6 citations · 12 across the 9 of their papers we have counts for
5 papers · 1 filter
Pretrained Image-Text Models are Secretly Video Captioners
Chunhui Zhang, Yiren Jian, Zhongyu Ouyang +1
Developing video captioning models is computationally expensive. The dynamic nature of video also complicates the design of multimodal models that can effectively caption these seq…
Expedited Training of Visual Conditioned Language Generation via Redundancy Reduction
Yiren Jian, Tingkai Liu, Yunzhe Tao +3
In this paper, we introduce , a streamlined framework designed for the pre-training of visually conditioned language generation models with high computatio…
Bootstrapping Vision-Language Learning with Decoupled Language Pre-training
Yiren Jian, Chongyang Gao, Soroush Vosoughi
We present a novel methodology aimed at optimizing the application of frozen large language models (LLMs) for resource-intensive vision-language (VL) pre-training. The current para…
Label Hallucination for Few-Shot Classification
Yiren Jian, Lorenzo Torresani
Few-shot classification requires adapting knowledge learned from a large annotated base dataset to recognize novel unseen classes, each represented by few labeled examples. In such…
MetaPix: Domain Transfer for Semantic Segmentation by Meta Pixel Weighting
Yiren Jian, Chongyang Gao
Training a deep neural model for semantic segmentation requires collecting a large amount of pixel-level labeled data. To alleviate the data scarcity problem presented in the real…