From Pixels to Prose: A Large Dataset of Dense Image Captions

no code implementations • 14 Jun 2024 • Vasu Singla, Kaiyu Yue, Sukriti Paul, Reza Shirkavand, Mayuka Jayawardhana, Alireza Ganjdanesh, Heng Huang, Abhinav Bhatele, Gowthami Somepalli, Tom Goldstein

Training large vision-language models requires extensive, high-quality image-text pairs.

Image Captioning

Object Recognition as Next Token Prediction

1 code implementation • CVPR 2024 • Kaiyu Yue, Bor-Chun Chen, Jonas Geiping, Hengduo Li, Tom Goldstein, Ser-Nam Lim

We present an approach to pose object recognition as next token prediction.

Decoder Language Modelling +2

Matching Guided Distillation

1 code implementation • ECCV 2020 • Kaiyu Yue, Jiangfan Deng, Feng Zhou

However, this introduces two problems: a) The adaptation module brings more parameters into training.

Visible Feature Guidance for Crowd Pedestrian Detection

no code implementations • 23 Aug 2020 • Zhida Huang, Kaiyu Yue, Jiangfan Deng, Feng Zhou

Then we perform NMS only on visible bounding boxes to achieve the best fitting full box in inference.

Pedestrian Detection

Compact Generalized Non-local Network

2 code implementations • NeurIPS 2018 • Kaiyu Yue, Ming Sun, Yuchen Yuan, Feng Zhou, Errui Ding, Fuxin Xu

The non-local module is designed for capturing long-range spatio-temporal dependencies in images and videos.

Object Detection Object Recognition +1

Fine-grained Video Categorization with Redundancy Reduction Attention

no code implementations • ECCV 2018 • Chen Zhu, Xiao Tan, Feng Zhou, Xiao Liu, Kaiyu Yue, Errui Ding, Yi Ma

Specifically, it firstly summarizes the video by weight-summing all feature vectors in the feature maps of selected frames with a spatio-temporal soft attention, and then predicts which channels to suppress or to enhance according to this summary with a learned non-linear transform.

Action Recognition Video Classification