize, Diagnose, and Optimize: Towards Fine-Grained Vision-Language Understanding

1 code implementation • 30 Nov 2023 • Wujian Peng, Sicheng Xie, Zuyao You, Shiyi Lan, Zuxuan Wu

With this in mind, we propose a simple yet effective approach to optimize VLMs in fine-grained understanding, achieving significant improvements on SPEC without compromising the zero-shot performance.

Attribute Compositional Zero-Shot Learning

Building an Open-Vocabulary Video CLIP Model with Better Architectures, Optimization and Data

1 code implementation • 8 Oct 2023 • Zuxuan Wu, Zejia Weng, Wujian Peng, Xitong Yang, Ang Li, Larry S. Davis, Yu-Gang Jiang

Despite significant results achieved by Contrastive Language-Image Pretraining (CLIP) in zero-shot image recognition, limited effort has been made exploring its potential for zero-shot video recognition.

Action Recognition Continual Learning +5

BMB: Balanced Memory Bank for Imbalanced Semi-supervised Learning

no code implementations • 22 May 2023 • Wujian Peng, Zejia Weng, Hengduo Li, Zuxuan Wu

Exploring a substantial amount of unlabeled data, semi-supervised learning (SSL) boosts the recognition performance when only a limited number of labels are provided.