Picture for Junhua Mao

Junhua Mao

Pedestrian Crossing Action Recognition and Trajectory Prediction with 3D Human Keypoints

Jun 01, 2023
Figure 1 for Pedestrian Crossing Action Recognition and Trajectory Prediction with 3D Human Keypoints
Figure 2 for Pedestrian Crossing Action Recognition and Trajectory Prediction with 3D Human Keypoints
Figure 3 for Pedestrian Crossing Action Recognition and Trajectory Prediction with 3D Human Keypoints
Figure 4 for Pedestrian Crossing Action Recognition and Trajectory Prediction with 3D Human Keypoints
Viaarxiv icon

Multi-modal 3D Human Pose Estimation with 2D Weak Supervision in Autonomous Driving

Dec 22, 2021
Figure 1 for Multi-modal 3D Human Pose Estimation with 2D Weak Supervision in Autonomous Driving
Figure 2 for Multi-modal 3D Human Pose Estimation with 2D Weak Supervision in Autonomous Driving
Figure 3 for Multi-modal 3D Human Pose Estimation with 2D Weak Supervision in Autonomous Driving
Figure 4 for Multi-modal 3D Human Pose Estimation with 2D Weak Supervision in Autonomous Driving
Viaarxiv icon

STINet: Spatio-Temporal-Interactive Network for Pedestrian Detection and Trajectory Prediction

May 08, 2020
Figure 1 for STINet: Spatio-Temporal-Interactive Network for Pedestrian Detection and Trajectory Prediction
Figure 2 for STINet: Spatio-Temporal-Interactive Network for Pedestrian Detection and Trajectory Prediction
Figure 3 for STINet: Spatio-Temporal-Interactive Network for Pedestrian Detection and Trajectory Prediction
Figure 4 for STINet: Spatio-Temporal-Interactive Network for Pedestrian Detection and Trajectory Prediction
Viaarxiv icon

Training and Evaluating Multimodal Word Embeddings with Large-scale Web Annotated Images

Nov 24, 2016
Figure 1 for Training and Evaluating Multimodal Word Embeddings with Large-scale Web Annotated Images
Figure 2 for Training and Evaluating Multimodal Word Embeddings with Large-scale Web Annotated Images
Figure 3 for Training and Evaluating Multimodal Word Embeddings with Large-scale Web Annotated Images
Figure 4 for Training and Evaluating Multimodal Word Embeddings with Large-scale Web Annotated Images
Viaarxiv icon

Attention Correctness in Neural Image Captioning

Add code
Nov 23, 2016
Figure 1 for Attention Correctness in Neural Image Captioning
Figure 2 for Attention Correctness in Neural Image Captioning
Figure 3 for Attention Correctness in Neural Image Captioning
Figure 4 for Attention Correctness in Neural Image Captioning
Viaarxiv icon

CNN-RNN: A Unified Framework for Multi-label Image Classification

Add code
Apr 15, 2016
Figure 1 for CNN-RNN: A Unified Framework for Multi-label Image Classification
Figure 2 for CNN-RNN: A Unified Framework for Multi-label Image Classification
Figure 3 for CNN-RNN: A Unified Framework for Multi-label Image Classification
Figure 4 for CNN-RNN: A Unified Framework for Multi-label Image Classification
Viaarxiv icon

Generation and Comprehension of Unambiguous Object Descriptions

Add code
Apr 11, 2016
Figure 1 for Generation and Comprehension of Unambiguous Object Descriptions
Figure 2 for Generation and Comprehension of Unambiguous Object Descriptions
Figure 3 for Generation and Comprehension of Unambiguous Object Descriptions
Figure 4 for Generation and Comprehension of Unambiguous Object Descriptions
Viaarxiv icon

Are You Talking to a Machine? Dataset and Methods for Multilingual Image Question Answering

Nov 02, 2015
Figure 1 for Are You Talking to a Machine? Dataset and Methods for Multilingual Image Question Answering
Figure 2 for Are You Talking to a Machine? Dataset and Methods for Multilingual Image Question Answering
Figure 3 for Are You Talking to a Machine? Dataset and Methods for Multilingual Image Question Answering
Figure 4 for Are You Talking to a Machine? Dataset and Methods for Multilingual Image Question Answering
Viaarxiv icon

Learning like a Child: Fast Novel Visual Concept Learning from Sentence Descriptions of Images

Add code
Oct 02, 2015
Figure 1 for Learning like a Child: Fast Novel Visual Concept Learning from Sentence Descriptions of Images
Figure 2 for Learning like a Child: Fast Novel Visual Concept Learning from Sentence Descriptions of Images
Figure 3 for Learning like a Child: Fast Novel Visual Concept Learning from Sentence Descriptions of Images
Figure 4 for Learning like a Child: Fast Novel Visual Concept Learning from Sentence Descriptions of Images
Viaarxiv icon

Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)

Add code
Jun 11, 2015
Figure 1 for Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)
Figure 2 for Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)
Figure 3 for Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)
Figure 4 for Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)
Viaarxiv icon