JM
Junhua Mao
cs.CVcs.LGcs.CLcs.AIcs.ROActive PatchAppearance Recognitioncs.NETexture Classification
On Valency
published · living versionsW_jyrd6hb8·v1 · currentpublished
Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)
with Wei Xu, Yi Yang, Jiang Wang, Zhiheng Huang +1
1 version
Preprints & journals
13 papers in the corpus · 2014–2025OpenAI GPT-5 System Card2601.03267v2 · Aaditya Singh, Adam Fry, Adam Perelman et al.2025 · 26 citationsarXiv
Pedestrian Crossing Action Recognition and Trajectory Prediction with 3D Human Keypoints2306.01075v1 · Jiachen Li, Xinwei Shi, Feiyu Chen et al.2023 · 23 citationsarXiv
Multi-modal 3D Human Pose Estimation with 2D Weak Supervision in Autonomous Driving2112.12141v1 · Jingxiao Zheng, Xinwei Shi, Alexander Gorban et al.2021 · 51 citationsarXiv
STINet: Spatio-Temporal-Interactive Network for Pedestrian Detection and Trajectory Prediction2005.04255v1 · Zhishuai Zhang, Jiyang Gao, Junhua Mao et al.2020 · 76 citationsCVPR 2020
Training and Evaluating Multimodal Word Embeddings with Large-scale Web Annotated Images1611.08321v1 · Junhua Mao, Jiajing Xu, Yushi Jing et al.2016 · 42 citationsarXiv
Attention Correctness in Neural Image Captioning1605.09553v2 · Chenxi Liu, Junhua Mao, Fei Sha et al.2016 · 207 citationsarXiv
CNN-RNN: A Unified Framework for Multi-label Image Classification1604.04573v1 · Jiang Wang, Yi Yang, Junhua Mao et al.2016 · 1,327 citationsarXiv
Generation and Comprehension of Unambiguous Object Descriptions1511.02283v3 · Junhua Mao, Jonathan Huang, Alexander Toshev et al.2015 · 1,215 citationsarXiv
Are You Talking to a Machine? Dataset and Methods for Multilingual Image Question Answering1505.05612v3 · Haoyuan Gao, Junhua Mao, Jie Zhou et al.2015 · 224 citationsarXiv
Learning like a Child: Fast Novel Visual Concept Learning from Sentence Descriptions of Images1504.06692v2 · Junhua Mao, Wei Xu, Yi Yang et al.2015 · 148 citationsarXiv
Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)1412.6632v5 · Junhua Mao, Wei Xu, Yi Yang et al.2014 · 1,041 citationsICLR 2015on Valency
Explain Images with Multimodal Recurrent Neural Networks1410.1090v1 · Junhua Mao, Wei Xu, Yi Yang et al.2014 · 350 citationsarXiv
An Active Patch Model for Real World Texture and Appearance Classification.25531013 · Mao, Junhua, Zhu, Jun, Yuille, Alan L2022 · 15 citationsComputer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision. 2014;8691:140-155
Career total: 23 works. 13 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.