162 citations · 896 across the 37 of their papers we have counts for
7 papers · 1 filter
Anchor Box Optimization for Object Detection
Yuanyi Zhong, Jianfeng Wang, Jian Peng +1
In this paper, we propose a general approach to optimize anchor boxes for object detection. Nowadays, anchor boxes are widely adopted in state-of-the-art detection frameworks. Howe…
Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation
Xin Wang, Qiuyuan Huang, Asli Celikyilmaz +5
Vision-language navigation (VLN) is the task of navigating an embodied agent to carry out natural language instructions inside real 3D environments. In this paper, we study how to…
Revisit Multinomial Logistic Regression in Deep Learning: Data Dependent Model Initialization for Image Recognition
Bowen Cheng, Rong Xiao, Yandong Guo +3
We study in this paper how to initialize the parameters of multinomial logistic regression (a fully connected layer followed with softmax and cross entropy loss), which is widely u…
AutoLoc: Weakly-supervised Temporal Action Localization
Zheng Shou, Hang Gao, Lei Zhang +2
Temporal Action Localization (TAL) in untrimmed video is important for many applications. But it is very expensive to annotate the segment-level ground truth (action class and temp…
Turbo Learning for Captionbot and Drawingbot
Qiuyuan Huang, Pengchuan Zhang, Dapeng Wu +1
We study in this paper the problems of both image captioning and text-to-image generation, and present a novel turbo learning approach to jointly training an image-to-text generato…
Generating Diverse and Accurate Visual Captions by Comparative Adversarial Learning
Dianqi Li, Qiuyuan Huang, Xiaodong He +2
We study how to generate captions that are not only accurate in describing an image but also discriminative across different images. The problem is both fundamental and interesting…
Real-time Burst Photo Selection Using a Light-Head Adversarial Network
Baoyuan Wang, Noranart Vesdapunt, Utkarsh Sinha +1
We present an automatic moment capture system that runs in real-time on mobile cameras. The system is designed to run in the viewfinder mode and capture a burst sequence of frames…