activity
20172021
most citedTripletGAN: Training Generative Model with Triplet Loss

9 citations · 11 across the 4 of their papers we have counts for

collaborators

5 papers

cs.CV20211 cited

Boundary Knowledge Translation based Reference Semantic Segmentation

Lechao Cheng, Zunlei Feng, Xinchao Wang +3

Given a reference object of an unknown type in an image, human observers can effortlessly find the objects of the same category in another image and precisely tell their visual bou…

cs.CV20211 cited

Edge-competing Pathological Liver Vessel Segmentation with Limited Labels

Zunlei Feng, Zhonghua Wang, Xinchao Wang +5

The microvascular invasion (MVI) is a major prognostic factor in hepatocellular carcinoma, which is one of the malignant tumors with the highest mortality rate. The diagnosis of MV…

cs.CL2021

MTVR: Multilingual Moment Retrieval in Videos

Jie Lei, Tamara L. Berg, Mohit Bansal

We introduce mTVR, a large-scale multilingual video moment retrieval dataset, containing 218K English and Chinese queries from 21.8K TV show video clips. The dataset is collected b…

cs.CV2018

Selective Zero-Shot Classification with Augmented Attributes

Jie Song, Chengchao Shen, Jie Lei +4

In this paper, we introduce a selective zero-shot classification problem: how can the classifier avoid making dubious predictions? Existing attribute-based zero-shot classification…

cs.LG20179 cited

TripletGAN: Training Generative Model with Triplet Loss

Gongze Cao, Yezhou Yang, Jie Lei +3

As an effective way of metric learning, triplet loss has been widely used in many deep learning tasks, including face recognition and person-ReID, leading to many states of the art…