activity
20162023
most citedBLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation

871 citations · 3k across the 44 of their papers we have counts for

collaborators
Showing 2018Show all

7 papers · 1 filter

cs.CV20189 cited

DART: Domain-Adversarial Residual-Transfer Networks for Unsupervised Cross-Domain Image Classification

Xianghong Fang, Haoli Bai, Ziyi Guo +3

The accuracy of deep learning (e.g., convolutional neural networks) for an image classification task critically relies on the amount of labeled training data. Aiming to solve an im…

cs.CV2018305 cited

Robust Graph Learning from Noisy Data

Zhao Kang, Haiqi Pan, Steven C. H. Hoi +1

Learning graphs from data automatically has shown encouraging performance on clustering and semisupervised learning tasks. However, real data are often corrupted, which may cause t…

cs.CV2018

Question-Guided Hybrid Convolution for Visual Question Answering

Peng Gao, Pan Lu, Hongsheng Li +4

In this paper, we propose a novel Question-Guided Hybrid Convolution (QGHC) network for Visual Question Answering (VQA). Most state-of-the-art VQA methods fuse the high-level textu…

cs.LG2018

Adaptive Cost-sensitive Online Classification

Peilin Zhao, Yifan Zhang, Min Wu +3

Cost-Sensitive Online Classification has drawn extensive attention in recent years, where the main approach is to directly online optimize two well-known cost-sensitive metrics: (i…

cs.CV2018

Single-Shot Bidirectional Pyramid Networks for High-Quality Object Detection

Xiongwei Wu, Daoxin Zhang, Jianke Zhu +1

Recent years have witnessed many exciting achievements for object detection using deep learning techniques. Despite achieving significant progresses, most existing detectors are de…

cs.CR2018

URLNet: Learning a URL Representation with Deep Learning for Malicious URL Detection

Hung Le, Quang Pham, Doyen Sahoo +1

Malicious URLs host unsolicited content and are used to perpetrate cybercrimes. It is imperative to detect them in a timely manner. Traditionally, this is done through the usage of…