D
Danfeng Qin
Researcher at Google
Publications - 12
Citations - 560
Danfeng Qin is an academic researcher from Google. The author has contributed to research in topics: Object detection & Image retrieval. The author has an hindex of 6, co-authored 11 publications receiving 451 citations. Previous affiliations of Danfeng Qin include ETH Zurich.
Papers
More filters
Proceedings ArticleDOI
Hello neighbor: Accurate object retrieval with k-reciprocal nearest neighbors
TL;DR: This paper introduces a simple yet effective method to improve visual word based image retrieval based on an analysis of the k-reciprocal nearest neighbor structure in the image space and demonstrates a significant improvement over standard bag-of-words retrieval.
Proceedings ArticleDOI
Query Adaptive Similarity for Large Scale Object Retrieval
TL;DR: This paper presents a probabilistic framework for modeling the feature to feature similarity measure, and proposes a function to score the individual contributions into an image to image similarity within the probabilism framework.
Book ChapterDOI
Improving Object Detection with Selective Self-supervised Self-training
TL;DR: A selective net is proposed to rectify the supervision signals in Web images and not only identifies positive bounding boxes but also creates a safe zone for mining hard negative boxes.
Proceedings ArticleDOI
Cap2Det: Learning to Amplify Weak Caption Supervision for Object Detection
TL;DR: This work shows how to squeeze the most information out of captions by training a text-only classifier that generalizes beyond dataset boundaries and provides an opportunity for learning detection models from noisy but more abundant and freely-available caption data.
Posted Content
Cap2Det: Learning to Amplify Weak Caption Supervision for Object Detection
TL;DR: In this paper, a text-only classifier is trained to generalize beyond the dataset boundaries to extract the most information out of the captions by training a text only classifier that generalizes beyond dataset boundaries.