output
20172020
most citedDIDFuse: Deep Image Decomposition for Infrared and Visible Image Fusion

328 citations

13 papers

cs.CV2020★ 27 cited

Counterfactual Samples Synthesizing for Robust Visual Question Answering

Long Chen, Xin Yan, Jun Xiao +3

Despite Visual Question Answering (VQA) has realized impressive progress over the last few years, today's VQA models tend to capture superficial linguistic correlations in the trai…

eess.IV2020★ 328 cited

DIDFuse: Deep Image Decomposition for Infrared and Visible Image Fusion

Zixiang Zhao, Shuang Xu, Chunxia Zhang +3

Infrared and visible image fusion, a hot topic in the field of image processing, aims at obtaining fused images keeping the advantages of source images. This paper proposes a novel…

cs.CV2019★ 2 cited

Adversarial Seeded Sequence Growing for Weakly-Supervised Temporal Action Localization

Chengwei Zhang, Yunlu Xu, Zhanzhan Cheng +4

Temporal action localization is an important yet challenging research topic due to its various applications. Since the frame-level or segment-level annotations of untrimmed videos…

cs.CV2019

REAPS: Towards Better Recognition of Fine-grained Images by Region Attending and Part Sequencing

Peng Zhang, Xinyu Zhu, Zhanzhan Cheng +2

Fine-grained image recognition has been a hot research topic in computer vision due to its various applications. The-state-of-the-art is the part/region-based approaches that first…

cs.CV2019★ 79 cited

Semantic-Guided Multi-Attention Localization for Zero-Shot Learning

Yizhe Zhu, Jianwen Xie, Zhiqiang Tang +2

Zero-shot learning extends the conventional object classification to the unseen class recognition by introducing semantic representations of classes. Existing approaches predominan…

cs.CV2018★ 9 cited

Segregated Temporal Assembly Recurrent Networks for Weakly Supervised Multiple Action Detection

Yunlu Xu, Chengwei Zhang, Zhanzhan Cheng +4

This paper proposes a segregated temporal assembly recurrent (STAR) network for weakly-supervised multiple action detection. The model learns from untrimmed videos with only superv…

cs.CV2018

Extreme Network Compression via Filter Group Approximation

Bo Peng, Wenming Tan, Zheyang Li +3

In this paper we propose a novel decomposition method based on filter group approximation, which can significantly reduce the redundancy of deep convolutional neural networks (CNNs…

cs.CV2018★ 62 cited

Gated Fusion Network for Joint Image Deblurring and Super-Resolution

Xinyi Zhang, Hang Dong, Zhe Hu +3

Single-image super-resolution is a fundamental task for vision applications to enhance the image quality with respect to spatial resolution. If the input image contains degraded pi…

cs.MM2018★ 8 cited

A practical convolutional neural network as loop filter for intra frame

Xiaodan Song, Jiabao Yao, Lulu Zhou +4

Loop filters are used in video coding to remove artifacts or improve performance. Recent advances in deploying convolutional neural network (CNN) to replace traditional loop filter…

cs.CV2018★ 64 cited

Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregation

Chao Li, Qiaoyong Zhong, Di Xie +1

Skeleton-based human action recognition has recently drawn increasing attentions with the availability of large-scale skeleton datasets. The most crucial factors for this task lie…

cs.CV2018★ 18 cited

Learning Descriptor Networks for 3D Shape Synthesis and Analysis

Jianwen Xie, Zilong Zheng, Ruiqi Gao +3

This paper proposes a 3D shape descriptor network, which is a deep convolutional energy-based model, for modeling volumetric shape patterns. The maximum likelihood training of the…

cs.CV2018★ 26 cited

Deep Co-Training for Semi-Supervised Image Recognition

Siyuan Qiao, Wei Shen, Zhishuai Zhang +2

In this paper, we study the problem of semi-supervised image recognition, which is to learn classifiers using both labeled and unlabeled images. We present Deep Co-Training, a deep…

cs.CV2017★ 14 cited

Single-Shot Object Detection with Enriched Semantics

Zhishuai Zhang, Siyuan Qiao, Cihang Xie +3

We propose a novel single shot object detection network named Detection with Enriched Semantics (DES). Our motivation is to enrich the semantics of object detection features within…